First Push

SnowballTarget/SnowballTarget-149984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a4a6fe22063f4e97dbd418766ebcdf160feadfe67fbe4837f7750f22db6d829
+size 914755

SnowballTarget/SnowballTarget-149984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad30e0d478abdf067735f149eea399847874b5ad3610384660e82b56e6406d8c
+size 5434078

SnowballTarget/SnowballTarget-199984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c43ee55f854660073cbf58d5045d1502570eb90298d4a5ac7496259543a1439a
+size 914755

SnowballTarget/SnowballTarget-199984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c4adf7afdc5489ea25c86276d133258a197c4d9cfcb4a7415cda2a27100f91b
+size 5434078

SnowballTarget/SnowballTarget-249944.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7614f64f95b9b12026c7bef0faeb79f2185742e805711345b1462a733d358247
+size 914755

SnowballTarget/SnowballTarget-249944.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:597088c9a97edf88974f105bc8303ce3f6f0aa52a04665f53220abe30ad6ed1d
+size 5434078

SnowballTarget/SnowballTarget-299968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6be4589feeb350172dc5349c0572b802164a2a8260c5303770fab3bb1e60aa1
+size 914755

SnowballTarget/SnowballTarget-299968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:371fb12e31121a43320ea809c2c969f7979c364412d39eb303bfbb17c245da11
+size 5434078

SnowballTarget/SnowballTarget-49936.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dde1a1720bcc81310251b72198fe186750ca04d1f9a750099e24d9aa18bccf53
-size 650646
+oid sha256:2a71121d2c2efe7e192c4c53bbc7f11b2602f785df57d085242a1588296af630
+size 914755

SnowballTarget/SnowballTarget-49936.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9c344a3b6b1b12cac6fe8136dcf667e19156dd25785a35e5a22977e08914af0
-size 3849827
+oid sha256:a4428e8aacd5027b376424fb6905b8907a2d0cd0008954e5c448fda69c5fab3c
+size 5433987

SnowballTarget/SnowballTarget-99960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9165ec317b9d845f874413fdfb3d9cc2e77c9a2b6680333b0c52bbf96dd28eca
+size 914755

SnowballTarget/SnowballTarget-99960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16ec9ea23d9155079a45c48f4ab055ccd1d7c52179a7772b5b08b276c854c339
+size 5433987

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a60b903d0194cc48a5176336cec0c1f53d7f8adfb79d85cfecfade3f818a8ad
-size 3849077
+oid sha256:9ffe02ad9f33498f77309f4f3823793191a9e8a5a2468af531695e5161dc1529
+size 5433077

SnowballTarget/events.out.tfevents.1772314849.7560ac0c70d8.17239.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e84e84ebf26aaae52ef6df64cb45e54e9449d596d8073d75957ea7244a8e246
+size 33747

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": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0006, "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": 3, "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": 400000, "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": "SnowballTarget3", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -5,7 +5,7 @@ behaviors:
     hyperparameters:
       batch_size: 128
       buffer_size: 2048
-      learning_rate: 0.0003
+      learning_rate: 0.0006
       beta: 0.005
       epsilon: 0.2
       lambd: 0.95
@@ -18,7 +18,7 @@ behaviors:
     network_settings:
       normalize: false
       hidden_units: 256
-      num_layers: 2
+      num_layers: 3
       vis_encode_type: simple
       memory: null
       goal_conditioning_type: hyper
@@ -38,7 +38,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 10
     even_checkpoints: false
-    max_steps: 200000
+    max_steps: 400000
     time_horizon: 64
     summary_freq: 10000
     threaded: false
@@ -66,7 +66,7 @@ engine_settings:
   no_graphics_monitor: false
 environment_parameters: null
 checkpoint_settings:
-  run_id: SnowballTarget1
+  run_id: SnowballTarget3
   initialize_from: null
   load_model: false
   resume: false

run_logs/Player-0.log

@@ -2,9 +2,6 @@ Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarge
 Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
-PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face
-PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face/SnowballTarget
-Unable to load player prefs
 Initialize engine version: 2021.3.14f1 (eee1884e7226)
 [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
 Forcing GfxDevice: Null
@@ -34,7 +31,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.179 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)
@@ -45,7 +42,7 @@ 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: 0.776202 ms
+UnloadTime: 0.749284 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 1 worker threads for Enlighten.
@@ -53,7 +50,7 @@ Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 1879 frames, [16.0 KB-32.0 KB]: 31 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 8966 frames, [16.0 KB-32.0 KB]: 151 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
@@ -169,19 +166,19 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 42
+  Peak main deferred allocation count 41
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [4.0 MB-8.0 MB]: 1911 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 9118 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 6.3 MB
+      Peak Allocated memory 8.2 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 1911 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 9118 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 17.3 MB
@@ -213,13 +210,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 1300 frames, [64.0 KB-128.0 KB]: 611 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 8557 frames, [64.0 KB-128.0 KB]: 561 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 66.8 KB
+      Peak Allocated memory 66.4 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 1911 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 9118 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 39.6 KB
@@ -231,13 +228,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 1911 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 9118 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 0.6 MB
       Peak Large allocation bytes 0 B
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 1910 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 9117 frames, [2.0 MB-4.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 2.2 MB
@@ -249,13 +246,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 1911 frames
+      Peak usage frame count: [0-1.0 KB]: 9118 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]: 1911 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 9118 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.7 KB

run_logs/timers.json

@@ -2,213 +2,213 @@
     "name": "root",
     "gauges": {
         "SnowballTarget.Policy.Entropy.mean": {
-            "value": 2.0488200187683105,
-            "min": 2.0488200187683105,
-            "max": 2.8476309776306152,
-            "count": 6
+            "value": 0.7095248699188232,
+            "min": 0.7095248699188232,
+            "max": 2.8473734855651855,
+            "count": 33
         },
         "SnowballTarget.Policy.Entropy.sum": {
-            "value": 19652.28125,
-            "min": 19652.28125,
-            "max": 29068.6171875,
-            "count": 6
+            "value": 6805.7626953125,
+            "min": 6805.7626953125,
+            "max": 29065.98828125,
+            "count": 33
         },
         "SnowballTarget.Step.mean": {
-            "value": 59976.0,
+            "value": 329992.0,
             "min": 9952.0,
-            "max": 59976.0,
-            "count": 6
+            "max": 329992.0,
+            "count": 33
         },
         "SnowballTarget.Step.sum": {
-            "value": 59976.0,
+            "value": 329992.0,
             "min": 9952.0,
-            "max": 59976.0,
-            "count": 6
+            "max": 329992.0,
+            "count": 33
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 6.058079242706299,
-            "min": 0.2809963822364807,
-            "max": 6.058079242706299,
-            "count": 6
+            "value": 13.541885375976562,
+            "min": 0.3765427768230438,
+            "max": 13.750577926635742,
+            "count": 33
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 1241.90625,
-            "min": 54.51329803466797,
-            "max": 1241.90625,
-            "count": 6
+            "value": 2762.544677734375,
+            "min": 73.04930114746094,
+            "max": 2814.87060546875,
+            "count": 33
         },
         "SnowballTarget.Losses.PolicyLoss.mean": {
-            "value": 0.06850531374049537,
-            "min": 0.06042709291166687,
-            "max": 0.06877997634297821,
-            "count": 6
+            "value": 0.07133594242052413,
+            "min": 0.062328982485946746,
+            "max": 0.07871535035128724,
+            "count": 33
         },
         "SnowballTarget.Losses.PolicyLoss.sum": {
-            "value": 0.34252656870247683,
-            "min": 0.24170837164666747,
-            "max": 0.34389988171489105,
-            "count": 6
+            "value": 0.35667971210262067,
+            "min": 0.24931592994378698,
+            "max": 0.3935767517564362,
+            "count": 33
         },
         "SnowballTarget.Losses.ValueLoss.mean": {
-            "value": 0.28466968022140804,
-            "min": 0.113027092144715,
-            "max": 0.2994488288520598,
-            "count": 6
+            "value": 0.17541804827895818,
+            "min": 0.11917218662611229,
+            "max": 0.26781621604573497,
+            "count": 33
         },
         "SnowballTarget.Losses.ValueLoss.sum": {
-            "value": 1.4233484011070403,
-            "min": 0.45210836857886,
-            "max": 1.4233484011070403,
-            "count": 6
+            "value": 0.8770902413947909,
+            "min": 0.47668874650444915,
+            "max": 1.3390810802286748,
+            "count": 33
         },
         "SnowballTarget.Policy.LearningRate.mean": {
-            "value": 0.000217632027456,
-            "min": 0.000217632027456,
-            "max": 0.000291882002706,
-            "count": 6
+            "value": 0.00011173208137799998,
+            "min": 0.00011173208137799998,
+            "max": 0.0005918820013529999,
+            "count": 33
         },
         "SnowballTarget.Policy.LearningRate.sum": {
-            "value": 0.00108816013728,
-            "min": 0.000929928090024,
-            "max": 0.00138516003828,
-            "count": 6
+            "value": 0.0005586604068899999,
+            "min": 0.0005586604068899999,
+            "max": 0.00288516001914,
+            "count": 33
         },
         "SnowballTarget.Policy.Epsilon.mean": {
-            "value": 0.172544,
-            "min": 0.172544,
-            "max": 0.19729400000000002,
-            "count": 6
+            "value": 0.118622,
+            "min": 0.118622,
+            "max": 0.19864700000000002,
+            "count": 33
         },
         "SnowballTarget.Policy.Epsilon.sum": {
-            "value": 0.86272,
-            "min": 0.7099760000000002,
-            "max": 0.96172,
-            "count": 6
+            "value": 0.59311,
+            "min": 0.49538800000000005,
+            "max": 0.98086,
+            "count": 33
         },
         "SnowballTarget.Policy.Beta.mean": {
-            "value": 0.0036299456,
-            "min": 0.0036299456,
-            "max": 0.0048649706,
-            "count": 6
+            "value": 0.0009392378000000002,
+            "min": 0.0009392378000000002,
+            "max": 0.004932485299999999,
+            "count": 33
         },
         "SnowballTarget.Policy.Beta.sum": {
-            "value": 0.018149728,
-            "min": 0.015507802400000001,
-            "max": 0.023089828,
-            "count": 6
+            "value": 0.004696189000000001,
+            "min": 0.004696189000000001,
+            "max": 0.024044914,
+            "count": 33
         },
         "SnowballTarget.Environment.EpisodeLength.mean": {
             "value": 199.0,
             "min": 199.0,
             "max": 199.0,
-            "count": 6
+            "count": 33
         },
         "SnowballTarget.Environment.EpisodeLength.sum": {
             "value": 10945.0,
             "min": 8756.0,
             "max": 10945.0,
-            "count": 6
+            "count": 33
         },
         "SnowballTarget.Environment.CumulativeReward.mean": {
-            "value": 15.018181818181818,
-            "min": 3.1818181818181817,
-            "max": 15.018181818181818,
-            "count": 6
+            "value": 26.796296296296298,
+            "min": 3.477272727272727,
+            "max": 26.963636363636365,
+            "count": 33
         },
         "SnowballTarget.Environment.CumulativeReward.sum": {
-            "value": 826.0,
-            "min": 140.0,
-            "max": 826.0,
-            "count": 6
+            "value": 1447.0,
+            "min": 153.0,
+            "max": 1483.0,
+            "count": 33
         },
         "SnowballTarget.Policy.ExtrinsicReward.mean": {
-            "value": 15.018181818181818,
-            "min": 3.1818181818181817,
-            "max": 15.018181818181818,
-            "count": 6
+            "value": 26.796296296296298,
+            "min": 3.477272727272727,
+            "max": 26.963636363636365,
+            "count": 33
         },
         "SnowballTarget.Policy.ExtrinsicReward.sum": {
-            "value": 826.0,
-            "min": 140.0,
-            "max": 826.0,
-            "count": 6
+            "value": 1447.0,
+            "min": 153.0,
+            "max": 1483.0,
+            "count": 33
         },
         "SnowballTarget.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 6
+            "count": 33
         },
         "SnowballTarget.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 6
+            "count": 33
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1772313093",
+        "start_time_seconds": "1772314848",
         "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget3 --no-graphics",
         "mlagents_version": "1.2.0.dev0",
         "mlagents_envs_version": "1.2.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.8.0+cu128",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1772313250"
+        "end_time_seconds": "1772315593"
     },
-    "total": 157.06482778999998,
+    "total": 744.4466958350004,
     "count": 1,
-    "self": 0.670623020000221,
+    "self": 0.42514927800039004,
     "children": {
         "run_training.setup": {
-            "total": 0.03421207199994569,
+            "total": 0.023836146000121516,
             "count": 1,
-            "self": 0.03421207199994569
+            "self": 0.023836146000121516
         },
         "TrainerController.start_learning": {
-            "total": 156.35999269799981,
+            "total": 743.9977104109998,
             "count": 1,
-            "self": 0.11876409400861121,
+            "self": 0.5701817649573968,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.990556369999922,
+                    "total": 1.9720252289998825,
                     "count": 1,
-                    "self": 2.990556369999922
+                    "self": 1.9720252289998825
                 },
                 "TrainerController.advance": {
-                    "total": 153.01845343099149,
-                    "count": 6368,
-                    "self": 0.12307593300147346,
+                    "total": 741.4484766610431,
+                    "count": 30392,
+                    "self": 0.6209287119768305,
                     "children": {
                         "env_step": {
-                            "total": 111.11913552599708,
-                            "count": 6368,
-                            "self": 86.91522811199752,
+                            "total": 532.7946861069622,
+                            "count": 30392,
+                            "self": 415.44035444101155,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 24.134051642992517,
-                                    "count": 6368,
-                                    "self": 0.42944335099127784,
+                                    "total": 117.00914793202355,
+                                    "count": 30392,
+                                    "self": 2.023098731980099,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 23.70460829200124,
-                                            "count": 6368,
-                                            "self": 23.70460829200124
+                                            "total": 114.98604920004345,
+                                            "count": 30392,
+                                            "self": 114.98604920004345
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.06985577100704177,
-                                    "count": 6367,
+                                    "total": 0.3451837339271151,
+                                    "count": 30392,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 155.4729760470134,
-                                            "count": 6367,
+                                            "total": 741.0003784210057,
+                                            "count": 30392,
                                             "is_parallel": true,
-                                            "self": 79.07886147600925,
+                                            "self": 375.93809538301775,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -217,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.00517981799998779,
+                                                            "total": 0.0019181510001544666,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.003078040999980658,
+                                                            "self": 0.0006041430001459958,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0021017770000071323,
+                                                                    "total": 0.0013140080000084708,
                                                                     "count": 10,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0021017770000071323
+                                                                    "self": 0.0013140080000084708
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.04272492699988106,
+                                                            "total": 0.035656288000154746,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.000613314000020182,
+                                                            "self": 0.0005850039997312706,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0003680620000068302,
+                                                                    "total": 0.00043290500025250367,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0003680620000068302
+                                                                    "self": 0.00043290500025250367
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.038697946999946,
+                                                                    "total": 0.03275899800019033,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.038697946999946
+                                                                    "self": 0.03275899800019033
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.003045603999908053,
+                                                                    "total": 0.00187938099998064,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0003807190003044525,
+                                                                    "self": 0.00036688099908133154,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0026648849996036006,
+                                                                            "total": 0.0015125000008993084,
                                                                             "count": 10,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0026648849996036006
+                                                                            "self": 0.0015125000008993084
                                                                         }
                                                                     }
                                                                 }
@@ -267,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 76.39411457100414,
-                                                    "count": 6366,
+                                                    "total": 365.062283037988,
+                                                    "count": 30391,
                                                     "is_parallel": true,
-                                                    "self": 3.5545296539958144,
+                                                    "self": 16.953038460037988,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 1.8599655780067224,
-                                                            "count": 6366,
+                                                            "total": 8.97932959200216,
+                                                            "count": 30391,
                                                             "is_parallel": true,
-                                                            "self": 1.8599655780067224
+                                                            "self": 8.97932959200216
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 58.18954710299772,
-                                                            "count": 6366,
+                                                            "total": 278.1169417809606,
+                                                            "count": 30391,
                                                             "is_parallel": true,
-                                                            "self": 58.18954710299772
+                                                            "self": 278.1169417809606
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 12.79007223600388,
-                                                            "count": 6366,
+                                                            "total": 61.01297320498725,
+                                                            "count": 30391,
                                                             "is_parallel": true,
-                                                            "self": 2.3706919339840624,
+                                                            "self": 11.085336442878543,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 10.419380302019817,
-                                                                    "count": 63660,
+                                                                    "total": 49.927636762108705,
+                                                                    "count": 303910,
                                                                     "is_parallel": true,
-                                                                    "self": 10.419380302019817
+                                                                    "self": 49.927636762108705
                                                                 }
                                                             }
                                                         }
@@ -307,31 +307,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 41.77624197199293,
-                            "count": 6367,
-                            "self": 0.14528491099144958,
+                            "total": 208.032861842104,
+                            "count": 30392,
+                            "self": 0.679465280126351,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 9.447515910001812,
-                                    "count": 6367,
-                                    "self": 9.312396783001986,
+                                    "total": 44.70426057097711,
+                                    "count": 30392,
+                                    "self": 44.064410302977194,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.1351191269998253,
-                                            "count": 1,
-                                            "self": 0.1351191269998253
+                                            "total": 0.6398502679999183,
+                                            "count": 6,
+                                            "self": 0.6398502679999183
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 32.18344115099967,
-                                    "count": 31,
-                                    "self": 13.06682582999747,
+                                    "total": 162.64913599100055,
+                                    "count": 152,
+                                    "self": 64.29756426800122,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 19.1166153210022,
-                                            "count": 1578,
-                                            "self": 19.1166153210022
+                                            "total": 98.35157172299932,
+                                            "count": 7698,
+                                            "self": 98.35157172299932
                                         }
                                     }
                                 }
@@ -340,19 +340,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.3849999049853068e-06,
+                    "total": 1.4320003174361773e-06,
                     "count": 1,
-                    "self": 1.3849999049853068e-06
+                    "self": 1.4320003174361773e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.23221741799989104,
+                    "total": 0.007025323999187094,
                     "count": 1,
-                    "self": 0.0009053489998223085,
+                    "self": 2.329199924133718e-05,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.23131206900006873,
+                            "total": 0.007002031999945757,
                             "count": 1,
-                            "self": 0.23131206900006873
+                            "self": 0.007002031999945757
                         }
                     }
                 }

run_logs/training_status.json

@@ -3,32 +3,59 @@
         "checkpoints": [
             {
                 "steps": 49936,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
-                "reward": 13.181818181818182,
-                "creation_time": 1772313206.6047485,
+                "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-49936.onnx",
+                "reward": 17.545454545454547,
+                "creation_time": 1772314963.4103618,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
+                    "results/SnowballTarget3/SnowballTarget/SnowballTarget-49936.pt"
                 ]
             },
             {
-                "steps": 69608,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-69608.onnx",
-                "reward": 16.818181818181817,
-                "creation_time": 1772313249.5164647,
+                "steps": 99960,
+                "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-99960.onnx",
+                "reward": 23.0,
+                "creation_time": 1772315076.5508173,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-69608.pt"
+                    "results/SnowballTarget3/SnowballTarget/SnowballTarget-99960.pt"
+                ]
+            },
+            {
+                "steps": 149984,
+                "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-149984.onnx",
+                "reward": 26.454545454545453,
+                "creation_time": 1772315186.8693945,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget3/SnowballTarget/SnowballTarget-149984.pt"
+                ]
+            },
+            {
+                "steps": 199984,
+                "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-199984.onnx",
+                "reward": 25.727272727272727,
+                "creation_time": 1772315296.4198992,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget3/SnowballTarget/SnowballTarget-199984.pt"
+                ]
+            },
+            {
+                "steps": 249944,
+                "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-249944.onnx",
+                "reward": 26.454545454545453,
+                "creation_time": 1772315407.5301805,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget3/SnowballTarget/SnowballTarget-249944.pt"
+                ]
+            },
+            {
+                "steps": 299968,
+                "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-299968.onnx",
+                "reward": 26.545454545454547,
+                "creation_time": 1772315518.2998154,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget3/SnowballTarget/SnowballTarget-299968.pt"
                 ]
             }
-        ],
-        "final_checkpoint": {
-            "steps": 69608,
-            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": 16.818181818181817,
-            "creation_time": 1772313249.5164647,
-            "auxillary_file_paths": [
-                "results/SnowballTarget1/SnowballTarget/SnowballTarget-69608.pt"
-            ]
-        }
+        ]
     },
     "metadata": {
         "stats_format_version": "0.3.0",