Initial commit

Pyramids.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:597c324525ed84474cba8b9ccfd56dce5e9b267e7deb4a7f19bde7df399b6b2e
+size 1420238

Pyramids/Pyramids-1000033.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:597c324525ed84474cba8b9ccfd56dce5e9b267e7deb4a7f19bde7df399b6b2e
+size 1420238

Pyramids/Pyramids-1000033.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e05831a12215cafb1c7267bea586a41dedfefacd9bbc976944ab4c6fb4e8e9d4
+size 8656731

Pyramids/Pyramids-16000.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14b32dc00fd73b9d3e26b40bf3c529c4a1a74099860638703eaa2e839083c8f1
+size 1420238

Pyramids/Pyramids-16000.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fa638357046aee91ed86380d4c5998726a023a70b1e646942b91b6c7f3c367a
+size 8656569

Pyramids/Pyramids-499929.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f926157b030519a459690dbcb23208075eb099eb9a4b20517c6c03fa455bb9e0
+size 1420238

Pyramids/Pyramids-499929.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1f3bb88ff43109ffa52ae1f79d31079b20518bef7fecbbd6f06eeafec8d1850
+size 8656650

Pyramids/Pyramids-999905.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:597c324525ed84474cba8b9ccfd56dce5e9b267e7deb4a7f19bde7df399b6b2e
+size 1420238

Pyramids/Pyramids-999905.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c42248e34a9391621aa1bb2497e6dac2e9b460db045f8ceaf2564e22c5b547d5
+size 8656650

Pyramids/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3c7f5fd0b594ae9e9fd7e7458e91d669f3d67ef2d0df8e8e82842351d867136
+size 8656181

Pyramids/events.out.tfevents.1751406805.DESKTOP-DJ85P97.30552.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1a951bcb4bf8f2a8ac2983409c34092c87246c7fddba3fb92b938526914b0b7
+size 1423

Pyramids/events.out.tfevents.1751406870.DESKTOP-DJ85P97.30694.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aca57745b4f78bc3a02e376d368ff99738786d453d2039eeaba0c2516e25d764
+size 323495

README.md

@@ -1,14 +1,14 @@
 ---
 library_name: ml-agents
 tags:
-- SnowballTarget
+- Pyramids
 - deep-reinforcement-learning
 - reinforcement-learning
-- ML-Agents-SnowballTarget
+- ML-Agents-Pyramids
 ---
 
-  # **ppo** Agent playing **SnowballTarget**
-  This is a trained model of a **ppo** agent playing **SnowballTarget**
+  # **ppo** Agent playing **Pyramids**
+  This is a trained model of a **ppo** agent playing **Pyramids**
   using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
 
   ## Usage (with ML-Agents)

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 1000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -1,12 +1,12 @@
 default_settings: null
 behaviors:
-  SnowballTarget:
+  Pyramids:
     trainer_type: ppo
     hyperparameters:
       batch_size: 128
       buffer_size: 2048
       learning_rate: 0.0003
-      beta: 0.005
+      beta: 0.01
       epsilon: 0.2
       lambd: 0.95
       num_epoch: 3
@@ -14,10 +14,10 @@ behaviors:
       learning_rate_schedule: linear
       beta_schedule: linear
       epsilon_schedule: linear
-    checkpoint_interval: 50000
+    checkpoint_interval: 500000
     network_settings:
       normalize: false
-      hidden_units: 256
+      hidden_units: 512
       num_layers: 2
       vis_encode_type: simple
       memory: null
@@ -35,17 +35,30 @@ behaviors:
           memory: null
           goal_conditioning_type: hyper
           deterministic: false
+      rnd:
+        gamma: 0.99
+        strength: 0.01
+        network_settings:
+          normalize: false
+          hidden_units: 64
+          num_layers: 3
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+        learning_rate: 0.0001
+        encoding_size: null
     init_path: null
-    keep_checkpoints: 10
+    keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 200000
-    time_horizon: 64
-    summary_freq: 10000
+    max_steps: 1000000
+    time_horizon: 128
+    summary_freq: 30000
     threaded: false
     self_play: null
     behavioral_cloning: null
 env_settings:
-  env_path: ./training-envs-executables/linux/SnowballTarget/SnowballTarget
+  env_path: ./training-envs-executables/linux/Pyramids/Pyramids
   env_args: null
   base_port: 5005
   num_envs: 1
@@ -66,10 +79,10 @@ engine_settings:
   no_graphics_monitor: false
 environment_parameters: null
 checkpoint_settings:
-  run_id: SnowballTarget1
+  run_id: Pyramids Training
   initialize_from: null
   load_model: false
-  resume: false
+  resume: true
   force: false
   train_model: false
   inference: false

run_logs/Player-0.log

@@ -1,12 +1,11 @@
-Mono path[0] = '/home/cogollo/RLCourse/Unit 5/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/Managed'
-Mono config path = '/home/cogollo/RLCourse/Unit 5/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
+Mono path[0] = '/home/cogollo/RLCourse/Unit 5/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
+Mono config path = '/home/cogollo/RLCourse/Unit 5/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
+Found 1 interfaces on host : 0) 172.31.161.172
+Multi-casting "[IP] 172.31.161.172 [Port] 55038 [Flags] 2 [Guid] 629710086 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.31.161.172) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
-PlayerPrefs - Creating folder: /home/cogollo/.config/unity3d/Hugging Face
-PlayerPrefs - Creating folder: /home/cogollo/.config/unity3d/Hugging Face/SnowballTarget
-Unable to load player prefs
-Initialize engine version: 2021.3.14f1 (eee1884e7226)
-[Subsystems] Discovering subsystems at path /home/cogollo/RLCourse/Unit 5/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
+Initialize engine version: 2021.3.5f1 (40eb3a945986)
+[Subsystems] Discovering subsystems at path /home/cogollo/RLCourse/Unit 5/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/UnitySubsystems
 Forcing GfxDevice: Null
 GfxDevice: creating device client; threaded=0; jobified=0
 NullGfxDevice:
@@ -14,10 +13,31 @@ NullGfxDevice:
     Renderer: Null Device
     Vendor:   Unity Technologies
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.172 seconds
+- Completed reload, in  0.078 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Autodesk Interactive shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+WARNING: Shader Unsupported: 'Legacy Shaders/Diffuse' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Legacy Shaders/Diffuse shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Legacy Shaders/Diffuse' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+WARNING: Shader Unsupported: 'ML-Agents/GridPattern' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader ML-Agents/GridPattern shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'ML-Agents/GridPattern' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
@@ -25,95 +45,105 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 1.238800 ms
+UnloadTime: 0.634200 ms
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
 Setting up 3 worker threads for Enlighten.
-Memory Statistics:
+PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 5367 frames, [16.0 KB-32.0 KB]: 90 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 2949 frames, [32.0 KB-64.0 KB]: 12189 frames, [64.0 KB-128.0 KB]: 3329 frames, [2.0 MB-4.0 MB]: 1 frames
       Initial Block Size 4.0 MB
       Current Block Size 4.0 MB
       Peak Allocated Bytes 2.0 MB
       Overflow Count 0
-    [ALLOC_TEMP_Loading.AsyncRead]
-      Initial Block Size 64.0 KB
-      Current Block Size 64.0 KB
-      Peak Allocated Bytes 240 B
-      Overflow Count 0
-    [ALLOC_TEMP_Loading.PreloadManager]
-      Initial Block Size 256.0 KB
-      Current Block Size 304.0 KB
-      Peak Allocated Bytes 228.9 KB
-      Overflow Count 4
     [ALLOC_TEMP_Background Job.Worker 8]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 9]
+    [ALLOC_TEMP_Background Job.Worker 10]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 0]
+    [ALLOC_TEMP_Job.Worker 4]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 3.6 KB
+      Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 10]
+    [ALLOC_TEMP_Background Job.Worker 6]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 14]
+    [ALLOC_TEMP_Background Job.Worker 1]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 6]
+    [ALLOC_TEMP_Background Job.Worker 11]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 4]
-      Initial Block Size 256.0 KB
-      Current Block Size 256.0 KB
-      Peak Allocated Bytes 3.6 KB
-      Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 3]
-      Initial Block Size 256.0 KB
-      Current Block Size 256.0 KB
-      Peak Allocated Bytes 3.6 KB
-      Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 12]
+    [ALLOC_TEMP_Background Job.Worker 3]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_EnlightenWorker] x 3
+    [ALLOC_TEMP_BatchDeleteObjects]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 15]
+    [ALLOC_TEMP_AUDIO_FMOD stream thread]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 2]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 1]
+    [ALLOC_TEMP_Background Job.Worker 7]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 2]
+    [ALLOC_TEMP_Background Job.Worker 15]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 7]
+    [ALLOC_TEMP_Job.Worker 1]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0.8 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 320.0 KB
+      Peak Allocated Bytes 251.6 KB
+      Overflow Count 4
+    [ALLOC_TEMP_AUDIO_FMOD PulseAudio Mixer]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Profiler.Dispatcher]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 3]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 12]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -133,58 +163,69 @@ Memory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 1]
-      Initial Block Size 256.0 KB
-      Current Block Size 256.0 KB
-      Peak Allocated Bytes 3.6 KB
-      Overflow Count 0
     [ALLOC_TEMP_Job.Worker 2]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 3.6 KB
+      Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 3]
+    [ALLOC_TEMP_Background Job.Worker 0]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 11]
+    [ALLOC_TEMP_Background Job.Worker 4]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 0]
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 9]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 4]
+    [ALLOC_TEMP_Background Job.Worker 14]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_BatchDeleteObjects]
+    [ALLOC_TEMP_EnlightenWorker] x 3
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 128 B
+      Overflow Count 0
+[ALLOC_MEMORYPROFILER]
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18169 frames
+  Requested Block Size 1.0 MB
+  Peak Block count 2
+  Peak Allocated memory 1.6 MB
+  Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 37
+  Peak main deferred allocation count 12968
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.0 MB
+      Peak Allocated bytes 1.7 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [4.0 MB-8.0 MB]: 5458 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18467 frames
       Requested Block Size 16.0 MB
-      Peak Block count 1
-      Peak Allocated memory 6.8 MB
+      Peak Block count 3
+      Peak Allocated memory 30.9 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 5458 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 18468 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.6 MB
+      Peak Allocated memory 25.0 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -211,52 +252,63 @@ Memory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.0 MB
+      Peak Allocated bytes 1.7 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 4978 frames, [64.0 KB-128.0 KB]: 480 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 18467 frames, [64.0 KB-128.0 KB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 66.4 KB
+      Peak Allocated memory 67.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 5458 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 18468 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 39.6 KB
+      Peak Allocated memory 67.7 KB
       Peak Large allocation bytes 0 B
 [ALLOC_CACHEOBJECTS] Dual Thread Allocator
-  Peak main deferred allocation count 0
+  Peak main deferred allocation count 1
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.0 MB
+      Peak Allocated bytes 1.7 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 5458 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18169 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
-      Peak Allocated memory 0.6 MB
+      Peak Allocated memory 1.4 MB
       Peak Large allocation bytes 0 B
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 5457 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 18467 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
-      Peak Block count 1
-      Peak Allocated memory 2.2 MB
+      Peak Block count 2
+      Peak Allocated memory 4.7 MB
       Peak Large allocation bytes 0 B
 [ALLOC_TYPETREE] Dual Thread Allocator
   Peak main deferred allocation count 0
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.0 MB
+      Peak Allocated bytes 1.7 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 5458 frames
+      Peak usage frame count: [0-1.0 KB]: 18468 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_TYPETREE_THREAD]
-      Peak usage frame count: [1.0 KB-2.0 KB]: 5458 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 18468 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
-      Peak Allocated memory 1.7 KB
+      Peak Allocated memory 1.9 KB
       Peak Large allocation bytes 0 B
+[ALLOC_PROFILER]
+  Peak usage frame count: [16.0 KB-32.0 KB]: 18468 frames
+  Requested Block Size 16.0 MB
+  Peak Block count 1
+  Peak Allocated memory 30.7 KB
+  Peak Large allocation bytes 0 B
+    [ALLOC_PROFILER_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 396 B
+##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1751408842735,"processId":30722,"allocatedMemory":2034839,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":73418},{"Thread":34572},{"Manager":12847},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3548},{"DynamicArray":30868},{"HashMap":7680},{"Utility":2992},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}

run_logs/timers.json

@@ -1,214 +1,250 @@
 {
     "name": "root",
     "gauges": {
-        "SnowballTarget.Policy.Entropy.mean": {
-            "value": 0.8752543926239014,
-            "min": 0.8752543926239014,
-            "max": 2.870757818222046,
-            "count": 20
+        "Pyramids.Policy.Entropy.mean": {
+            "value": 0.43157386779785156,
+            "min": 0.43157386779785156,
+            "max": 1.1835137605667114,
+            "count": 33
         },
-        "SnowballTarget.Policy.Entropy.sum": {
-            "value": 8318.41796875,
-            "min": 8318.41796875,
-            "max": 29304.6953125,
-            "count": 20
+        "Pyramids.Policy.Entropy.sum": {
+            "value": 12954.12109375,
+            "min": 12954.12109375,
+            "max": 33916.4375,
+            "count": 33
         },
-        "SnowballTarget.Step.mean": {
-            "value": 199984.0,
-            "min": 9952.0,
-            "max": 199984.0,
-            "count": 20
+        "Pyramids.Step.mean": {
+            "value": 989948.0,
+            "min": 29952.0,
+            "max": 989948.0,
+            "count": 33
         },
-        "SnowballTarget.Step.sum": {
-            "value": 199984.0,
-            "min": 9952.0,
-            "max": 199984.0,
-            "count": 20
+        "Pyramids.Step.sum": {
+            "value": 989948.0,
+            "min": 29952.0,
+            "max": 989948.0,
+            "count": 33
         },
-        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 12.726642608642578,
-            "min": 0.49879372119903564,
-            "max": 12.726642608642578,
-            "count": 20
+        "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.6525560021400452,
+            "min": -0.19506368041038513,
+            "max": 0.6525560021400452,
+            "count": 33
         },
-        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 2481.6953125,
-            "min": 96.76598358154297,
-            "max": 2577.39453125,
-            "count": 20
+        "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 185.32589721679688,
+            "min": -26.498668670654297,
+            "max": 185.32589721679688,
+            "count": 33
         },
-        "SnowballTarget.Losses.PolicyLoss.mean": {
-            "value": 0.06730769544596757,
-            "min": 0.061559674127470224,
-            "max": 0.07374301972278559,
-            "count": 20
+        "Pyramids.Policy.RndValueEstimate.mean": {
+            "value": -0.018126411363482475,
+            "min": -0.032225046306848526,
+            "max": 0.47743427753448486,
+            "count": 33
         },
-        "SnowballTarget.Losses.PolicyLoss.sum": {
-            "value": 0.2692307817838703,
-            "min": 0.2462386965098809,
-            "max": 0.3687150986139279,
-            "count": 20
+        "Pyramids.Policy.RndValueEstimate.sum": {
+            "value": -5.1479010581970215,
+            "min": -8.86188793182373,
+            "max": 86.08393859863281,
+            "count": 33
         },
-        "SnowballTarget.Losses.ValueLoss.mean": {
-            "value": 0.18663179523804607,
-            "min": 0.12328974780964427,
-            "max": 0.3032238807748346,
-            "count": 20
+        "Pyramids.Losses.PolicyLoss.mean": {
+            "value": 0.07054435086964188,
+            "min": 0.06523563337072523,
+            "max": 0.0744501472680565,
+            "count": 33
         },
-        "SnowballTarget.Losses.ValueLoss.sum": {
-            "value": 0.7465271809521843,
-            "min": 0.4931589912385771,
-            "max": 1.516119403874173,
-            "count": 20
+        "Pyramids.Losses.PolicyLoss.sum": {
+            "value": 0.9876209121749863,
+            "min": 0.1957069001121757,
+            "max": 1.0574157290102448,
+            "count": 33
         },
-        "SnowballTarget.Policy.LearningRate.mean": {
-            "value": 8.082097306000005e-06,
-            "min": 8.082097306000005e-06,
-            "max": 0.000291882002706,
-            "count": 20
+        "Pyramids.Losses.ValueLoss.mean": {
+            "value": 0.015353312257278501,
+            "min": 0.0007061740459281193,
+            "max": 0.01610820238004505,
+            "count": 33
         },
-        "SnowballTarget.Policy.LearningRate.sum": {
-            "value": 3.232838922400002e-05,
-            "min": 3.232838922400002e-05,
-            "max": 0.00138516003828,
-            "count": 20
+        "Pyramids.Losses.ValueLoss.sum": {
+            "value": 0.21494637160189903,
+            "min": 0.008058103971658662,
+            "max": 0.2255148333206307,
+            "count": 33
         },
-        "SnowballTarget.Policy.Epsilon.mean": {
-            "value": 0.10269400000000001,
-            "min": 0.10269400000000001,
-            "max": 0.19729400000000002,
-            "count": 20
+        "Pyramids.Policy.LearningRate.mean": {
+            "value": 7.751711701842858e-06,
+            "min": 7.751711701842858e-06,
+            "max": 0.00029274240241920004,
+            "count": 33
         },
-        "SnowballTarget.Policy.Epsilon.sum": {
-            "value": 0.41077600000000003,
-            "min": 0.41077600000000003,
-            "max": 0.96172,
-            "count": 20
+        "Pyramids.Policy.LearningRate.sum": {
+            "value": 0.00010852396382580002,
+            "min": 0.00010852396382580002,
+            "max": 0.0036326677891107993,
+            "count": 33
         },
-        "SnowballTarget.Policy.Beta.mean": {
-            "value": 0.0001444306000000001,
-            "min": 0.0001444306000000001,
-            "max": 0.0048649706,
-            "count": 20
+        "Pyramids.Policy.Epsilon.mean": {
+            "value": 0.10258387142857142,
+            "min": 0.10258387142857142,
+            "max": 0.19758080000000003,
+            "count": 33
         },
-        "SnowballTarget.Policy.Beta.sum": {
-            "value": 0.0005777224000000004,
-            "min": 0.0005777224000000004,
-            "max": 0.023089828,
-            "count": 20
+        "Pyramids.Policy.Epsilon.sum": {
+            "value": 1.4361742,
+            "min": 0.5927424000000001,
+            "max": 2.6108892000000004,
+            "count": 33
         },
-        "SnowballTarget.Environment.EpisodeLength.mean": {
-            "value": 199.0,
-            "min": 199.0,
-            "max": 199.0,
-            "count": 20
+        "Pyramids.Policy.Beta.mean": {
+            "value": 0.00026812875571428576,
+            "min": 0.00026812875571428576,
+            "max": 0.00975832192,
+            "count": 33
         },
-        "SnowballTarget.Environment.EpisodeLength.sum": {
-            "value": 8756.0,
-            "min": 8756.0,
-            "max": 10945.0,
-            "count": 20
+        "Pyramids.Policy.Beta.sum": {
+            "value": 0.0037538025800000004,
+            "min": 0.0037538025800000004,
+            "max": 0.12110783107999999,
+            "count": 33
         },
-        "SnowballTarget.Environment.CumulativeReward.mean": {
-            "value": 25.727272727272727,
-            "min": 3.7954545454545454,
-            "max": 25.727272727272727,
-            "count": 20
+        "Pyramids.Losses.RNDLoss.mean": {
+            "value": 0.01063509937375784,
+            "min": 0.010519095696508884,
+            "max": 0.2793361246585846,
+            "count": 33
         },
-        "SnowballTarget.Environment.CumulativeReward.sum": {
-            "value": 1132.0,
-            "min": 167.0,
-            "max": 1371.0,
-            "count": 20
+        "Pyramids.Losses.RNDLoss.sum": {
+            "value": 0.1488913893699646,
+            "min": 0.14726734161376953,
+            "max": 1.2707055807113647,
+            "count": 33
         },
-        "SnowballTarget.Policy.ExtrinsicReward.mean": {
-            "value": 25.727272727272727,
-            "min": 3.7954545454545454,
-            "max": 25.727272727272727,
-            "count": 20
-        },
-        "SnowballTarget.Policy.ExtrinsicReward.sum": {
-            "value": 1132.0,
-            "min": 167.0,
-            "max": 1371.0,
-            "count": 20
-        },
-        "SnowballTarget.IsTraining.mean": {
+        "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 20
+            "count": 33
         },
-        "SnowballTarget.IsTraining.sum": {
+        "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 20
+            "count": 33
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 299.45631067961165,
+            "min": 299.45631067961165,
+            "max": 999.0,
+            "count": 32
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 30844.0,
+            "min": 24318.0,
+            "max": 33372.0,
+            "count": 32
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.6798764544666982,
+            "min": -1.0000000521540642,
+            "max": 1.6798764544666982,
+            "count": 32
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 171.34739835560322,
+            "min": -32.000001668930054,
+            "max": 171.34739835560322,
+            "count": 32
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.6798764544666982,
+            "min": -1.0000000521540642,
+            "max": 1.6798764544666982,
+            "count": 32
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 171.34739835560322,
+            "min": -32.000001668930054,
+            "max": 171.34739835560322,
+            "count": 32
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.03312544703201674,
+            "min": 0.03312544703201674,
+            "max": 2.579658311791718,
+            "count": 32
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 3.3787955972657073,
+            "min": 3.065735498068534,
+            "max": 82.54906597733498,
+            "count": 32
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1751405822",
+        "start_time_seconds": "1751406869",
         "python_version": "3.10.18 (main, Jun  4 2025, 08:56:00) [GCC 13.3.0]",
-        "command_line_arguments": "/home/cogollo/mlagents_env/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
+        "command_line_arguments": "/home/cogollo/mlagents_env/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --resume",
         "mlagents_version": "1.2.0.dev0",
         "mlagents_envs_version": "1.2.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.7.1+cu126",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1751406265"
+        "end_time_seconds": "1751408842"
     },
-    "total": 417.07360755499394,
+    "total": 1856.999686985997,
     "count": 1,
-    "self": 0.2710036929929629,
+    "self": 0.31932419499207754,
     "children": {
         "run_training.setup": {
-            "total": 0.02634564299660269,
+            "total": 0.021418308999272995,
             "count": 1,
-            "self": 0.02634564299660269
+            "self": 0.021418308999272995
         },
         "TrainerController.start_learning": {
-            "total": 416.7762582190044,
+            "total": 1856.6589444820056,
             "count": 1,
-            "self": 0.32326647778972983,
+            "self": 1.2493460242112633,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 4.07515343400155,
+                    "total": 2.5361245889944257,
                     "count": 1,
-                    "self": 4.07515343400155
+                    "self": 2.5361245889944257
                 },
                 "TrainerController.advance": {
-                    "total": 412.28849097521015,
-                    "count": 18192,
-                    "self": 0.34006819097703556,
+                    "total": 1852.7811810717976,
+                    "count": 63022,
+                    "self": 1.1899232625946752,
                     "children": {
                         "env_step": {
-                            "total": 271.70272140239103,
-                            "count": 18192,
-                            "self": 157.74910049094615,
+                            "total": 1042.043702635463,
+                            "count": 63022,
+                            "self": 779.9959552165164,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 113.73539778144914,
-                                    "count": 18192,
-                                    "self": 1.3056365732918493,
+                                    "total": 261.22081486089155,
+                                    "count": 63022,
+                                    "self": 4.396588633302599,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 112.42976120815729,
-                                            "count": 18192,
-                                            "self": 112.42976120815729
+                                            "total": 256.82422622758895,
+                                            "count": 61558,
+                                            "self": 256.82422622758895
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.21822312999574933,
-                                    "count": 18192,
+                                    "total": 0.8269325580549776,
+                                    "count": 63022,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 415.81698639861133,
-                                            "count": 18192,
+                                            "total": 1854.0195414528062,
+                                            "count": 63022,
                                             "is_parallel": true,
-                                            "self": 279.7954934797817,
+                                            "self": 1156.042825190416,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -217,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0030962630044086836,
+                                                            "total": 0.0018153179989894852,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0018048600031761453,
+                                                            "self": 0.0007114139953046106,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0012914030012325384,
-                                                                    "count": 10,
+                                                                    "total": 0.0011039040036848746,
+                                                                    "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0012914030012325384
+                                                                    "self": 0.0011039040036848746
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.01975389699509833,
+                                                            "total": 0.027480443997774273,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0002452120024827309,
+                                                            "self": 0.00023723299818811938,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00018277999333804473,
+                                                                    "total": 0.00018620800256030634,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00018277999333804473
+                                                                    "self": 0.00018620800256030634
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.01844679200439714,
+                                                                    "total": 0.026354200999776367,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.01844679200439714
+                                                                    "self": 0.026354200999776367
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0008791129948804155,
+                                                                    "total": 0.0007028019972494803,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0001930310027091764,
+                                                                    "self": 0.00017835199105320498,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0006860819921712391,
-                                                                            "count": 10,
+                                                                            "total": 0.0005244500061962754,
+                                                                            "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0006860819921712391
+                                                                            "self": 0.0005244500061962754
                                                                         }
                                                                     }
                                                                 }
@@ -267,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 136.0214929188296,
-                                                    "count": 18191,
+                                                    "total": 697.9767162623903,
+                                                    "count": 63021,
                                                     "is_parallel": true,
-                                                    "self": 4.181488279253244,
+                                                    "self": 13.67834424200555,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 2.7266511430279934,
-                                                            "count": 18191,
+                                                            "total": 10.789437118080969,
+                                                            "count": 63021,
                                                             "is_parallel": true,
-                                                            "self": 2.7266511430279934
+                                                            "self": 10.789437118080969
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 115.89310034152732,
-                                                            "count": 18191,
+                                                            "total": 634.0428370539157,
+                                                            "count": 63021,
                                                             "is_parallel": true,
-                                                            "self": 115.89310034152732
+                                                            "self": 634.0428370539157
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 13.220253155021055,
-                                                            "count": 18191,
+                                                            "total": 39.46609784838802,
+                                                            "count": 63021,
                                                             "is_parallel": true,
-                                                            "self": 3.057622793756309,
+                                                            "self": 9.871907055916381,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 10.162630361264746,
-                                                                    "count": 181910,
+                                                                    "total": 29.594190792471636,
+                                                                    "count": 504168,
                                                                     "is_parallel": true,
-                                                                    "self": 10.162630361264746
+                                                                    "self": 29.594190792471636
                                                                 }
                                                             }
                                                         }
@@ -307,31 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 140.24570138184208,
-                            "count": 18192,
-                            "self": 0.4279935143276816,
+                            "total": 809.54755517374,
+                            "count": 63022,
+                            "self": 2.3640318971447414,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 27.836928472475847,
-                                    "count": 18192,
-                                    "self": 27.384556184471876,
+                                    "total": 127.37807295958919,
+                                    "count": 63022,
+                                    "self": 127.17165255959117,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.45237228800397133,
-                                            "count": 4,
-                                            "self": 0.45237228800397133
+                                            "total": 0.20642039999802364,
+                                            "count": 2,
+                                            "self": 0.20642039999802364
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 111.98077939503855,
-                                    "count": 90,
-                                    "self": 23.712709611027094,
+                                    "total": 679.805450317006,
+                                    "count": 445,
+                                    "self": 277.75940190442634,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 88.26806978401146,
-                                            "count": 4587,
-                                            "self": 88.26806978401146
+                                            "total": 402.0460484125797,
+                                            "count": 22410,
+                                            "self": 402.0460484125797
                                         }
                                     }
                                 }
@@ -340,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 6.400005077011883e-07,
+                    "total": 6.440022843889892e-07,
                     "count": 1,
-                    "self": 6.400005077011883e-07
+                    "self": 6.440022843889892e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.08934669200243661,
+                    "total": 0.0922921530000167,
                     "count": 1,
-                    "self": 0.0004997930009267293,
+                    "self": 0.0020129369950154796,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.08884689900150988,
+                            "total": 0.09027921600500122,
                             "count": 1,
-                            "self": 0.08884689900150988
+                            "self": 0.09027921600500122
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,59 +1,50 @@
 {
-    "SnowballTarget": {
+    "Pyramids": {
         "checkpoints": [
             {
-                "steps": 49936,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
-                "reward": 15.181818181818182,
-                "creation_time": 1751405937.6387424,
+                "steps": 16000,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-16000.onnx",
+                "reward": null,
+                "creation_time": 1751406841.3736622,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-16000.pt"
                 ]
             },
             {
-                "steps": 99960,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
-                "reward": 22.90909090909091,
-                "creation_time": 1751406047.5688028,
+                "steps": 499929,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499929.onnx",
+                "reward": 1.568000003695488,
+                "creation_time": 1751407836.530037,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-499929.pt"
                 ]
             },
             {
-                "steps": 149984,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
-                "reward": 24.363636363636363,
-                "creation_time": 1751406158.3935463,
+                "steps": 999905,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999905.onnx",
+                "reward": 1.7605000361800194,
+                "creation_time": 1751408842.3427362,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-999905.pt"
                 ]
             },
             {
-                "steps": 199984,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
-                "reward": 26.818181818181817,
-                "creation_time": 1751406265.164866,
+                "steps": 1000033,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000033.onnx",
+                "reward": 1.7605000361800194,
+                "creation_time": 1751408842.4458108,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
-                ]
-            },
-            {
-                "steps": 200112,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
-                "reward": 26.818181818181817,
-                "creation_time": 1751406265.2688215,
-                "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-1000033.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 200112,
-            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": 26.818181818181817,
-            "creation_time": 1751406265.2688215,
+            "steps": 1000033,
+            "file_path": "results/Pyramids Training/Pyramids.onnx",
+            "reward": 1.7605000361800194,
+            "creation_time": 1751408842.4458108,
             "auxillary_file_paths": [
-                "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-1000033.pt"
             ]
         }
     },