first commit

Worm.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9be148ecdde05c9e968a07c21ace3f2dfc9ba42aac6993ac747d76a138b0a29c
-size 2255612
+oid sha256:ec18ef17841d4b3803c9fc16461994d16883bbab6f1ffd7ed46874df1b55338f
+size 2259590

Worm/Worm-1010000.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec18ef17841d4b3803c9fc16461994d16883bbab6f1ffd7ed46874df1b55338f
+size 2259590

Worm/Worm-1010000.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98ee8803bf3f3055a93c8d8da89768f9e3f98e0c93927b2cc6e1375785fba308
+size 13495692

Worm/Worm-499000.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ef4420ca1e54bb1728ba2a08201e009235060ffbff9adde626ede23efa587f1
+size 2259590

Worm/Worm-499000.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78d84901e0635cce3b798bebe3676eeac68d868b3639f8529d309ce6f0b1eb65
+size 13495607

Worm/Worm-999000.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a36b58d29b52a0fe83c6f34914b37bac94ca22f9a169e5353be32cec6638b776
+size 2259590

Worm/Worm-999000.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12c0e5a7195b8d97f40703ae82a500cfbd9f89102f8937473a397801eedc44db
+size 13495607

Worm/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fed70d13d8903443f35196aaa11e834656a90812ea182b99e21f7090d825242
-size 4503458
+oid sha256:ceea0eabeba4dfa4fb2efa1ea7c17a9f49e44e14ddf0285d62dc9a1e131c1a03
+size 13495522

Worm/events.out.tfevents.1722629429.9fa18eb4fb71.20198.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f79fabfb6775450d60181bbc016e5403d3006fdc73a6701afac088a988c3a337
+size 154429

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"Worm": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 2024, "buffer_size": 20240, "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": 500000, "network_settings": {"normalize": true, "hidden_units": 512, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.995, "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": 70000, "time_horizon": 1000, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Worm/Worm", "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": "Worm Training", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"Worm": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 2024, "buffer_size": 20240, "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": 500000, "network_settings": {"normalize": true, "hidden_units": 512, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.995, "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": 1000000, "time_horizon": 1000, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Worm/Worm", "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": "Worm Training", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -38,7 +38,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 70000
+    max_steps: 1000000
     time_horizon: 1000
     summary_freq: 30000
     threaded: false

run_logs/Player-0.log

@@ -1,12 +1,9 @@
 Mono path[0] = '/content/ml-agents/training-envs-executables/linux/Worm/Worm_Data/Managed'
 Mono config path = '/content/ml-agents/training-envs-executables/linux/Worm/Worm_Data/MonoBleedingEdge/etc'
 Found 1 interfaces on host : 0) 172.28.0.12
-Multi-casting "[IP] 172.28.0.12 [Port] 55468 [Flags] 2 [Guid] 3378534234 [EditorId] 588871222 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.12) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
+Multi-casting "[IP] 172.28.0.12 [Port] 55198 [Flags] 2 [Guid] 2750458474 [EditorId] 588871222 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.12) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
-PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies
-PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies/UnityEnvironment
-Unable to load player prefs
 Initialize engine version: 2021.3.5f1 (40eb3a945986)
 [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/Worm/Worm_Data/UnitySubsystems
 Forcing GfxDevice: Null
@@ -36,7 +33,7 @@ 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  0.146 seconds
+- Completed reload, in  0.122 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)
@@ -68,7 +65,7 @@ ERROR: Shader Autodesk Interactive shader is not supported on this GPU (none of
 WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 1.259619 ms
+UnloadTime: 1.088404 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.
@@ -76,7 +73,7 @@ PlayerConnection::CleanupMemory 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: [4.0 KB-8.0 KB]: 20194 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
@@ -149,7 +146,7 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_TEMP_Profiler.Dispatcher]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
-      Peak Allocated Bytes 0 B
+      Peak Allocated Bytes 240 B
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 12]
       Initial Block Size 32.0 KB
@@ -207,25 +204,25 @@ PlayerConnection::CleanupMemory Statistics:
       Peak Allocated Bytes 128 B
       Overflow Count 0
 [ALLOC_MEMORYPROFILER]
-  Peak usage frame count: [64.0 KB-128.0 KB]: 1 frames
+  Peak usage frame count: [64.0 KB-128.0 KB]: 20195 frames
   Requested Block Size 1.0 MB
   Peak Block count 1
   Peak Allocated memory 103.1 KB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 65
+  Peak main deferred allocation count 83
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 0.8 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 20195 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 4.9 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 1 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 20195 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 17.9 MB
@@ -242,7 +239,7 @@ PlayerConnection::CleanupMemory 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)]
@@ -257,13 +254,13 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 0.8 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]: 20194 frames, [64.0 KB-128.0 KB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [128.0 KB-256.0 KB]: 1 frames
+      Peak usage frame count: [128.0 KB-256.0 KB]: 20195 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 151.2 KB
@@ -275,16 +272,16 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 0.8 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]: 20195 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: [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [256.0 KB-0.5 MB]: 20194 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
-      Peak Allocated memory 4.2 MB
+      Peak Allocated memory 4.1 MB
       Peak Large allocation bytes 0 B
 [ALLOC_TYPETREE] Dual Thread Allocator
   Peak main deferred allocation count 0
@@ -293,25 +290,25 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 0.8 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 1 frames
+      Peak usage frame count: [0-1.0 KB]: 20195 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: [8.0 KB-16.0 KB]: 1 frames
+      Peak usage frame count: [4.0 KB-8.0 KB]: 20194 frames, [8.0 KB-16.0 KB]: 1 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 9.3 KB
       Peak Large allocation bytes 0 B
 [ALLOC_PROFILER]
-  Peak usage frame count: [16.0 KB-32.0 KB]: 1 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 20195 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
-  Peak Allocated memory 27.4 KB
+  Peak Allocated memory 29.2 KB
   Peak Large allocation bytes 0 B
     [ALLOC_PROFILER_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 332 B
-##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1722629327804,"processId":19743,"allocatedMemory":1970109,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34460},{"Manager":10603},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3423},{"DynamicArray":30868},{"HashMap":7680},{"Utility":1360},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}
+##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1722632047012,"processId":20234,"allocatedMemory":1970109,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34460},{"Manager":10603},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3423},{"DynamicArray":30868},{"HashMap":7680},{"Utility":1360},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}

run_logs/timers.json

@@ -1,8 +1,154 @@
 {
     "name": "root",
+    "gauges": {
+        "Worm.Policy.Entropy.mean": {
+            "value": 1.3745230436325073,
+            "min": 1.3745230436325073,
+            "max": 1.418938398361206,
+            "count": 33
+        },
+        "Worm.Policy.Entropy.sum": {
+            "value": 41235.69140625,
+            "min": 41235.69140625,
+            "max": 42568.15234375,
+            "count": 33
+        },
+        "Worm.Environment.EpisodeLength.mean": {
+            "value": 999.0,
+            "min": 999.0,
+            "max": 999.0,
+            "count": 33
+        },
+        "Worm.Environment.EpisodeLength.sum": {
+            "value": 29970.0,
+            "min": 29970.0,
+            "max": 29970.0,
+            "count": 33
+        },
+        "Worm.Step.mean": {
+            "value": 989000.0,
+            "min": 29000.0,
+            "max": 989000.0,
+            "count": 33
+        },
+        "Worm.Step.sum": {
+            "value": 989000.0,
+            "min": 29000.0,
+            "max": 989000.0,
+            "count": 33
+        },
+        "Worm.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 11.160162925720215,
+            "min": -0.04857126995921135,
+            "max": 11.160162925720215,
+            "count": 33
+        },
+        "Worm.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 334.8049011230469,
+            "min": -1.4571380615234375,
+            "max": 334.8049011230469,
+            "count": 33
+        },
+        "Worm.Environment.CumulativeReward.mean": {
+            "value": 98.87115840911865,
+            "min": 0.11945420691918116,
+            "max": 98.87115840911865,
+            "count": 33
+        },
+        "Worm.Environment.CumulativeReward.sum": {
+            "value": 2966.1347522735596,
+            "min": 3.583626207575435,
+            "max": 2966.1347522735596,
+            "count": 33
+        },
+        "Worm.Policy.ExtrinsicReward.mean": {
+            "value": 98.87115840911865,
+            "min": 0.11945420691918116,
+            "max": 98.87115840911865,
+            "count": 33
+        },
+        "Worm.Policy.ExtrinsicReward.sum": {
+            "value": 2966.1347522735596,
+            "min": 3.583626207575435,
+            "max": 2966.1347522735596,
+            "count": 33
+        },
+        "Worm.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 33
+        },
+        "Worm.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 33
+        },
+        "Worm.Losses.PolicyLoss.mean": {
+            "value": 0.01527170484353389,
+            "min": 0.014031458659831384,
+            "max": 0.021487750632721663,
+            "count": 32
+        },
+        "Worm.Losses.PolicyLoss.sum": {
+            "value": 0.01527170484353389,
+            "min": 0.014031458659831384,
+            "max": 0.021487750632721663,
+            "count": 32
+        },
+        "Worm.Losses.ValueLoss.mean": {
+            "value": 1.0280655381225405,
+            "min": 0.0010215550844025398,
+            "max": 1.0280655381225405,
+            "count": 32
+        },
+        "Worm.Losses.ValueLoss.sum": {
+            "value": 1.0280655381225405,
+            "min": 0.0010215550844025398,
+            "max": 1.0280655381225405,
+            "count": 32
+        },
+        "Worm.Policy.LearningRate.mean": {
+            "value": 1.2000096000000011e-05,
+            "min": 1.2000096000000011e-05,
+            "max": 0.0002910000029999999,
+            "count": 32
+        },
+        "Worm.Policy.LearningRate.sum": {
+            "value": 1.2000096000000011e-05,
+            "min": 1.2000096000000011e-05,
+            "max": 0.0002910000029999999,
+            "count": 32
+        },
+        "Worm.Policy.Epsilon.mean": {
+            "value": 0.10400000000000001,
+            "min": 0.10400000000000001,
+            "max": 0.19699999999999998,
+            "count": 32
+        },
+        "Worm.Policy.Epsilon.sum": {
+            "value": 0.10400000000000001,
+            "min": 0.10400000000000001,
+            "max": 0.19699999999999998,
+            "count": 32
+        },
+        "Worm.Policy.Beta.mean": {
+            "value": 0.00020960000000000022,
+            "min": 0.00020960000000000022,
+            "max": 0.0048503,
+            "count": 32
+        },
+        "Worm.Policy.Beta.sum": {
+            "value": 0.00020960000000000022,
+            "min": 0.00020960000000000022,
+            "max": 0.0048503,
+            "count": 32
+        }
+    },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1722629321",
+        "start_time_seconds": "1722629428",
         "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/Worm.yaml --env=./training-envs-executables/linux/Worm/Worm --run-id=Worm Training --no-graphics --resume",
         "mlagents_version": "1.1.0.dev0",
@@ -10,36 +156,203 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.3.1+cu121",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1722629327"
+        "end_time_seconds": "1722632047"
     },
-    "total": 6.491948422999485,
+    "total": 2618.616045187,
     "count": 1,
-    "self": 1.0715788289999182,
+    "self": 0.5895694419996289,
     "children": {
         "run_training.setup": {
-            "total": 0.07545116499932192,
+            "total": 0.07057258599979832,
             "count": 1,
-            "self": 0.07545116499932192
+            "self": 0.07057258599979832
         },
         "TrainerController.start_learning": {
-            "total": 5.344918429000245,
+            "total": 2617.9559031590006,
             "count": 1,
-            "self": 0.0001798149996830034,
+            "self": 3.5184329071671527,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 4.355862774000343,
+                    "total": 2.115038299999469,
+                    "count": 1,
+                    "self": 2.115038299999469
+                },
+                "TrainerController.advance": {
+                    "total": 2612.202853132834,
+                    "count": 101000,
+                    "self": 3.6204221668522223,
+                    "children": {
+                        "env_step": {
+                            "total": 1783.504117572943,
+                            "count": 101000,
+                            "self": 1525.6088532438207,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 255.525407303081,
+                                    "count": 101000,
+                                    "self": 19.630982223135106,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 235.8944250799459,
+                                            "count": 101000,
+                                            "self": 235.8944250799459
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 2.3698570260412453,
+                                    "count": 101000,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 2611.036638657196,
+                                            "count": 101000,
+                                            "is_parallel": true,
+                                            "self": 1325.6193843631881,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.001291333000153827,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.00028855200071120635,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0010027809994426207,
+                                                                    "count": 2,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0010027809994426207
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.03778330699969956,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.00031413999931828585,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0006524330001411727,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0006524330001411727
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.03609104200040747,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.03609104200040747
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0007256919998326339,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00023427199903380824,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0004914200007988256,
+                                                                            "count": 2,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0004914200007988256
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 1285.4172542940078,
+                                                    "count": 100999,
+                                                    "is_parallel": true,
+                                                    "self": 30.023187571935523,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 44.49086723203709,
+                                                            "count": 100999,
+                                                            "is_parallel": true,
+                                                            "self": 44.49086723203709
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 1144.131780039098,
+                                                            "count": 100999,
+                                                            "is_parallel": true,
+                                                            "self": 1144.131780039098
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 66.77141945093717,
+                                                            "count": 100999,
+                                                            "is_parallel": true,
+                                                            "self": 20.456434648031973,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 46.3149848029052,
+                                                                    "count": 201998,
+                                                                    "is_parallel": true,
+                                                                    "self": 46.3149848029052
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 825.078313393039,
+                            "count": 101000,
+                            "self": 4.424324589042044,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 101.15340718999596,
+                                    "count": 101000,
+                                    "self": 100.83370532399567,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.3197018660002868,
+                                            "count": 2,
+                                            "self": 0.3197018660002868
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 719.500581614001,
+                                    "count": 33,
+                                    "self": 179.2270422210031,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 540.2735393929979,
+                                            "count": 1386,
+                                            "self": 540.2735393929979
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 9.79000105871819e-07,
                     "count": 1,
-                    "self": 4.355862774000343
+                    "self": 9.79000105871819e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.9888758400002189,
+                    "total": 0.11957783999969251,
                     "count": 1,
-                    "self": 0.004160178000347514,
+                    "self": 0.004787818999830051,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.9847156619998714,
+                            "total": 0.11479002099986246,
                             "count": 1,
-                            "self": 0.9847156619998714
+                            "self": 0.11479002099986246
                         }
                     }
                 }

run_logs/training_status.json

@@ -14,15 +14,42 @@
                 "auxillary_file_paths": [
                     "results/Worm Training/Worm/Worm-0.pt"
                 ]
+            },
+            {
+                "steps": 499000,
+                "file_path": "results/Worm Training/Worm/Worm-499000.onnx",
+                "reward": 12.827275966343127,
+                "creation_time": 1722630720.1919713,
+                "auxillary_file_paths": [
+                    "results/Worm Training/Worm/Worm-499000.pt"
+                ]
+            },
+            {
+                "steps": 999000,
+                "file_path": "results/Worm Training/Worm/Worm-999000.onnx",
+                "reward": 95.8111195034451,
+                "creation_time": 1722632026.4854581,
+                "auxillary_file_paths": [
+                    "results/Worm Training/Worm/Worm-999000.pt"
+                ]
+            },
+            {
+                "steps": 1010000,
+                "file_path": "results/Worm Training/Worm/Worm-1010000.onnx",
+                "reward": 96.71534004211426,
+                "creation_time": 1722632046.5004234,
+                "auxillary_file_paths": [
+                    "results/Worm Training/Worm/Worm-1010000.pt"
+                ]
             }
         ],
         "final_checkpoint": {
-            "steps": 0,
+            "steps": 1010000,
             "file_path": "results/Worm Training/Worm.onnx",
-            "reward": null,
-            "creation_time": 1722629326.817869,
+            "reward": 96.71534004211426,
+            "creation_time": 1722632046.5004234,
             "auxillary_file_paths": [
-                "results/Worm Training/Worm/Worm-0.pt"
+                "results/Worm Training/Worm/Worm-1010000.pt"
             ]
         }
     }