First Push

SnowballTarget.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5850df89dd645ef0687017150e1d6dce4633c28f64cdceff909cd8051504c1f2
+oid sha256:5ed3d329fdaaea65a97836edd5a31fde8ed4017dd49b44480a0d1f9326880b1a
 size 650646

SnowballTarget/SnowballTarget-100408.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ed3d329fdaaea65a97836edd5a31fde8ed4017dd49b44480a0d1f9326880b1a
+size 650646

SnowballTarget/SnowballTarget-100408.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:889e4617da93cb5a00b1ed2fc37fef01cb2c3cb7a4d37c9e499e49033176188e
+size 3849902

SnowballTarget/SnowballTarget-49936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca5e9cf181069b7c366306c826f264ec3390d9667aa98624dece4a736655a5a4
+size 650646

SnowballTarget/SnowballTarget-49936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:292877339dcd8f2435a03f690a695f9ae2bcaca23969566b3c2ead22fabe4352
+size 3849827

SnowballTarget/SnowballTarget-99960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ed3d329fdaaea65a97836edd5a31fde8ed4017dd49b44480a0d1f9326880b1a
+size 650646

SnowballTarget/SnowballTarget-99960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e750deb004086c365c50b5e748265612a539bc653cc9bba57d26f32586eab450
+size 3849827

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7230399066e63bd803b6e455223ee9e54ea3f6efcbf0d9043ac8ca475765dfaa
+oid sha256:17aaf26100d1235a4de5b444f45f08c492b731ec2b63a9034200458fbadb12fd
 size 3849077

SnowballTarget/events.out.tfevents.1774976632.8f8b6b2476b5.7723.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0a4d7d9874b4dd32e4957ef5acd9c85f98bd31e5d0102126a0cb002aac9ea23
+size 15645

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": 20000, "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": "SnowballTarget2", "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": 0.0003, "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": 100000, "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

@@ -38,7 +38,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 10
     even_checkpoints: false
-    max_steps: 20000
+    max_steps: 100000
     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: SnowballTarget2
+  run_id: SnowballTarget3
   initialize_from: null
   load_model: false
   resume: false

run_logs/Player-0.log

@@ -31,7 +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  0.079 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)
@@ -42,7 +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: 0.599996 ms
+UnloadTime: 0.648566 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.
@@ -50,7 +50,7 @@ Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 550 frames, [16.0 KB-32.0 KB]: 9 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 2693 frames, [16.0 KB-32.0 KB]: 45 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
@@ -166,22 +166,22 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 33
+  Peak main deferred allocation count 42
     [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]: 560 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 2739 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 5.7 MB
+      Peak Allocated memory 6.6 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 560 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 2739 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.5 MB
+      Peak Allocated memory 17.3 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -210,13 +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]: 537 frames, [64.0 KB-128.0 KB]: 23 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 1636 frames, [64.0 KB-128.0 KB]: 1103 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 66.0 KB
+      Peak Allocated memory 67.3 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 560 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 2739 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 39.6 KB
@@ -228,13 +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]: 560 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 2739 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]: 559 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 2738 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
@@ -246,13 +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]: 560 frames
+      Peak usage frame count: [0-1.0 KB]: 2739 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]: 560 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 2739 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": 2.7886087894439697,
-            "min": 2.7886087894439697,
-            "max": 2.863290309906006,
-            "count": 2
+            "value": 1.5022602081298828,
+            "min": 1.5022602081298828,
+            "max": 2.8349201679229736,
+            "count": 10
         },
         "SnowballTarget.Policy.Entropy.sum": {
-            "value": 28711.515625,
-            "min": 28711.515625,
-            "max": 29228.466796875,
-            "count": 2
+            "value": 15467.2705078125,
+            "min": 15351.3232421875,
+            "max": 28938.865234375,
+            "count": 10
         },
         "SnowballTarget.Step.mean": {
-            "value": 19992.0,
+            "value": 99960.0,
             "min": 9952.0,
-            "max": 19992.0,
-            "count": 2
+            "max": 99960.0,
+            "count": 10
         },
         "SnowballTarget.Step.sum": {
-            "value": 19992.0,
+            "value": 99960.0,
             "min": 9952.0,
-            "max": 19992.0,
-            "count": 2
+            "max": 99960.0,
+            "count": 10
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 1.1450257301330566,
-            "min": 0.2738800346851349,
-            "max": 1.1450257301330566,
-            "count": 2
+            "value": 8.337539672851562,
+            "min": 0.5177991986274719,
+            "max": 8.337539672851562,
+            "count": 10
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 234.73028564453125,
-            "min": 53.132728576660156,
-            "max": 234.73028564453125,
-            "count": 2
+            "value": 1700.858154296875,
+            "min": 100.45304870605469,
+            "max": 1700.858154296875,
+            "count": 10
         },
         "SnowballTarget.Losses.PolicyLoss.mean": {
-            "value": 0.06859861134001347,
-            "min": 0.06859861134001347,
-            "max": 0.07424564163068449,
-            "count": 2
+            "value": 0.06643584113586329,
+            "min": 0.059157242598588455,
+            "max": 0.07375054838642017,
+            "count": 10
         },
         "SnowballTarget.Losses.PolicyLoss.sum": {
-            "value": 0.3429930567000673,
-            "min": 0.29698256652273797,
-            "max": 0.3429930567000673,
-            "count": 2
+            "value": 0.3321792056793164,
+            "min": 0.23662897039435382,
+            "max": 0.3645427834856616,
+            "count": 10
         },
         "SnowballTarget.Losses.ValueLoss.mean": {
-            "value": 0.1720975478198014,
-            "min": 0.1124169812332291,
-            "max": 0.1720975478198014,
-            "count": 2
+            "value": 0.26491491928988814,
+            "min": 0.14860686539631227,
+            "max": 0.27866546423996197,
+            "count": 10
         },
         "SnowballTarget.Losses.ValueLoss.sum": {
-            "value": 0.8604877390990071,
-            "min": 0.4496679249329164,
-            "max": 0.8604877390990071,
-            "count": 2
+            "value": 1.3245745964494406,
+            "min": 0.5944274615852491,
+            "max": 1.3933273211998098,
+            "count": 10
         },
         "SnowballTarget.Policy.LearningRate.mean": {
-            "value": 7.032007656e-05,
-            "min": 7.032007656e-05,
-            "max": 0.00021882002706000002,
-            "count": 2
+            "value": 1.6464094511999996e-05,
+            "min": 1.6464094511999996e-05,
+            "max": 0.000283764005412,
+            "count": 10
         },
         "SnowballTarget.Policy.LearningRate.sum": {
-            "value": 0.0003516003828,
-            "min": 0.0003516003828,
-            "max": 0.0008752801082400001,
-            "count": 2
+            "value": 8.232047255999999e-05,
+            "min": 8.232047255999999e-05,
+            "max": 0.00127032007656,
+            "count": 10
         },
         "SnowballTarget.Policy.Epsilon.mean": {
-            "value": 0.12344000000000002,
-            "min": 0.12344000000000002,
-            "max": 0.17294,
-            "count": 2
+            "value": 0.105488,
+            "min": 0.105488,
+            "max": 0.194588,
+            "count": 10
         },
         "SnowballTarget.Policy.Epsilon.sum": {
-            "value": 0.6172000000000001,
-            "min": 0.6172000000000001,
-            "max": 0.69176,
-            "count": 2
+            "value": 0.52744,
+            "min": 0.4615520000000001,
+            "max": 0.92344,
+            "count": 10
         },
         "SnowballTarget.Policy.Beta.mean": {
-            "value": 0.0011796560000000003,
-            "min": 0.0011796560000000003,
-            "max": 0.003649706,
-            "count": 2
+            "value": 0.0002838512,
+            "min": 0.0002838512,
+            "max": 0.0047299412,
+            "count": 10
         },
         "SnowballTarget.Policy.Beta.sum": {
-            "value": 0.005898280000000001,
-            "min": 0.005898280000000001,
-            "max": 0.014598824,
-            "count": 2
+            "value": 0.001419256,
+            "min": 0.001419256,
+            "max": 0.021179656,
+            "count": 10
         },
         "SnowballTarget.Environment.EpisodeLength.mean": {
             "value": 199.0,
             "min": 199.0,
             "max": 199.0,
-            "count": 2
+            "count": 10
         },
         "SnowballTarget.Environment.EpisodeLength.sum": {
             "value": 10945.0,
             "min": 8756.0,
             "max": 10945.0,
-            "count": 2
+            "count": 10
         },
         "SnowballTarget.Environment.CumulativeReward.mean": {
-            "value": 5.0,
-            "min": 2.9545454545454546,
-            "max": 5.0,
-            "count": 2
+            "value": 17.89090909090909,
+            "min": 4.318181818181818,
+            "max": 17.89090909090909,
+            "count": 10
         },
         "SnowballTarget.Environment.CumulativeReward.sum": {
-            "value": 275.0,
-            "min": 130.0,
-            "max": 275.0,
-            "count": 2
+            "value": 984.0,
+            "min": 190.0,
+            "max": 984.0,
+            "count": 10
         },
         "SnowballTarget.Policy.ExtrinsicReward.mean": {
-            "value": 5.0,
-            "min": 2.9545454545454546,
-            "max": 5.0,
-            "count": 2
+            "value": 17.89090909090909,
+            "min": 4.318181818181818,
+            "max": 17.89090909090909,
+            "count": 10
         },
         "SnowballTarget.Policy.ExtrinsicReward.sum": {
-            "value": 275.0,
-            "min": 130.0,
-            "max": 275.0,
-            "count": 2
+            "value": 984.0,
+            "min": 190.0,
+            "max": 984.0,
+            "count": 10
         },
         "SnowballTarget.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 2
+            "count": 10
         },
         "SnowballTarget.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 2
+            "count": 10
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1774976468",
+        "start_time_seconds": "1774976632",
         "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
-        "command_line_arguments": "/usr/local/envs/mlagagents_env/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --no-graphics",
+        "command_line_arguments": "/usr/local/envs/mlagagents_env/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": "2.7.1+cu118",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1774976513"
+        "end_time_seconds": "1774976854"
     },
-    "total": 45.75893181099991,
+    "total": 222.39212270199982,
     "count": 1,
-    "self": 0.4246389079999062,
+    "self": 0.43112549999955263,
     "children": {
         "run_training.setup": {
-            "total": 0.01874560099986411,
+            "total": 0.019144188000154827,
             "count": 1,
-            "self": 0.01874560099986411
+            "self": 0.019144188000154827
         },
         "TrainerController.start_learning": {
-            "total": 45.31554730200014,
+            "total": 221.94185301400012,
             "count": 1,
-            "self": 0.032395118001659284,
+            "self": 0.1617235859896482,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 1.972945657000082,
+                    "total": 2.5758988569998564,
                     "count": 1,
-                    "self": 1.972945657000082
+                    "self": 2.5758988569998564
                 },
                 "TrainerController.advance": {
-                    "total": 43.20511843599843,
-                    "count": 1864,
-                    "self": 0.035610695998002484,
+                    "total": 219.1223074770105,
+                    "count": 9128,
+                    "self": 0.17215367099129253,
                     "children": {
                         "env_step": {
-                            "total": 30.56987653799729,
-                            "count": 1864,
-                            "self": 23.898045318996537,
+                            "total": 158.77502279600503,
+                            "count": 9128,
+                            "self": 124.54743731498002,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 6.652144026000315,
-                                    "count": 1864,
-                                    "self": 0.12283871899580845,
+                                    "total": 34.128239301023086,
+                                    "count": 9128,
+                                    "self": 0.6157145250260783,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 6.529305307004506,
-                                            "count": 1864,
-                                            "self": 6.529305307004506
+                                            "total": 33.51252477599701,
+                                            "count": 9128,
+                                            "self": 33.51252477599701
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.01968719300043631,
-                                    "count": 1864,
+                                    "total": 0.0993461800019304,
+                                    "count": 9128,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 44.99548432800066,
-                                            "count": 1864,
+                                            "total": 220.84013189198868,
+                                            "count": 9128,
                                             "is_parallel": true,
-                                            "self": 24.0163584649963,
+                                            "self": 111.11328651598888,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -217,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.002133148999973855,
+                                                            "total": 0.0019438110000464803,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006476479998127616,
+                                                            "self": 0.0005991620000713738,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0014855010001610935,
+                                                                    "total": 0.0013446489999751066,
                                                                     "count": 10,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0014855010001610935
+                                                                    "self": 0.0013446489999751066
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.03979574199979652,
+                                                            "total": 0.06966054900021845,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005889729995942616,
+                                                            "self": 0.0005618960001356754,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0004049500000746775,
+                                                                    "total": 0.0004064699999162258,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004049500000746775
+                                                                    "self": 0.0004064699999162258
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.036427894000098604,
+                                                                    "total": 0.06485024200014777,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.036427894000098604
+                                                                    "self": 0.06485024200014777
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0023739250000289758,
+                                                                    "total": 0.003841941000018778,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00044610199984163046,
+                                                                    "self": 0.00033277200031989196,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0019278230001873453,
+                                                                            "total": 0.003509168999698886,
                                                                             "count": 10,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0019278230001873453
+                                                                            "self": 0.003509168999698886
                                                                         }
                                                                     }
                                                                 }
@@ -267,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 20.979125863004356,
-                                                    "count": 1863,
+                                                    "total": 109.7268453759998,
+                                                    "count": 9127,
                                                     "is_parallel": true,
-                                                    "self": 1.0312309580033343,
+                                                    "self": 5.172228144986548,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 0.5481675310024912,
-                                                            "count": 1863,
+                                                            "total": 2.693908988003386,
+                                                            "count": 9127,
                                                             "is_parallel": true,
-                                                            "self": 0.5481675310024912
+                                                            "self": 2.693908988003386
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 15.83885789500141,
-                                                            "count": 1863,
+                                                            "total": 83.26875971400955,
+                                                            "count": 9127,
                                                             "is_parallel": true,
-                                                            "self": 15.83885789500141
+                                                            "self": 83.26875971400955
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 3.5608694789971196,
-                                                            "count": 1863,
+                                                            "total": 18.59194852900032,
+                                                            "count": 9127,
                                                             "is_parallel": true,
-                                                            "self": 0.6497622700135253,
+                                                            "self": 3.3743537390209895,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 2.9111072089835943,
-                                                                    "count": 18630,
+                                                                    "total": 15.21759478997933,
+                                                                    "count": 91270,
                                                                     "is_parallel": true,
-                                                                    "self": 2.9111072089835943
+                                                                    "self": 15.21759478997933
                                                                 }
                                                             }
                                                         }
@@ -307,24 +307,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 12.599631202003138,
-                            "count": 1864,
-                            "self": 0.04028913400725287,
+                            "total": 60.175131010014184,
+                            "count": 9128,
+                            "self": 0.20222826102599356,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 2.646693363995837,
-                                    "count": 1864,
-                                    "self": 2.646693363995837
+                                    "total": 13.45278677298893,
+                                    "count": 9128,
+                                    "self": 13.182463559988946,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.2703232129999833,
+                                            "count": 2,
+                                            "self": 0.2703232129999833
+                                        }
+                                    }
                                 },
                                 "_update_policy": {
-                                    "total": 9.912648704000048,
-                                    "count": 9,
-                                    "self": 4.249229723001918,
+                                    "total": 46.52011597599926,
+                                    "count": 45,
+                                    "self": 19.366904741990083,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 5.663418980998131,
-                                            "count": 456,
-                                            "self": 5.663418980998131
+                                            "total": 27.153211234009177,
+                                            "count": 2292,
+                                            "self": 27.153211234009177
                                         }
                                     }
                                 }
@@ -333,19 +340,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 9.82000074145617e-07,
+                    "total": 1.0539999948377954e-06,
                     "count": 1,
-                    "self": 9.82000074145617e-07
+                    "self": 1.0539999948377954e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.10508710899989637,
+                    "total": 0.08192204000010861,
                     "count": 1,
-                    "self": 0.0006039029997282341,
+                    "self": 0.0010590900001261616,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.10448320600016814,
+                            "total": 0.08086294999998245,
                             "count": 1,
-                            "self": 0.10448320600016814
+                            "self": 0.08086294999998245
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,22 +2,40 @@
     "SnowballTarget": {
         "checkpoints": [
             {
-                "steps": 20504,
-                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-20504.onnx",
-                "reward": 4.909090909090909,
-                "creation_time": 1774976513.4607475,
+                "steps": 49936,
+                "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-49936.onnx",
+                "reward": 13.454545454545455,
+                "creation_time": 1774976743.7856536,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-20504.pt"
+                    "results/SnowballTarget3/SnowballTarget/SnowballTarget-49936.pt"
+                ]
+            },
+            {
+                "steps": 99960,
+                "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-99960.onnx",
+                "reward": 17.636363636363637,
+                "creation_time": 1774976853.9458916,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget3/SnowballTarget/SnowballTarget-99960.pt"
+                ]
+            },
+            {
+                "steps": 100408,
+                "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-100408.onnx",
+                "reward": 17.636363636363637,
+                "creation_time": 1774976854.0681803,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget3/SnowballTarget/SnowballTarget-100408.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 20504,
-            "file_path": "results/SnowballTarget2/SnowballTarget.onnx",
-            "reward": 4.909090909090909,
-            "creation_time": 1774976513.4607475,
+            "steps": 100408,
+            "file_path": "results/SnowballTarget3/SnowballTarget.onnx",
+            "reward": 17.636363636363637,
+            "creation_time": 1774976854.0681803,
             "auxillary_file_paths": [
-                "results/SnowballTarget2/SnowballTarget/SnowballTarget-20504.pt"
+                "results/SnowballTarget3/SnowballTarget/SnowballTarget-100408.pt"
             ]
         }
     },