First training of Worm

Worm.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66321e05b4f65a0b05e81a90aa9f38b02aefe9c0c8d28503d1f27c4df707a08d
+oid sha256:ddfacd3446a4afea1e6c6298d7e369c4802e00d912a8efc93366da983efd0bcf
 size 2255979

Worm/{Worm-1010000.onnx → Worm-1499000.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66321e05b4f65a0b05e81a90aa9f38b02aefe9c0c8d28503d1f27c4df707a08d
+oid sha256:371604f0c48b81bb5470c657a262fae4dc03c77523da3ebfd432d98bcdcf7552
 size 2255979

Worm/{Worm-999000.pt → Worm-1499000.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91885ca04b06910fd1a51f99cf381ee51c4ab83fe5ed2bba6ed01e74eb5f64c0
+oid sha256:735e2b2bdb94223de48acd5170a3663744ad5d63925a9c07396d0a93b29124b4
 size 13492846

Worm/{Worm-999000.onnx → Worm-1999000.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8708cc92378c11ef7cb16585e532923b627b3dd9f47ca43fbbf549c115a73f9
+oid sha256:9f1c51a3e715f057be7db8e17b710fd86b687ed564f63e4b5b13683fabe0ab16
 size 2255979

Worm/{Worm-1010000.pt → Worm-1999000.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f17e2a9b912387f5e2d46faaab27b1b0e6caa5e055c5783947f43bbdadc2fc59
+oid sha256:03dd5ac1c56db06812e31f702af114df3a27621b6c0458231653e33473057213
 size 13492846

Worm/{Worm-499000.onnx → Worm-2499000.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67d6621077072c150d83037cf442db9c315daed135bb6ccfa2bc10fc3f80e29d
+oid sha256:d24af45d54cbc7ee74cd7a5284b2280781f0c2f0288145239e29dccc102abef4
 size 2255979

Worm/{Worm-499000.pt → Worm-2499000.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28848b72a0826da3967ae749316bdf180077590b921c40edc87530f5c890e416
+oid sha256:c01d9cc43d9a69d2888e20a89203c957555095e7302516d7a21dbbf1eae11f0b
 size 13492846

Worm/Worm-2999000.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6c199c6e4e8bea9e75f6c96d10068ae17bf1c1352aad77cb456514fcafac815
+size 2255979

Worm/Worm-2999000.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3989a270f5c70a93bcf21c5ea195f9d9c3d7c2b3566f46b8f7a3c167aa63c51
+size 13492846

Worm/Worm-3010000.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddfacd3446a4afea1e6c6298d7e369c4802e00d912a8efc93366da983efd0bcf
+size 2255979

Worm/Worm-3010000.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e92a66e699e31cbaa32bc9554f0655d7b30927c05b29b3fb005e351046549972
+size 13492846

Worm/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f17e2a9b912387f5e2d46faaab27b1b0e6caa5e055c5783947f43bbdadc2fc59
+oid sha256:e92a66e699e31cbaa32bc9554f0655d7b30927c05b29b3fb005e351046549972
 size 13492846

Worm/events.out.tfevents.1673596724.f4a4ae4e0774.12557.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a730d0aaabe4a936d1560fd879c07ed16385d2f50afed99200456685864f5fe0
+size 59029

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": 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, "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": "./training-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: 1000000
+    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/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) 172.28.0.2
-Multi-casting "[IP] 172.28.0.2 [Port] 55440 [Flags] 2 [Guid] 383153397 [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] 55342 [Flags] 2 [Guid] 227577708 [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/training-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  0.099 seconds
+- Completed reload, in  0.087 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: 1.184685 ms
+UnloadTime: 0.720988 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]: 20194 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [4.0 KB-8.0 KB]: 39990 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
@@ -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]: 20195 frames
+  Peak usage frame count: [64.0 KB-128.0 KB]: 39991 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 83
+  Peak main deferred allocation count 23
     [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]: 20195 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 39991 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 5.0 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 20195 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 39991 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 17.8 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]: 20194 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 39990 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]: 20195 frames
+      Peak usage frame count: [128.0 KB-256.0 KB]: 39991 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]: 20195 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 39991 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]: 20194 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [256.0 KB-0.5 MB]: 39990 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
-      Peak Allocated memory 4.1 MB
+      Peak Allocated memory 4.2 MB
       Peak Large allocation bytes 0 B
 [ALLOC_TYPETREE] Dual Thread Allocator
   Peak main deferred allocation count 0
@@ -293,19 +290,19 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 0.7 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 20195 frames
+      Peak usage frame count: [0-1.0 KB]: 39991 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]: 20194 frames, [8.0 KB-16.0 KB]: 1 frames
+      Peak usage frame count: [4.0 KB-8.0 KB]: 39990 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]: 20195 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 39991 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
   Peak Allocated memory 29.2 KB
@@ -314,4 +311,4 @@ PlayerConnection::CleanupMemory Statistics:
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 332 B
-##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1673596249504,"processId":3230,"allocatedMemory":1957308,"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":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":1673599255711,"processId":12574,"allocatedMemory":1957308,"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":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

@@ -2,220 +2,220 @@
     "name": "root",
     "gauges": {
         "Worm.Policy.Entropy.mean": {
-            "value": 1.3855702877044678,
-            "min": 1.3855702877044678,
-            "max": 1.4216307401657104,
-            "count": 33
+            "value": 1.2473835945129395,
+            "min": 1.2473835945129395,
+            "max": 1.3855050802230835,
+            "count": 67
         },
         "Worm.Policy.Entropy.sum": {
-            "value": 41567.109375,
-            "min": 41567.109375,
-            "max": 42648.921875,
-            "count": 33
+            "value": 37421.5078125,
+            "min": 13855.05078125,
+            "max": 41526.13671875,
+            "count": 67
         },
         "Worm.Environment.EpisodeLength.mean": {
             "value": 999.0,
             "min": 999.0,
             "max": 999.0,
-            "count": 33
+            "count": 67
         },
         "Worm.Environment.EpisodeLength.sum": {
             "value": 29970.0,
-            "min": 29970.0,
+            "min": 9990.0,
             "max": 29970.0,
-            "count": 33
+            "count": 67
         },
         "Worm.Step.mean": {
-            "value": 989000.0,
-            "min": 29000.0,
-            "max": 989000.0,
-            "count": 33
+            "value": 2999000.0,
+            "min": 1019000.0,
+            "max": 2999000.0,
+            "count": 67
         },
         "Worm.Step.sum": {
-            "value": 989000.0,
-            "min": 29000.0,
-            "max": 989000.0,
-            "count": 33
+            "value": 2999000.0,
+            "min": 1019000.0,
+            "max": 2999000.0,
+            "count": 67
         },
         "Worm.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 7.239400386810303,
-            "min": 0.07958345115184784,
-            "max": 7.239400386810303,
-            "count": 33
+            "value": 88.42459106445312,
+            "min": 7.076003074645996,
+            "max": 88.42459106445312,
+            "count": 67
         },
         "Worm.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 217.1820068359375,
-            "min": 2.307919979095459,
-            "max": 217.1820068359375,
-            "count": 33
+            "value": 2652.73779296875,
+            "min": 63.68402862548828,
+            "max": 2652.73779296875,
+            "count": 67
         },
         "Worm.Environment.CumulativeReward.mean": {
-            "value": 69.1140012105306,
-            "min": 0.36864107997874573,
-            "max": 69.1140012105306,
-            "count": 33
+            "value": 485.6922536214193,
+            "min": 65.49288283454047,
+            "max": 485.6922536214193,
+            "count": 67
         },
         "Worm.Environment.CumulativeReward.sum": {
-            "value": 2073.420036315918,
-            "min": 11.059232399362372,
-            "max": 2073.420036315918,
-            "count": 33
+            "value": 14570.767608642578,
+            "min": 589.4359455108643,
+            "max": 14570.767608642578,
+            "count": 67
         },
         "Worm.Policy.ExtrinsicReward.mean": {
-            "value": 69.1140012105306,
-            "min": 0.36864107997874573,
-            "max": 69.1140012105306,
-            "count": 33
+            "value": 485.6922536214193,
+            "min": 65.49288283454047,
+            "max": 485.6922536214193,
+            "count": 67
         },
         "Worm.Policy.ExtrinsicReward.sum": {
-            "value": 2073.420036315918,
-            "min": 11.059232399362372,
-            "max": 2073.420036315918,
-            "count": 33
+            "value": 14570.767608642578,
+            "min": 589.4359455108643,
+            "max": 14570.767608642578,
+            "count": 67
         },
         "Worm.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 67
         },
         "Worm.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 67
         },
         "Worm.Losses.PolicyLoss.mean": {
-            "value": 0.01700288818461732,
-            "min": 0.012559550390592665,
-            "max": 0.02170003344820413,
-            "count": 32
+            "value": 0.01923009639479763,
+            "min": 0.012588625807655348,
+            "max": 0.022810967846973135,
+            "count": 66
         },
         "Worm.Losses.PolicyLoss.sum": {
-            "value": 0.01700288818461732,
-            "min": 0.012559550390592665,
-            "max": 0.02170003344820413,
-            "count": 32
+            "value": 0.01923009639479763,
+            "min": 0.012588625807655348,
+            "max": 0.022810967846973135,
+            "count": 66
         },
         "Worm.Losses.ValueLoss.mean": {
-            "value": 0.6396481550875164,
-            "min": 0.0015461337946665783,
-            "max": 0.6396481550875164,
-            "count": 32
+            "value": 8.96524442945208,
+            "min": 0.7316992041610536,
+            "max": 8.96524442945208,
+            "count": 66
         },
         "Worm.Losses.ValueLoss.sum": {
-            "value": 0.6396481550875164,
-            "min": 0.0015461337946665783,
-            "max": 0.6396481550875164,
-            "count": 32
+            "value": 8.96524442945208,
+            "min": 0.7316992041610536,
+            "max": 8.96524442945208,
+            "count": 66
         },
         "Worm.Policy.LearningRate.mean": {
-            "value": 1.2000096000000011e-05,
-            "min": 1.2000096000000011e-05,
-            "max": 0.0002910000029999999,
-            "count": 32
+            "value": 1.0000996666666565e-06,
+            "min": 1.0000996666666565e-06,
+            "max": 0.0001960000346666667,
+            "count": 66
         },
         "Worm.Policy.LearningRate.sum": {
-            "value": 1.2000096000000011e-05,
-            "min": 1.2000096000000011e-05,
-            "max": 0.0002910000029999999,
-            "count": 32
+            "value": 1.0000996666666565e-06,
+            "min": 1.0000996666666565e-06,
+            "max": 0.0001960000346666667,
+            "count": 66
         },
         "Worm.Policy.Epsilon.mean": {
-            "value": 0.10400000000000001,
-            "min": 0.10400000000000001,
-            "max": 0.19699999999999998,
-            "count": 32
+            "value": 0.10033333333333334,
+            "min": 0.10033333333333334,
+            "max": 0.1653333333333333,
+            "count": 66
         },
         "Worm.Policy.Epsilon.sum": {
-            "value": 0.10400000000000001,
-            "min": 0.10400000000000001,
-            "max": 0.19699999999999998,
-            "count": 32
+            "value": 0.10033333333333334,
+            "min": 0.10033333333333334,
+            "max": 0.1653333333333333,
+            "count": 66
         },
         "Worm.Policy.Beta.mean": {
-            "value": 0.00020960000000000022,
-            "min": 0.00020960000000000022,
-            "max": 0.0048503,
-            "count": 32
+            "value": 2.663333333333317e-05,
+            "min": 2.663333333333317e-05,
+            "max": 0.003270133333333334,
+            "count": 66
         },
         "Worm.Policy.Beta.sum": {
-            "value": 0.00020960000000000022,
-            "min": 0.00020960000000000022,
-            "max": 0.0048503,
-            "count": 32
+            "value": 2.663333333333317e-05,
+            "min": 2.663333333333317e-05,
+            "max": 0.003270133333333334,
+            "count": 66
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1673594490",
+        "start_time_seconds": "1673596721",
         "python_version": "3.8.16 (default, Dec  7 2022, 01:12:13) \n[GCC 7.5.0]",
-        "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",
+        "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": "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": "1673596249"
+        "end_time_seconds": "1673599255"
     },
-    "total": 1759.3737478989997,
+    "total": 2533.895560222,
     "count": 1,
-    "self": 0.390409956999747,
+    "self": 0.3826803120000477,
     "children": {
         "run_training.setup": {
-            "total": 0.1343860179999865,
+            "total": 0.11366827200026819,
             "count": 1,
-            "self": 0.1343860179999865
+            "self": 0.11366827200026819
         },
         "TrainerController.start_learning": {
-            "total": 1758.848951924,
+            "total": 2533.3992116379995,
             "count": 1,
-            "self": 2.8911124390392615,
+            "self": 3.6822132199090447,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 11.722249229999989,
+                    "total": 6.363252045000081,
                     "count": 1,
-                    "self": 11.722249229999989
+                    "self": 6.363252045000081
                 },
                 "TrainerController.advance": {
-                    "total": 1744.1191414329605,
-                    "count": 101000,
-                    "self": 3.274395886034199,
+                    "total": 2523.2309502990906,
+                    "count": 200000,
+                    "self": 3.704318265191432,
                     "children": {
                         "env_step": {
-                            "total": 1480.5657777029633,
-                            "count": 101000,
-                            "self": 1270.740867891979,
+                            "total": 2090.9527501580924,
+                            "count": 200000,
+                            "self": 1825.465447973144,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 207.63498515105084,
-                                    "count": 101000,
-                                    "self": 14.168415779053475,
+                                    "total": 262.99436340811735,
+                                    "count": 200000,
+                                    "self": 16.696327589024804,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 193.46656937199737,
-                                            "count": 101000,
-                                            "self": 54.161449766959095,
+                                            "total": 246.29803581909255,
+                                            "count": 200000,
+                                            "self": 61.51209154401113,
                                             "children": {
                                                 "TorchPolicy.sample_actions": {
-                                                    "total": 139.30511960503827,
-                                                    "count": 101000,
-                                                    "self": 139.30511960503827
+                                                    "total": 184.78594427508142,
+                                                    "count": 200000,
+                                                    "self": 184.78594427508142
                                                 }
                                             }
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 2.1899246599334674,
-                                    "count": 101000,
+                                    "total": 2.4929387768311244,
+                                    "count": 200000,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 1752.1385774060286,
-                                            "count": 101000,
+                                            "total": 2525.981292178923,
+                                            "count": 200000,
                                             "is_parallel": true,
-                                            "self": 675.5021697600755,
+                                            "self": 941.2388896158895,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -224,48 +224,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0031173570000646578,
+                                                            "total": 0.0009491400001024886,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.00042032100009237183,
+                                                            "self": 0.0003122079997410765,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.002697035999972286,
+                                                                    "total": 0.0006369320003614121,
                                                                     "count": 2,
                                                                     "is_parallel": true,
-                                                                    "self": 0.002697035999972286
+                                                                    "self": 0.0006369320003614121
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.03844414299999244,
+                                                            "total": 0.032511349999822414,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0003189819999533938,
+                                                            "self": 0.0002228489997833094,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00048704200003157894,
+                                                                    "total": 0.0004554140000436746,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00048704200003157894
+                                                                    "self": 0.0004554140000436746
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.03669263699998737,
+                                                                    "total": 0.03119927000034295,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.03669263699998737
+                                                                    "self": 0.03119927000034295
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0009454820000200925,
+                                                                    "total": 0.0006338169996524812,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0002787139999327337,
+                                                                    "self": 0.00027419100024417276,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0006667680000873588,
+                                                                            "total": 0.0003596259994083084,
                                                                             "count": 2,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0006667680000873588
+                                                                            "self": 0.0003596259994083084
                                                                         }
                                                                     }
                                                                 }
@@ -274,34 +274,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1076.636407645953,
-                                                    "count": 100999,
+                                                    "total": 1584.7424025630335,
+                                                    "count": 199999,
                                                     "is_parallel": true,
-                                                    "self": 26.31573110897216,
+                                                    "self": 33.701285600835945,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 44.83505546201013,
-                                                            "count": 100999,
+                                                            "total": 67.27756689308626,
+                                                            "count": 199999,
                                                             "is_parallel": true,
-                                                            "self": 44.83505546201013
+                                                            "self": 67.27756689308626
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 938.2505047979997,
-                                                            "count": 100999,
+                                                            "total": 1384.9838197258905,
+                                                            "count": 199999,
                                                             "is_parallel": true,
-                                                            "self": 938.2505047979997
+                                                            "self": 1384.9838197258905
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 67.23511627697121,
-                                                            "count": 100999,
+                                                            "total": 98.77973034322076,
+                                                            "count": 199999,
                                                             "is_parallel": true,
-                                                            "self": 25.792633828914973,
+                                                            "self": 37.63187597298793,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 41.44248244805624,
-                                                                    "count": 201998,
+                                                                    "total": 61.147854370232835,
+                                                                    "count": 399998,
                                                                     "is_parallel": true,
-                                                                    "self": 41.44248244805624
+                                                                    "self": 61.147854370232835
                                                                 }
                                                             }
                                                         }
@@ -314,31 +314,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 260.2789678439632,
-                            "count": 101000,
-                            "self": 4.255586039994341,
+                            "total": 428.5738818758068,
+                            "count": 200000,
+                            "self": 4.225397488769886,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 73.89419529096926,
-                                    "count": 101000,
-                                    "self": 73.6270702959689,
+                                    "total": 112.8562919180381,
+                                    "count": 200000,
+                                    "self": 112.34849405003797,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.26712499500035847,
-                                            "count": 2,
-                                            "self": 0.26712499500035847
+                                            "total": 0.5077978680001252,
+                                            "count": 4,
+                                            "self": 0.5077978680001252
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 182.12918651299958,
-                                    "count": 33,
-                                    "self": 152.5630465890041,
+                                    "total": 311.49219246899884,
+                                    "count": 66,
+                                    "self": 262.42764281600284,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 29.56613992399548,
-                                            "count": 1386,
-                                            "self": 29.56613992399548
+                                            "total": 49.06454965299599,
+                                            "count": 2772,
+                                            "self": 49.06454965299599
                                         }
                                     }
                                 }
@@ -347,19 +347,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 8.249999154941179e-07,
+                    "total": 9.129998943535611e-07,
                     "count": 1,
-                    "self": 8.249999154941179e-07
+                    "self": 9.129998943535611e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.11644799700025033,
+                    "total": 0.12279516099988541,
                     "count": 1,
-                    "self": 0.002145944999938365,
+                    "self": 0.0027404689999457332,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.11430205200031196,
+                            "total": 0.12005469199993968,
                             "count": 1,
-                            "self": 0.11430205200031196
+                            "self": 0.12005469199993968
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,40 +2,58 @@
     "Worm": {
         "checkpoints": [
             {
-                "steps": 499000,
-                "file_path": "results/Worm Training/Worm/Worm-499000.onnx",
-                "reward": 8.598412576866778,
-                "creation_time": 1673595386.747185,
+                "steps": 1499000,
+                "file_path": "results/Worm Training/Worm/Worm-1499000.onnx",
+                "reward": 186.55951266818576,
+                "creation_time": 1673597362.9371624,
                 "auxillary_file_paths": [
-                    "results/Worm Training/Worm/Worm-499000.pt"
+                    "results/Worm Training/Worm/Worm-1499000.pt"
                 ]
             },
             {
-                "steps": 999000,
-                "file_path": "results/Worm Training/Worm/Worm-999000.onnx",
-                "reward": 68.18547609117296,
-                "creation_time": 1673596238.4526818,
+                "steps": 1999000,
+                "file_path": "results/Worm Training/Worm/Worm-1999000.onnx",
+                "reward": 280.24454524599275,
+                "creation_time": 1673597990.9565368,
                 "auxillary_file_paths": [
-                    "results/Worm Training/Worm/Worm-999000.pt"
+                    "results/Worm Training/Worm/Worm-1999000.pt"
                 ]
             },
             {
-                "steps": 1010000,
-                "file_path": "results/Worm Training/Worm/Worm-1010000.onnx",
-                "reward": 63.31785802841186,
-                "creation_time": 1673596249.1613116,
+                "steps": 2499000,
+                "file_path": "results/Worm Training/Worm/Worm-2499000.onnx",
+                "reward": 427.55323871813323,
+                "creation_time": 1673598618.544684,
                 "auxillary_file_paths": [
-                    "results/Worm Training/Worm/Worm-1010000.pt"
+                    "results/Worm Training/Worm/Worm-2499000.pt"
+                ]
+            },
+            {
+                "steps": 2999000,
+                "file_path": "results/Worm Training/Worm/Worm-2999000.onnx",
+                "reward": 485.8847961425781,
+                "creation_time": 1673599244.528669,
+                "auxillary_file_paths": [
+                    "results/Worm Training/Worm/Worm-2999000.pt"
+                ]
+            },
+            {
+                "steps": 3010000,
+                "file_path": "results/Worm Training/Worm/Worm-3010000.onnx",
+                "reward": 486.01788635253905,
+                "creation_time": 1673599255.353914,
+                "auxillary_file_paths": [
+                    "results/Worm Training/Worm/Worm-3010000.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1010000,
+            "steps": 3010000,
             "file_path": "results/Worm Training/Worm.onnx",
-            "reward": 63.31785802841186,
-            "creation_time": 1673596249.1613116,
+            "reward": 486.01788635253905,
+            "creation_time": 1673599255.353914,
             "auxillary_file_paths": [
-                "results/Worm Training/Worm/Worm-1010000.pt"
+                "results/Worm Training/Worm/Worm-3010000.pt"
             ]
         }
     },