Third Push

SnowballTarget.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c1a0dcbf706618ca492333647291c5aa6af5e578405733293fddacebc31084f
+oid sha256:d97f35ae1bab10bfd83e9e64bb95e28569b27da9597b84d7b93cb45eb397bb4a
 size 650646

SnowballTarget/SnowballTarget-149984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c8cef0f259163f5cfdbb6cb67d26c7a4c0bf063f4da74af40ec678f21b57316
+oid sha256:f9020c776387e7377da53b970849f772d9701108ac14b987b3612b153821710a
 size 650646

SnowballTarget/SnowballTarget-149984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5fc650450b88c355944c71d60f79d24d0964ad9a5b67217890974f3d9d44f1e
+oid sha256:6cced89dd491c4f41e1955474be80ba5f92f591764c41d335e80eb34402cfd1b
 size 3849115

SnowballTarget/SnowballTarget-199984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c1a0dcbf706618ca492333647291c5aa6af5e578405733293fddacebc31084f
+oid sha256:d97f35ae1bab10bfd83e9e64bb95e28569b27da9597b84d7b93cb45eb397bb4a
 size 650646

SnowballTarget/SnowballTarget-199984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea9da70781fc792f8a334ffd33204f2851d66a8bf4df7bd48f1a6ce87c78cc7d
+oid sha256:afb90de5180da4b6cf5282444ab75caabda45e373fc1434e3f7666bdc38235fe
 size 3849115

SnowballTarget/SnowballTarget-200112.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c1a0dcbf706618ca492333647291c5aa6af5e578405733293fddacebc31084f
+oid sha256:d97f35ae1bab10bfd83e9e64bb95e28569b27da9597b84d7b93cb45eb397bb4a
 size 650646

SnowballTarget/SnowballTarget-200112.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2144afc9a996cc7ecb897ba16f884d34118f5710991d06f4d23fe4e00d47506
+oid sha256:106c6d861f5d5aa069aec8368db8eeb180f3f2963970291c51c87523d36e002f
 size 3849115

SnowballTarget/SnowballTarget-49936.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d2be18554c2a1d7d7ad481564a2096c95d36f528f03572171a2adfdcbde6262
+oid sha256:c22d4284b92d1b6e823b28615b861472e7ecfdc4e50848fa073f17b5b1bff53b
 size 650646

SnowballTarget/SnowballTarget-49936.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d83a48f5664a724c98d28a445ce809b652ec10a38223404b3f4e641d48b5536
+oid sha256:9106023827024dceade797d334287bafeed69444a020506b43f06d0c7721b08d
 size 3849040

SnowballTarget/SnowballTarget-99960.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e53df9b5473c5b3fc5e7086a2dab0f221c93b0e7c9c39c3409a2a9b2f38c69e
+oid sha256:2990101d4004e0621127ce7dd575e1f7c19788ccb0fac2b274f8000490734568
 size 650646

SnowballTarget/SnowballTarget-99960.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d443e2e5e2c4026a1c73464fe85a161b7edfc8d63f16374a86a0518329b4b32
+oid sha256:af234d1c674dbf55249eea2e67b493537db4472d80f3e5d8ac9690d7efaa79e5
 size 3849040

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8148400f75c4541b7257423173e25d1c360ae44c8708b73770bc07031aff1735
+oid sha256:99fbaa9693cc72e19f1ff49905fd1df5732539487779cf24a259f78f6f216c28
 size 3848290

SnowballTarget/events.out.tfevents.1725452837.0d8b602b2909.1967.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fae347a3a529ba0de5d18e44c1b56b4dfb907b4e161a64b40cd3b11e755f1b2
+size 28345

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": true, "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": true, "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": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "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}

configuration.yaml

@@ -69,7 +69,7 @@ checkpoint_settings:
   run_id: SnowballTarget1
   initialize_from: null
   load_model: false
-  resume: true
+  resume: false
   force: false
   train_model: false
   inference: false

run_logs/Player-0.log

@@ -2,6 +2,9 @@ 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
@@ -31,7 +34,7 @@ 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  0.165 seconds
+- Completed reload, in  0.103 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 +45,7 @@ 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: 1.256428 ms
+UnloadTime: 0.729068 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 +53,7 @@ Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 5370 frames, [16.0 KB-32.0 KB]: 91 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
@@ -78,7 +81,7 @@ Memory Statistics:
     [ALLOC_TEMP_Job.Worker 0]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 2.8 KB
+      Peak Allocated Bytes 3.6 KB
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 10]
       Initial Block Size 32.0 KB
@@ -166,23 +169,23 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 3
+  Peak main deferred allocation count 37
     [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: [16.0 MB-32.0 MB]: 1 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 5462 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 20.6 MB
-      Peak Large allocation bytes 16.0 MB
+      Peak Allocated memory 6.5 MB
+      Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [1.0 MB-2.0 MB]: 1 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 5462 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 1.7 MB
-      Peak Large allocation bytes 0 B
+      Peak Allocated memory 17.9 MB
+      Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
   Used Block Count 1
@@ -195,7 +198,7 @@ Memory Statistics:
   Overflow Count (full) 0
 [ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
   Initial Block Size 2.0 MB
-  Used Block Count 1
+  Used Block Count 2
   Overflow Count (too large) 0
   Overflow Count (full) 0
 [ALLOC_TEMP_JOB_ASYNC (Background)]
@@ -210,13 +213,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 4708 frames, [64.0 KB-128.0 KB]: 754 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 65.6 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]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 5462 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 39.6 KB
@@ -228,13 +231,13 @@ 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]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 5462 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
-      Peak Allocated memory 0.5 MB
+      Peak Allocated memory 0.6 MB
       Peak Large allocation bytes 0 B
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 5461 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 +249,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 1 frames
+      Peak usage frame count: [0-1.0 KB]: 5462 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]: 1 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 5462 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.7 KB

run_logs/timers.json

@@ -1,40 +1,317 @@
 {
     "name": "root",
+    "gauges": {
+        "SnowballTarget.Policy.Entropy.mean": {
+            "value": 0.9373330473899841,
+            "min": 0.9373330473899841,
+            "max": 2.8643720149993896,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 8980.587890625,
+            "min": 8980.587890625,
+            "max": 29397.05078125,
+            "count": 20
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 199984.0,
+            "min": 9952.0,
+            "max": 199984.0,
+            "count": 20
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 199984.0,
+            "min": 9952.0,
+            "max": 199984.0,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 12.769098281860352,
+            "min": 0.3617739975452423,
+            "max": 12.769098281860352,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2489.97412109375,
+            "min": 70.18415832519531,
+            "max": 2581.089599609375,
+            "count": 20
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 20
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 8756.0,
+            "min": 8756.0,
+            "max": 10945.0,
+            "count": 20
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 25.181818181818183,
+            "min": 3.6136363636363638,
+            "max": 25.181818181818183,
+            "count": 20
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1108.0,
+            "min": 159.0,
+            "max": 1385.0,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 25.181818181818183,
+            "min": 3.6136363636363638,
+            "max": 25.181818181818183,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1108.0,
+            "min": 159.0,
+            "max": 1385.0,
+            "count": 20
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.06987765758651007,
+            "min": 0.06259998128179908,
+            "max": 0.07805273623528718,
+            "count": 20
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.2795106303460403,
+            "min": 0.2604347842884725,
+            "max": 0.36956131774315826,
+            "count": 20
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.18032612096445233,
+            "min": 0.12864354022267258,
+            "max": 0.27835796408209146,
+            "count": 20
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.7213044838578093,
+            "min": 0.5145741608906903,
+            "max": 1.3455678171971264,
+            "count": 20
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 8.082097306000005e-06,
+            "min": 8.082097306000005e-06,
+            "max": 0.00029184900271699997,
+            "count": 20
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 3.232838922400002e-05,
+            "min": 3.232838922400002e-05,
+            "max": 0.00138516003828,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.10269400000000001,
+            "min": 0.10269400000000001,
+            "max": 0.19728300000000004,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.41077600000000003,
+            "min": 0.41077600000000003,
+            "max": 0.96172,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 0.0001444306000000001,
+            "min": 0.0001444306000000001,
+            "max": 0.0048644217,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.0005777224000000004,
+            "min": 0.0005777224000000004,
+            "max": 0.023089828,
+            "count": 20
+        },
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 20
+        },
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 20
+        }
+    },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1725447559",
+        "start_time_seconds": "1725452837",
         "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
         "mlagents_version": "1.1.0.dev0",
         "mlagents_envs_version": "1.1.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.4.0+cu121",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1725447563"
+        "end_time_seconds": "1725453324"
     },
-    "total": 3.678352360999952,
+    "total": 487.700521837,
     "count": 1,
-    "self": 0.6420187269998223,
+    "self": 0.48108534499993993,
     "children": {
         "run_training.setup": {
-            "total": 0.11124676300005376,
+            "total": 0.0663818200000037,
             "count": 1,
-            "self": 0.11124676300005376
+            "self": 0.0663818200000037
         },
         "TrainerController.start_learning": {
-            "total": 2.925086871000076,
+            "total": 487.15305467200005,
             "count": 1,
-            "self": 0.00032350099991163006,
+            "self": 0.66380439699509,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.8003746439999304,
+                    "total": 2.1688778989999946,
                     "count": 1,
-                    "self": 2.8003746439999304
+                    "self": 2.1688778989999946
+                },
+                "TrainerController.advance": {
+                    "total": 484.24192170600503,
+                    "count": 18205,
+                    "self": 0.3251167240002246,
+                    "children": {
+                        "env_step": {
+                            "total": 483.9168049820048,
+                            "count": 18205,
+                            "self": 373.01660735300106,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 110.55774927799922,
+                                    "count": 18205,
+                                    "self": 1.6372911020024503,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 108.92045817599677,
+                                            "count": 18205,
+                                            "self": 108.92045817599677
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.34244835100452065,
+                                    "count": 18205,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 485.9318569990047,
+                                            "count": 18205,
+                                            "is_parallel": true,
+                                            "self": 227.92830747600698,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0024863480000476557,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.000710510000146769,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0017758379999008866,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0017758379999008866
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.04067934300002207,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0008000610000635788,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0004790790000015477,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0004790790000015477
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.037083150999990266,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.037083150999990266
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0023170519999666794,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00046226599994270146,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.001854786000023978,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.001854786000023978
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 258.00354952299773,
+                                                    "count": 18204,
+                                                    "is_parallel": true,
+                                                    "self": 11.7186065879946,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 6.1948302860022295,
+                                                            "count": 18204,
+                                                            "is_parallel": true,
+                                                            "self": 6.1948302860022295
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 201.9083923829956,
+                                                            "count": 18204,
+                                                            "is_parallel": true,
+                                                            "self": 201.9083923829956
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 38.1817202660053,
+                                                            "count": 18204,
+                                                            "is_parallel": true,
+                                                            "self": 7.395677356997908,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 30.786042909007392,
+                                                                    "count": 182040,
+                                                                    "is_parallel": true,
+                                                                    "self": 30.786042909007392
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
                 },
                 "trainer_threads": {
-                    "total": 3.537400016284664e-05,
+                    "total": 0.0001874069999985295,
                     "count": 1,
-                    "self": 3.537400016284664e-05,
+                    "self": 0.0001874069999985295,
                     "children": {
                         "thread_root": {
                             "total": 0.0,
@@ -43,16 +320,38 @@
                             "self": 0.0,
                             "children": {
                                 "trainer_advance": {
-                                    "total": 0.0002446969999709836,
-                                    "count": 1,
+                                    "total": 478.732554026972,
+                                    "count": 637741,
                                     "is_parallel": true,
-                                    "self": 2.55510001352377e-05,
+                                    "self": 13.856838520912618,
                                     "children": {
                                         "process_trajectory": {
-                                            "total": 0.0002191459998357459,
-                                            "count": 1,
+                                            "total": 256.0251156450591,
+                                            "count": 637741,
+                                            "is_parallel": true,
+                                            "self": 255.17942633905903,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 0.8456893060000539,
+                                                    "count": 4,
+                                                    "is_parallel": true,
+                                                    "self": 0.8456893060000539
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 208.85059986100032,
+                                            "count": 90,
                                             "is_parallel": true,
-                                            "self": 0.0002191459998357459
+                                            "self": 64.3202146309971,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 144.53038523000322,
+                                                    "count": 4584,
+                                                    "is_parallel": true,
+                                                    "self": 144.53038523000322
+                                                }
+                                            }
                                         }
                                     }
                                 }
@@ -61,14 +360,14 @@
                     }
                 },
                 "TrainerController._save_models": {
-                    "total": 0.12435335200007103,
+                    "total": 0.0782632629999398,
                     "count": 1,
-                    "self": 0.001577724000071612,
+                    "self": 0.0011008479999645715,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.12277562799999941,
+                            "total": 0.07716241499997523,
                             "count": 1,
-                            "self": 0.12277562799999941
+                            "self": 0.07716241499997523
                         }
                     }
                 }

run_logs/training_status.json

@@ -4,8 +4,8 @@
             {
                 "steps": 49936,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
-                "reward": 13.272727272727273,
-                "creation_time": 1725446580.2266877,
+                "reward": 13.545454545454545,
+                "creation_time": 1725452962.154112,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
                 ]
@@ -13,8 +13,8 @@
             {
                 "steps": 99960,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
-                "reward": 19.181818181818183,
-                "creation_time": 1725446726.775065,
+                "reward": 20.90909090909091,
+                "creation_time": 1725453083.0662804,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
                 ]
@@ -22,8 +22,8 @@
             {
                 "steps": 149984,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
-                "reward": 23.181818181818183,
-                "creation_time": 1725446873.8767211,
+                "reward": 24.636363636363637,
+                "creation_time": 1725453205.104856,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
                 ]
@@ -31,8 +31,8 @@
             {
                 "steps": 199984,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
-                "reward": 25.454545454545453,
-                "creation_time": 1725447018.8388464,
+                "reward": 25.09090909090909,
+                "creation_time": 1725453324.2524164,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
                 ]
@@ -40,17 +40,8 @@
             {
                 "steps": 200112,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
-                "reward": 25.454545454545453,
-                "creation_time": 1725447018.9591513,
-                "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
-                ]
-            },
-            {
-                "steps": 200112,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
-                "reward": null,
-                "creation_time": 1725447562.5325375,
+                "reward": 25.09090909090909,
+                "creation_time": 1725453324.3552895,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
                 ]
@@ -59,8 +50,8 @@
         "final_checkpoint": {
             "steps": 200112,
             "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": null,
-            "creation_time": 1725447562.5325375,
+            "reward": 25.09090909090909,
+            "creation_time": 1725453324.3552895,
             "auxillary_file_paths": [
                 "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
             ]