Trained Model v1.2

CubeChaseAgent.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23a6f9e48182387337673e7c8d312ef50b43ea15c2dcd0e75f2df7e0bbc8ca27
+size 74450

CubeChaseAgent/CubeChaseAgent-80967.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23a6f9e48182387337673e7c8d312ef50b43ea15c2dcd0e75f2df7e0bbc8ca27
+size 74450

CubeChaseAgent/CubeChaseAgent-80967.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:416853c459b02cb0ac2792db719f9d9b2713dc40c95bec120a66edf2f803ee79
+size 443995

CubeChaseAgent/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:416853c459b02cb0ac2792db719f9d9b2713dc40c95bec120a66edf2f803ee79
+size 443995

CubeChaseAgent/events.out.tfevents.1691412637.d64e0980d689.1843.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e65c1565f252147e7e37d4e95f54e26c94a454b9b0a836c6a5086516c46d257b
+size 44233

README.md

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

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"CubeChase": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 10, "buffer_size": 100, "learning_rate": 0.0003, "beta": 0.0005, "epsilon": 0.2, "lambd": 0.99, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "constant", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 128, "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": 5, "even_checkpoints": false, "max_steps": 500000, "time_horizon": 64, "summary_freq": 10000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/CubeChase/CubeChase", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "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}, "environment_parameters": null, "checkpoint_settings": {"run_id": "CubeChasev1.0", "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": {"CubeChaseAgent": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 10, "buffer_size": 100, "learning_rate": 0.0003, "beta": 0.0005, "epsilon": 0.2, "lambd": 0.99, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "constant", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 128, "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": 5, "even_checkpoints": false, "max_steps": 500000, "time_horizon": 64, "summary_freq": 10000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/CubeChase/CubeChase.x86_64", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "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}, "environment_parameters": null, "checkpoint_settings": {"run_id": "CubeChasev1.2", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -1,6 +1,6 @@
 default_settings: null
 behaviors:
-  CubeChase:
+  CubeChaseAgent:
     trainer_type: ppo
     hyperparameters:
       batch_size: 10
@@ -45,7 +45,7 @@ behaviors:
     self_play: null
     behavioral_cloning: null
 env_settings:
-  env_path: ./training-envs-executables/linux/CubeChase/CubeChase
+  env_path: ./training-envs-executables/linux/CubeChase/CubeChase.x86_64
   env_args: null
   base_port: 5005
   num_envs: 1
@@ -64,11 +64,11 @@ engine_settings:
   no_graphics: true
 environment_parameters: null
 checkpoint_settings:
-  run_id: CubeChasev1.0
+  run_id: CubeChasev1.2
   initialize_from: null
   load_model: false
   resume: false
-  force: false
+  force: true
   train_model: false
   inference: false
   results_dir: results

run_logs/Player-0.log

@@ -2,6 +2,9 @@ Mono path[0] = '/content/training-envs-executables/linux/CubeChase/CubeChase_Dat
 Mono config path = '/content/training-envs-executables/linux/CubeChase/CubeChase_Data/MonoBleedingEdge/etc'
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
+PlayerPrefs - Creating folder: /root/.config/unity3d/DefaultCompany
+PlayerPrefs - Creating folder: /root/.config/unity3d/DefaultCompany/CubeChase
+Unable to load player prefs
 Initialize engine version: 2021.3.22f1 (b6c551784ba3)
 [Subsystems] Discovering subsystems at path /content/training-envs-executables/linux/CubeChase/CubeChase_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  0.221 seconds
+- Completed reload, in  0.098 seconds
 ERROR: Shader Hidden/Universal Render Pipeline/Blit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Hidden/Universal Render Pipeline/CopyDepth shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Hidden/Universal Render Pipeline/Sampling shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -71,5 +74,218 @@ ERROR: Shader Universal Render Pipeline/Lit shader is not supported on this GPU
 WARNING: Shader Unsupported: 'Universal Render Pipeline/Lit' - 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: 4.564920 ms
+UnloadTime: 0.646957 ms
 requesting resize 84 x 84
+GRPC Exception: Status(StatusCode=Cancelled, Detail="CANCELLED"). Disconnecting from trainer.
+Setting up 1 worker threads for Enlighten.
+Memory Statistics:
+[ALLOC_TEMP_TLS] TLS Allocator
+  StackAllocators : 
+    [ALLOC_TEMP_MAIN]
+      Peak usage frame count: [1.0 KB-2.0 KB]: 972 frames, [2.0 MB-4.0 MB]: 1 frames
+      Initial Block Size 4.0 MB
+      Current Block Size 4.0 MB
+      Peak Allocated Bytes 2.3 MB
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 256 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 141.2 KB
+      Overflow Count 4
+    [ALLOC_TEMP_Background Job.Worker 8]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 9]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 10]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 14]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 6]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 12]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 15]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 1]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 2]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 7]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_AssetGarbageCollectorHelper]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 5]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 13]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 11]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 3]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 0]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 4]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+[ALLOC_DEFAULT] Dual Thread Allocator
+  Peak main deferred allocation count 4
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.2 MB
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 973 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 20.8 MB
+      Peak Large allocation bytes 16.0 MB
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [1.0 MB-2.0 MB]: 973 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 1.4 MB
+      Peak Large allocation bytes 0 B
+[ALLOC_TEMP_JOB_1_FRAME]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_2_FRAMES]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
+  Initial Block Size 2.0 MB
+  Used Block Count 2
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_ASYNC (Background)]
+  Initial Block Size 1.0 MB
+  Used Block Count 3
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_GFX] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.2 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 972 frames, [64.0 KB-128.0 KB]: 1 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 65.7 KB
+      Peak Large allocation bytes 0 B
+    [ALLOC_GFX_THREAD]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 973 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 36.2 KB
+      Peak Large allocation bytes 0 B
+[ALLOC_CACHEOBJECTS] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.2 MB
+    [ALLOC_CACHEOBJECTS_MAIN]
+      Peak usage frame count: [1.0 MB-2.0 MB]: 972 frames, [4.0 MB-8.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 1
+      Peak Allocated memory 5.8 MB
+      Peak Large allocation bytes 2.5 MB
+    [ALLOC_CACHEOBJECTS_THREAD]
+      Peak usage frame count: [256.0 KB-0.5 MB]: 972 frames, [1.0 MB-2.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 1
+      Peak Allocated memory 1.0 MB
+      Peak Large allocation bytes 0 B
+[ALLOC_TYPETREE] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.2 MB
+    [ALLOC_TYPETREE_MAIN]
+      Peak usage frame count: [0-1.0 KB]: 973 frames
+      Requested Block Size 2.0 MB
+      Peak Block count 1
+      Peak Allocated memory 1.1 KB
+      Peak Large allocation bytes 0 B
+    [ALLOC_TYPETREE_THREAD]
+      Peak usage frame count: [0-1.0 KB]: 973 frames
+      Requested Block Size 2.0 MB
+      Peak Block count 0
+      Peak Allocated memory 0 B
+      Peak Large allocation bytes 0 B

run_logs/timers.json

@@ -1,45 +1,353 @@
 {
     "name": "root",
+    "gauges": {
+        "CubeChaseAgent.Policy.Entropy.mean": {
+            "value": 1.3304638862609863,
+            "min": 1.3304638862609863,
+            "max": 1.4406789541244507,
+            "count": 8
+        },
+        "CubeChaseAgent.Policy.Entropy.sum": {
+            "value": 13371.162109375,
+            "min": 13371.162109375,
+            "max": 14743.5654296875,
+            "count": 8
+        },
+        "CubeChaseAgent.Environment.EpisodeLength.mean": {
+            "value": 2.8197408536585367,
+            "min": 2.8197408536585367,
+            "max": 12.106159895150721,
+            "count": 8
+        },
+        "CubeChaseAgent.Environment.EpisodeLength.sum": {
+            "value": 7399.0,
+            "min": 7399.0,
+            "max": 9237.0,
+            "count": 8
+        },
+        "CubeChaseAgent.Step.mean": {
+            "value": 79997.0,
+            "min": 9990.0,
+            "max": 79997.0,
+            "count": 8
+        },
+        "CubeChaseAgent.Step.sum": {
+            "value": 79997.0,
+            "min": 9990.0,
+            "max": 79997.0,
+            "count": 8
+        },
+        "CubeChaseAgent.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.9831324219703674,
+            "min": 0.43312692642211914,
+            "max": 0.9832891821861267,
+            "count": 8
+        },
+        "CubeChaseAgent.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2575.806884765625,
+            "min": 330.042724609375,
+            "max": 2575.806884765625,
+            "count": 8
+        },
+        "CubeChaseAgent.Environment.CumulativeReward.mean": {
+            "value": 0.9977099236641221,
+            "min": 0.5078740157480315,
+            "max": 0.9992038216560509,
+            "count": 8
+        },
+        "CubeChaseAgent.Environment.CumulativeReward.sum": {
+            "value": 2614.0,
+            "min": 387.0,
+            "max": 2614.0,
+            "count": 8
+        },
+        "CubeChaseAgent.Policy.ExtrinsicReward.mean": {
+            "value": 0.9977099236641221,
+            "min": 0.5078740157480315,
+            "max": 0.9992038216560509,
+            "count": 8
+        },
+        "CubeChaseAgent.Policy.ExtrinsicReward.sum": {
+            "value": 2614.0,
+            "min": 387.0,
+            "max": 2614.0,
+            "count": 8
+        },
+        "CubeChaseAgent.Losses.PolicyLoss.mean": {
+            "value": 0.2412640100830578,
+            "min": 0.2364040109031282,
+            "max": 0.2443406546307238,
+            "count": 8
+        },
+        "CubeChaseAgent.Losses.PolicyLoss.sum": {
+            "value": 22.92008095789049,
+            "min": 21.813553494995514,
+            "max": 23.20331698343004,
+            "count": 8
+        },
+        "CubeChaseAgent.Losses.ValueLoss.mean": {
+            "value": 0.0026035018763841144,
+            "min": 0.0011506950352082983,
+            "max": 0.08874128673615443,
+            "count": 8
+        },
+        "CubeChaseAgent.Losses.ValueLoss.sum": {
+            "value": 0.24733267825649086,
+            "min": 0.11046672337999663,
+            "max": 7.986715806253899,
+            "count": 8
+        },
+        "CubeChaseAgent.Policy.LearningRate.mean": {
+            "value": 0.00025501817920447155,
+            "min": 0.00025501817920447155,
+            "max": 0.00029694244768585103,
+            "count": 8
+        },
+        "CubeChaseAgent.Policy.LearningRate.sum": {
+            "value": 0.0242267270244248,
+            "min": 0.0242267270244248,
+            "max": 0.0270760528746492,
+            "count": 8
+        },
+        "CubeChaseAgent.Policy.Epsilon.mean": {
+            "value": 0.18500605473684215,
+            "min": 0.18500605473684215,
+            "max": 0.19898081555555558,
+            "count": 8
+        },
+        "CubeChaseAgent.Policy.Epsilon.sum": {
+            "value": 17.575575200000003,
+            "min": 17.575575200000003,
+            "max": 18.5282962,
+            "count": 8
+        },
+        "CubeChaseAgent.Policy.Beta.mean": {
+            "value": 0.0005000000000000001,
+            "min": 0.0005000000000000001,
+            "max": 0.0005000000000000001,
+            "count": 8
+        },
+        "CubeChaseAgent.Policy.Beta.sum": {
+            "value": 0.047500000000000014,
+            "min": 0.04500000000000001,
+            "max": 0.048000000000000015,
+            "count": 8
+        },
+        "CubeChaseAgent.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 8
+        },
+        "CubeChaseAgent.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 8
+        }
+    },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1691374425",
+        "start_time_seconds": "1691412635",
         "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/ppo/CubeChase.yaml --env=./training-envs-executables/linux/CubeChase/CubeChase --run-id=CubeChasev1.0 --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/ppo/CubeChase.yaml --env=./training-envs-executables/linux/CubeChase/CubeChase.x86_64 --run-id=CubeChasev1.2 --no-graphics --force",
         "mlagents_version": "0.31.0.dev0",
         "mlagents_envs_version": "0.31.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.11.0+cu102",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1691374431"
+        "end_time_seconds": "1691412880"
     },
-    "total": 6.10983647300003,
+    "total": 245.83182224499996,
     "count": 1,
-    "self": 0.02201324600002863,
+    "self": 0.4245115729999611,
     "children": {
         "run_training.setup": {
-            "total": 0.042684183999995184,
+            "total": 0.04349833100002343,
             "count": 1,
-            "self": 0.042684183999995184
+            "self": 0.04349833100002343
         },
         "TrainerController.start_learning": {
-            "total": 6.045139043000006,
+            "total": 245.36381234099997,
             "count": 1,
-            "self": 0.000548974000025737,
+            "self": 0.2728475159973982,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 6.044569276000004,
+                    "total": 6.391924240000037,
                     "count": 1,
-                    "self": 6.044569276000004
+                    "self": 6.391924240000037
+                },
+                "TrainerController.advance": {
+                    "total": 238.47294238400252,
+                    "count": 11102,
+                    "self": 0.22291748600707706,
+                    "children": {
+                        "env_step": {
+                            "total": 46.25549591399539,
+                            "count": 11102,
+                            "self": 44.18142690399924,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 1.9414303580004457,
+                                    "count": 11102,
+                                    "self": 0.2282176760034531,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 1.7132126819969926,
+                                            "count": 1621,
+                                            "self": 1.7132126819969926
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.13263865199570546,
+                                    "count": 11101,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 244.76964477900037,
+                                            "count": 11101,
+                                            "is_parallel": true,
+                                            "self": 212.69376319200012,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0012042240000482707,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0002967720000697227,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.000907451999978548,
+                                                                    "count": 2,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.000907451999978548
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.04441783600003646,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.00019538599997304118,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0011486580000337199,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0011486580000337199
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.04265053000000307,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.04265053000000307
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0004232620000266252,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0001985210000157167,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.00022474100001090846,
+                                                                            "count": 2,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.00022474100001090846
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 32.075881587000254,
+                                                    "count": 11100,
+                                                    "is_parallel": true,
+                                                    "self": 1.7562732710036357,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 1.98411509000357,
+                                                            "count": 11100,
+                                                            "is_parallel": true,
+                                                            "self": 1.98411509000357
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 24.525806725998393,
+                                                            "count": 11100,
+                                                            "is_parallel": true,
+                                                            "self": 24.525806725998393
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 3.8096864999946547,
+                                                            "count": 11100,
+                                                            "is_parallel": true,
+                                                            "self": 1.7021175089816438,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 2.107568991013011,
+                                                                    "count": 22200,
+                                                                    "is_parallel": true,
+                                                                    "self": 2.107568991013011
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 191.99452898400006,
+                            "count": 11101,
+                            "self": 0.25941598700370605,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 30.366022278994308,
+                                    "count": 11101,
+                                    "self": 30.366022278994308
+                                },
+                                "_update_policy": {
+                                    "total": 161.36909071800204,
+                                    "count": 763,
+                                    "self": 16.34106925999839,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 145.02802145800365,
+                                            "count": 23370,
+                                            "self": 145.02802145800365
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
                 },
                 "trainer_threads": {
-                    "total": 1.5859999962231086e-06,
+                    "total": 1.247000000148546e-06,
                     "count": 1,
-                    "self": 1.5859999962231086e-06
+                    "self": 1.247000000148546e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 1.920699997981501e-05,
+                    "total": 0.22609695400001328,
                     "count": 1,
-                    "self": 1.920699997981501e-05
+                    "self": 0.0005307090000314929,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.2255662449999818,
+                            "count": 1,
+                            "self": 0.2255662449999818
+                        }
+                    }
                 }
             }
         }

run_logs/training_status.json

@@ -1,4 +1,26 @@
 {
+    "CubeChaseAgent": {
+        "checkpoints": [
+            {
+                "steps": 80967,
+                "file_path": "results/CubeChasev1.2/CubeChaseAgent/CubeChaseAgent-80967.onnx",
+                "reward": 1.0,
+                "creation_time": 1691412880.5270169,
+                "auxillary_file_paths": [
+                    "results/CubeChasev1.2/CubeChaseAgent/CubeChaseAgent-80967.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 80967,
+            "file_path": "results/CubeChasev1.2/CubeChaseAgent.onnx",
+            "reward": 1.0,
+            "creation_time": 1691412880.5270169,
+            "auxillary_file_paths": [
+                "results/CubeChasev1.2/CubeChaseAgent/CubeChaseAgent-80967.pt"
+            ]
+        }
+    },
     "metadata": {
         "stats_format_version": "0.3.0",
         "mlagents_version": "0.31.0.dev0",