Second Worm

Worm.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e6aabd1fe150a31b120b4105f85ecf7ff19782eb0db0467b843b22e2de90c79
+oid sha256:d8ea592327a41ee66237c0cc8c4b3f1e70af151d0f62c5889d485bbba11f935e
 size 2255979

Worm/{Worm-499000.onnx → Worm-1499000.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f19e965e0c9497e5faab0bac840513e94d249d81b77e0a7fd227f31987d62bef
+oid sha256:5919b06d354532e26918ed655ce85c51cf059e923226d72696c5851dcf241d6b
 size 2255979

Worm/{Worm-499000.pt → Worm-1499000.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93dad8190190ae65b94aff153e6828e0fb85f102d18f10eb1527ea5f56fcb5af
+oid sha256:f0f5224f7eebd0374ef3b2efef14d0d151bd37157065c60357b61ce677dcbd63
 size 13492846

Worm/{Worm-510000.onnx → Worm-1999000.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e6aabd1fe150a31b120b4105f85ecf7ff19782eb0db0467b843b22e2de90c79
+oid sha256:2238b31f285bf346d0b04d3420e45774e5f7832d9b1d727b73ac075731c03e04
 size 2255979

Worm/{Worm-510000.pt → Worm-1999000.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5df13118e3e50559cad231cdbd7447b68b4fd7e753b3ae34f534cb3e1e30adc
+oid sha256:edad77a49c5a5377552c0f0795768f4727bc21822dbfab6125e855887f95b45a
 size 13492846

Worm/Worm-2499000.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:656036e766448b1ef7d15c96ba1c1270b4c27891f3fdce81cb94f9842ddc49a0
+size 2255979

Worm/Worm-2499000.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3136406a8b76264a63bff5f8cb15e752d6f46073d29d0c8284998748301a9104
+size 13492846

Worm/Worm-2999000.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9312fac23ad0d4990cde5dbed278130191bcc3abc67e3c7f5bcd4d886cb8c23c
+size 2255979

Worm/Worm-2999000.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69e12a9bb9aa64d085f13d90f22ca71ebeb28ba50218717dba4b85fdfc988185
+size 13492846

Worm/Worm-3010000.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8ea592327a41ee66237c0cc8c4b3f1e70af151d0f62c5889d485bbba11f935e
+size 2255979

Worm/Worm-3010000.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c417038515d4dc4348d2d2a0607fce07800cd41201ce614b048b3e2e0ba03eb6
+size 13492846

Worm/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5df13118e3e50559cad231cdbd7447b68b4fd7e753b3ae34f534cb3e1e30adc
+oid sha256:c417038515d4dc4348d2d2a0607fce07800cd41201ce614b048b3e2e0ba03eb6
 size 13492846

Worm/events.out.tfevents.1662408100.d155cc9641b4.709.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9d19559b01d09048bc78e6c4fafa20326c8b0a7467dd8d73deab59800c9469a
+size 1022

Worm/events.out.tfevents.1662408140.d155cc9641b4.780.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:343b9f50ce9f1445e88ca12b60b72c1589930769f4d7d88d652bfc4be15ef958
+size 113121

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, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "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, "checkpoint_interval": 500000, "max_steps": 500000, "time_horizon": 1000, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./trained-envs-executables/linux/Worm/Worm", "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": "Worm Training", "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": {"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, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "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, "checkpoint_interval": 500000, "max_steps": 3000000, "time_horizon": 1000, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./trained-envs-executables/linux/Worm/Worm", "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": "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

@@ -36,7 +36,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     checkpoint_interval: 500000
-    max_steps: 500000
+    max_steps: 3000000
     time_horizon: 1000
     summary_freq: 30000
     threaded: false
@@ -65,7 +65,7 @@ checkpoint_settings:
   run_id: Worm Training
   initialize_from: null
   load_model: false
-  resume: false
+  resume: true
   force: false
   train_model: false
   inference: false

run_logs/Player-0.log

@@ -1,12 +1,9 @@
 Mono path[0] = '/content/ml-agents/trained-envs-executables/linux/Worm/Worm_Data/Managed'
 Mono config path = '/content/ml-agents/trained-envs-executables/linux/Worm/Worm_Data/MonoBleedingEdge/etc'
 Found 1 interfaces on host : 0) 172.28.0.2
-Multi-casting "[IP] 172.28.0.2 [Port] 55060 [Flags] 2 [Guid] 2843271672 [EditorId] 588871222 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.2) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
+Multi-casting "[IP] 172.28.0.2 [Port] 55427 [Flags] 2 [Guid] 875153399 [EditorId] 588871222 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.2) [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/trained-envs-executables/linux/Worm/Worm_Data/UnitySubsystems
 Forcing GfxDevice: Null
@@ -36,7 +33,7 @@ ALSA lib pcm.c:2495:(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  0.091 seconds
+- Completed reload, in  0.093 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: 0.822514 ms
+UnloadTime: 0.742962 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: [4.0 KB-8.0 KB]: 10197 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [4.0 KB-8.0 KB]: 49987 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
@@ -131,12 +128,12 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 15]
+    [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_Background Job.Worker 7]
+    [ALLOC_TEMP_Background Job.Worker 15]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -186,12 +183,12 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0.8 KB
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 9]
+    [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 14]
+    [ALLOC_TEMP_Background Job.Worker 9]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -207,28 +204,28 @@ PlayerConnection::CleanupMemory Statistics:
       Peak Allocated Bytes 128 B
       Overflow Count 0
 [ALLOC_MEMORYPROFILER]
-  Peak usage frame count: [64.0 KB-128.0 KB]: 10198 frames
+  Peak usage frame count: [64.0 KB-128.0 KB]: 49988 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 22
+  Peak main deferred allocation count 65
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 0.7 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [4.0 MB-8.0 MB]: 10198 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 49988 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 5.0 MB
+      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]: 10198 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 49988 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.8 MB
+      Peak Allocated memory 17.9 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -257,13 +254,13 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 0.7 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 10197 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 49987 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]: 10198 frames
+      Peak usage frame count: [128.0 KB-256.0 KB]: 49988 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 0.7 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 10198 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 49988 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: [256.0 KB-0.5 MB]: 10197 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [256.0 KB-0.5 MB]: 49987 frames, [2.0 MB-4.0 MB]: 1 frames
       Requested Block Size 4.0 MB
-      Peak Block count 2
-      Peak Allocated memory 4.2 MB
+      Peak Block count 1
+      Peak Allocated memory 3.8 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 0.7 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 10198 frames
+      Peak usage frame count: [0-1.0 KB]: 49988 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: [4.0 KB-8.0 KB]: 10197 frames, [8.0 KB-16.0 KB]: 1 frames
+      Peak usage frame count: [4.0 KB-8.0 KB]: 49987 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]: 10198 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 49988 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":1662407917408,"processId":247,"allocatedMemory":1957305,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"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":3420},{"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":1662411364209,"processId":791,"allocatedMemory":1957305,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"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":3420},{"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

@@ -2,220 +2,220 @@
     "name": "root",
     "gauges": {
         "Worm.Policy.Entropy.mean": {
-            "value": 1.428634762763977,
-            "min": 1.418938398361206,
-            "max": 1.4288861751556396,
-            "count": 17
+            "value": 1.2281074523925781,
+            "min": 1.2281074523925781,
+            "max": 1.428634762763977,
+            "count": 83
         },
         "Worm.Policy.Entropy.sum": {
-            "value": 42859.04296875,
-            "min": 42568.15234375,
-            "max": 42866.5859375,
-            "count": 17
+            "value": 36843.22265625,
+            "min": 36843.22265625,
+            "max": 42859.04296875,
+            "count": 83
         },
         "Worm.Environment.EpisodeLength.mean": {
             "value": 999.0,
             "min": 999.0,
             "max": 999.0,
-            "count": 17
+            "count": 83
         },
         "Worm.Environment.EpisodeLength.sum": {
             "value": 29970.0,
             "min": 29970.0,
             "max": 29970.0,
-            "count": 17
+            "count": 83
         },
         "Worm.Step.mean": {
-            "value": 509000.0,
-            "min": 29000.0,
-            "max": 509000.0,
-            "count": 17
+            "value": 2999000.0,
+            "min": 539000.0,
+            "max": 2999000.0,
+            "count": 83
         },
         "Worm.Step.sum": {
-            "value": 509000.0,
-            "min": 29000.0,
-            "max": 509000.0,
-            "count": 17
+            "value": 2999000.0,
+            "min": 539000.0,
+            "max": 2999000.0,
+            "count": 83
         },
         "Worm.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.3504001200199127,
-            "min": 0.17438696324825287,
-            "max": 0.3504001200199127,
-            "count": 17
+            "value": 99.37371063232422,
+            "min": 0.34739580750465393,
+            "max": 99.37371063232422,
+            "count": 83
         },
         "Worm.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 10.512003898620605,
-            "min": 5.231608867645264,
-            "max": 10.512003898620605,
-            "count": 17
+            "value": 2981.21142578125,
+            "min": 10.074478149414062,
+            "max": 2981.21142578125,
+            "count": 83
         },
         "Worm.Environment.CumulativeReward.mean": {
-            "value": 3.974692003793704,
-            "min": 0.20528365392237902,
-            "max": 3.974692003793704,
-            "count": 17
+            "value": 520.6037302652995,
+            "min": 3.463860376127835,
+            "max": 520.6037302652995,
+            "count": 83
         },
         "Worm.Environment.CumulativeReward.sum": {
-            "value": 119.24076011381112,
-            "min": 5.9532259637489915,
-            "max": 119.24076011381112,
-            "count": 17
+            "value": 15618.111907958984,
+            "min": 100.45195090770721,
+            "max": 15618.111907958984,
+            "count": 83
         },
         "Worm.Policy.ExtrinsicReward.mean": {
-            "value": 3.974692003793704,
-            "min": 0.20528365392237902,
-            "max": 3.974692003793704,
-            "count": 17
+            "value": 520.6037302652995,
+            "min": 3.463860376127835,
+            "max": 520.6037302652995,
+            "count": 83
         },
         "Worm.Policy.ExtrinsicReward.sum": {
-            "value": 119.24076011381112,
-            "min": 5.9532259637489915,
-            "max": 119.24076011381112,
-            "count": 17
+            "value": 15618.111907958984,
+            "min": 100.45195090770721,
+            "max": 15618.111907958984,
+            "count": 83
         },
         "Worm.IsTraining.mean": {
-            "value": 0.0,
-            "min": 0.0,
+            "value": 1.0,
+            "min": 1.0,
             "max": 1.0,
-            "count": 17
+            "count": 83
         },
         "Worm.IsTraining.sum": {
-            "value": 0.0,
-            "min": 0.0,
+            "value": 1.0,
+            "min": 1.0,
             "max": 1.0,
-            "count": 17
+            "count": 83
         },
         "Worm.Losses.PolicyLoss.mean": {
-            "value": 0.01597467351460918,
-            "min": 0.012571080180350691,
-            "max": 0.02220770773627529,
-            "count": 16
+            "value": 0.016494595878092305,
+            "min": 0.012496019920079215,
+            "max": 0.02171410416901511,
+            "count": 82
         },
         "Worm.Losses.PolicyLoss.sum": {
-            "value": 0.01597467351460918,
-            "min": 0.012571080180350691,
-            "max": 0.02220770773627529,
-            "count": 16
+            "value": 0.016494595878092305,
+            "min": 0.012496019920079215,
+            "max": 0.02171410416901511,
+            "count": 82
         },
         "Worm.Losses.ValueLoss.mean": {
-            "value": 0.017406212720310406,
-            "min": 0.0014133177243084425,
-            "max": 0.017406212720310406,
-            "count": 16
+            "value": 5.932112194242931,
+            "min": 0.015786553112169106,
+            "max": 7.489530790419805,
+            "count": 82
         },
         "Worm.Losses.ValueLoss.sum": {
-            "value": 0.017406212720310406,
-            "min": 0.0014133177243084425,
-            "max": 0.017406212720310406,
-            "count": 16
+            "value": 5.932112194242931,
+            "min": 0.015786553112169106,
+            "max": 7.489530790419805,
+            "count": 82
         },
         "Worm.Policy.LearningRate.mean": {
-            "value": 1.2000096000000011e-05,
-            "min": 1.2000096000000011e-05,
-            "max": 0.00028200000599999995,
-            "count": 16
+            "value": 3.0000990000000026e-06,
+            "min": 3.0000990000000026e-06,
+            "max": 0.00024600001800000005,
+            "count": 82
         },
         "Worm.Policy.LearningRate.sum": {
-            "value": 1.2000096000000011e-05,
-            "min": 1.2000096000000011e-05,
-            "max": 0.00028200000599999995,
-            "count": 16
+            "value": 3.0000990000000026e-06,
+            "min": 3.0000990000000026e-06,
+            "max": 0.00024600001800000005,
+            "count": 82
         },
         "Worm.Policy.Epsilon.mean": {
-            "value": 0.10400000000000001,
-            "min": 0.10400000000000001,
-            "max": 0.194,
-            "count": 16
+            "value": 0.101,
+            "min": 0.101,
+            "max": 0.18200000000000005,
+            "count": 82
         },
         "Worm.Policy.Epsilon.sum": {
-            "value": 0.10400000000000001,
-            "min": 0.10400000000000001,
-            "max": 0.194,
-            "count": 16
+            "value": 0.101,
+            "min": 0.101,
+            "max": 0.18200000000000005,
+            "count": 82
         },
         "Worm.Policy.Beta.mean": {
-            "value": 0.00020960000000000022,
-            "min": 0.00020960000000000022,
-            "max": 0.0047006,
-            "count": 16
+            "value": 5.990000000000004e-05,
+            "min": 5.990000000000004e-05,
+            "max": 0.004101799999999999,
+            "count": 82
         },
         "Worm.Policy.Beta.sum": {
-            "value": 0.00020960000000000022,
-            "min": 0.00020960000000000022,
-            "max": 0.0047006,
-            "count": 16
+            "value": 5.990000000000004e-05,
+            "min": 5.990000000000004e-05,
+            "max": 0.004101799999999999,
+            "count": 82
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1662407258",
+        "start_time_seconds": "1662408137",
         "python_version": "3.7.13 (default, Apr 24 2022, 01:04:09) \n[GCC 7.5.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Worm.yaml --env=./trained-envs-executables/linux/Worm/Worm --run-id=Worm Training --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Worm.yaml --env=./trained-envs-executables/linux/Worm/Worm --run-id=Worm Training --no-graphics --resume",
         "mlagents_version": "0.29.0.dev0",
         "mlagents_envs_version": "0.29.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.8.1+cu102",
         "numpy_version": "1.21.6",
-        "end_time_seconds": "1662407917"
+        "end_time_seconds": "1662411364"
     },
-    "total": 658.778968944,
+    "total": 3227.223342972,
     "count": 1,
-    "self": 0.3867948189998742,
+    "self": 0.4319030539995765,
     "children": {
         "run_training.setup": {
-            "total": 0.04269169100001591,
+            "total": 0.04244852900001206,
             "count": 1,
-            "self": 0.04269169100001591
+            "self": 0.04244852900001206
         },
         "TrainerController.start_learning": {
-            "total": 658.349482434,
+            "total": 3226.7489913890004,
             "count": 1,
-            "self": 1.0174214150044918,
+            "self": 5.011138950077566,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 9.288609135999991,
+                    "total": 5.522024972000054,
                     "count": 1,
-                    "self": 9.288609135999991
+                    "self": 5.522024972000054
                 },
                 "TrainerController.advance": {
-                    "total": 647.9262574909956,
-                    "count": 51000,
-                    "self": 1.0869746869987011,
+                    "total": 3216.0898506789226,
+                    "count": 250000,
+                    "self": 5.196725621778114,
                     "children": {
                         "env_step": {
-                            "total": 534.6039458570044,
-                            "count": 51000,
-                            "self": 468.45977514498975,
+                            "total": 2633.163532223111,
+                            "count": 250000,
+                            "self": 2305.8082285332166,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 65.57130738201016,
-                                    "count": 51000,
-                                    "self": 4.223101729018367,
+                                    "total": 324.3323897798223,
+                                    "count": 250000,
+                                    "self": 22.1403746578103,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 61.348205652991794,
-                                            "count": 51000,
-                                            "self": 15.330910989985284,
+                                            "total": 302.192015122012,
+                                            "count": 250000,
+                                            "self": 76.07665375211377,
                                             "children": {
                                                 "TorchPolicy.sample_actions": {
-                                                    "total": 46.01729466300651,
-                                                    "count": 51000,
-                                                    "self": 46.01729466300651
+                                                    "total": 226.1153613698982,
+                                                    "count": 250000,
+                                                    "self": 226.1153613698982
                                                 }
                                             }
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.572863330004509,
-                                    "count": 51000,
+                                    "total": 3.022913910071793,
+                                    "count": 250000,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 655.9103684310032,
-                                            "count": 51000,
+                                            "total": 3217.189885740073,
+                                            "count": 250000,
                                             "is_parallel": true,
-                                            "self": 250.29203113401485,
+                                            "self": 1217.5168594330783,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -224,48 +224,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0010145619999661903,
+                                                            "total": 0.001029897000080382,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.00033098199992309674,
+                                                            "self": 0.00032974900022963993,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0006835800000430936,
+                                                                    "total": 0.000700147999850742,
                                                                     "count": 2,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0006835800000430936
+                                                                    "self": 0.000700147999850742
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.029888966000044093,
+                                                            "total": 0.02948732899994866,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0001705239999978403,
+                                                            "self": 0.00021975100003146508,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00042877300001009644,
+                                                                    "total": 0.00040555400005359843,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00042877300001009644
+                                                                    "self": 0.00040555400005359843
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.02893172599999616,
+                                                                    "total": 0.028275719000021127,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.02893172599999616
+                                                                    "self": 0.028275719000021127
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.00035794300003999524,
+                                                                    "total": 0.0005863049998424685,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00013223600006995184,
+                                                                    "self": 0.00021804899984090298,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0002257069999700434,
+                                                                            "total": 0.00036825600000156555,
                                                                             "count": 2,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0002257069999700434
+                                                                            "self": 0.00036825600000156555
                                                                         }
                                                                     }
                                                                 }
@@ -274,34 +274,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 405.6183372969884,
-                                                    "count": 50999,
+                                                    "total": 1999.6730263069946,
+                                                    "count": 249999,
                                                     "is_parallel": true,
-                                                    "self": 8.67063979999881,
+                                                    "self": 42.278463598850976,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 15.651258368993695,
-                                                            "count": 50999,
+                                                            "total": 76.01717416214797,
+                                                            "count": 249999,
                                                             "is_parallel": true,
-                                                            "self": 15.651258368993695
+                                                            "self": 76.01717416214797
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 358.49210899499656,
-                                                            "count": 50999,
+                                                            "total": 1769.8692639030182,
+                                                            "count": 249999,
                                                             "is_parallel": true,
-                                                            "self": 358.49210899499656
+                                                            "self": 1769.8692639030182
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 22.804330132999326,
-                                                            "count": 50999,
+                                                            "total": 111.50812464297746,
+                                                            "count": 249999,
                                                             "is_parallel": true,
-                                                            "self": 8.956747805012014,
+                                                            "self": 44.33241369017401,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 13.847582327987311,
-                                                                    "count": 101998,
+                                                                    "total": 67.17571095280346,
+                                                                    "count": 499998,
                                                                     "is_parallel": true,
-                                                                    "self": 13.847582327987311
+                                                                    "self": 67.17571095280346
                                                                 }
                                                             }
                                                         }
@@ -314,31 +314,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 112.2353369469925,
-                            "count": 51000,
-                            "self": 1.356951336996019,
+                            "total": 577.7295928340336,
+                            "count": 250000,
+                            "self": 6.568939747116701,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 34.14090397099642,
-                                    "count": 51000,
-                                    "self": 34.01851668299639,
+                                    "total": 166.98389703791872,
+                                    "count": 250000,
+                                    "self": 166.366754103919,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.12238728800002718,
-                                            "count": 1,
-                                            "self": 0.12238728800002718
+                                            "total": 0.6171429339997303,
+                                            "count": 5,
+                                            "self": 0.6171429339997303
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 76.73748163900007,
-                                    "count": 16,
-                                    "self": 66.82305585299991,
+                                    "total": 404.1767560489982,
+                                    "count": 83,
+                                    "self": 352.00662608197695,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 9.914425786000152,
-                                            "count": 672,
-                                            "self": 9.914425786000152
+                                            "total": 52.17012996702124,
+                                            "count": 3486,
+                                            "self": 52.17012996702124
                                         }
                                     }
                                 }
@@ -347,19 +347,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.0779999684018549e-06,
+                    "total": 1.1989995982730761e-06,
                     "count": 1,
-                    "self": 1.0779999684018549e-06
+                    "self": 1.1989995982730761e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.1171933140000192,
+                    "total": 0.12597558900051808,
                     "count": 1,
-                    "self": 0.0023542819999420317,
+                    "self": 0.003015911000147753,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.11483903200007717,
+                            "total": 0.12295967800037033,
                             "count": 1,
-                            "self": 0.11483903200007717
+                            "self": 0.12295967800037033
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,31 +2,58 @@
     "Worm": {
         "checkpoints": [
             {
-                "steps": 499000,
-                "file_path": "results/Worm Training/Worm/Worm-499000.onnx",
-                "reward": 4.126047435559724,
-                "creation_time": 1662407905.9600158,
+                "steps": 1499000,
+                "file_path": "results/Worm Training/Worm/Worm-1499000.onnx",
+                "reward": 229.31115880505791,
+                "creation_time": 1662409407.6591468,
                 "auxillary_file_paths": [
-                    "results/Worm Training/Worm/Worm-499000.pt"
+                    "results/Worm Training/Worm/Worm-1499000.pt"
                 ]
             },
             {
-                "steps": 510000,
-                "file_path": "results/Worm Training/Worm/Worm-510000.onnx",
-                "reward": 3.952044781910566,
-                "creation_time": 1662407917.057544,
+                "steps": 1999000,
+                "file_path": "results/Worm Training/Worm/Worm-1999000.onnx",
+                "reward": 381.3194644325658,
+                "creation_time": 1662410055.9258168,
                 "auxillary_file_paths": [
-                    "results/Worm Training/Worm/Worm-510000.pt"
+                    "results/Worm Training/Worm/Worm-1999000.pt"
+                ]
+            },
+            {
+                "steps": 2499000,
+                "file_path": "results/Worm Training/Worm/Worm-2499000.onnx",
+                "reward": 469.69168429904516,
+                "creation_time": 1662410703.4024246,
+                "auxillary_file_paths": [
+                    "results/Worm Training/Worm/Worm-2499000.pt"
+                ]
+            },
+            {
+                "steps": 2999000,
+                "file_path": "results/Worm Training/Worm/Worm-2999000.onnx",
+                "reward": 519.4827659870016,
+                "creation_time": 1662411347.7412777,
+                "auxillary_file_paths": [
+                    "results/Worm Training/Worm/Worm-2999000.pt"
+                ]
+            },
+            {
+                "steps": 3010000,
+                "file_path": "results/Worm Training/Worm/Worm-3010000.onnx",
+                "reward": 524.4866424560547,
+                "creation_time": 1662411363.8262858,
+                "auxillary_file_paths": [
+                    "results/Worm Training/Worm/Worm-3010000.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 510000,
+            "steps": 3010000,
             "file_path": "results/Worm Training/Worm.onnx",
-            "reward": 3.952044781910566,
-            "creation_time": 1662407917.057544,
+            "reward": 524.4866424560547,
+            "creation_time": 1662411363.8262858,
             "auxillary_file_paths": [
-                "results/Worm Training/Worm/Worm-510000.pt"
+                "results/Worm Training/Worm/Worm-3010000.pt"
             ]
         }
     },