Second Worm

Worm.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef8b24fee934f1ca9158d0221f33eddbaa7d37050653af4763ea1b849da9b88f
+oid sha256:e83dea530136dc4c842ec28039e5030fa21215f0eda30e23159b764d754ea3cf
 size 2255979

Worm/{Worm-0.onnx → Worm-1499000.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b7b75b5e1702ea2740f74020fbb9ae1636753e5e63461abbb65794e298fcd52
+oid sha256:e97a3aa593cf318802942973d3d70d37989a28b03b850988998f68b3527bbfda
 size 2255979

Worm/Worm-1499000.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b45f7279241ce6feeeb05f973f0e6ec871999e723c2426f76a5cb9a11c25dc5
+size 13492844

Worm/{Worm-499000.onnx → Worm-1999000.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56467750059b619044f4e6d6e213a0778602011f12689b147d2c539e236363a9
+oid sha256:8aaea2725aec3d469676089a4a15a5bca5e0947a252323ce0d617a1fceb22b57
 size 2255979

Worm/{Worm-499000.pt → Worm-1999000.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6b4ddc36254983affb4935858168a263007e7c0f1d7e09a5615d15197b9003a
+oid sha256:08c3aa9d50bc5594c62bc660b081724bd62d5063584808b4781d3811f0271237
 size 13492846

Worm/{Worm-810000.onnx → Worm-2499000.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef8b24fee934f1ca9158d0221f33eddbaa7d37050653af4763ea1b849da9b88f
+oid sha256:1db54b530afeb3d1732b90c10eb33ca47ddd0b60887ffe99e2dd74a38a2d6db4
 size 2255979

Worm/Worm-2499000.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48d62051e0c1f38a65134823d0f95ce82e0bbcb0a4a8b5c3cc10f2acff1ee4db
+size 13492842

Worm/{Worm-0.pt → Worm-2999000.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd244db4098450cb0b9634341a302c2d29bcac5af307198099bb8f3a6586cba9
-size 4503875
+oid sha256:916c9cfb1d93c13d66040f5b9df5e4f5471133a3e991b17fe5e65e92705099dc
+size 2255979

Worm/Worm-2999000.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81a36e522800764292fa7cf36dcb04a19ed10978b98e9d3951e971a4c3fd00bb
+size 13492846

Worm/Worm-3010000.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e83dea530136dc4c842ec28039e5030fa21215f0eda30e23159b764d754ea3cf
+size 2255979

Worm/Worm-3010000.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0568c1a43341b07608c463005dfe60eab37bfde513bbe8dd8f307c61fee7531
+size 13492846

Worm/Worm-810000.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d7c177164762d008a2cbeec05fd3b7c64ec255be081aa4d492efce38f7cfc386
-size 13492845

Worm/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7c177164762d008a2cbeec05fd3b7c64ec255be081aa4d492efce38f7cfc386
-size 13492845
+oid sha256:a0568c1a43341b07608c463005dfe60eab37bfde513bbe8dd8f307c61fee7531
+size 13492846

Worm/events.out.tfevents.1666037381.a10efdb037db.1349.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f3a9ab3c9b0dee95077b3aeecb2a001f1f8cb94665cc5cd728d3afd841d0fe8
+size 84538

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": 800000, "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}
+{"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: 800000
+    max_steps: 3000000
     time_horizon: 1000
     summary_freq: 30000
     threaded: false

run_logs/Player-0.log

@@ -1,7 +1,7 @@
 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] 55331 [Flags] 2 [Guid] 3878089777 [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] 55296 [Flags] 2 [Guid] 2524799705 [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'
 Initialize engine version: 2021.3.5f1 (40eb3a945986)
@@ -33,7 +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  0.085 seconds
+- Completed reload, in  0.082 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)
@@ -65,7 +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: 0.716047 ms
+UnloadTime: 0.790525 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.
@@ -73,7 +73,7 @@ PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [4.0 KB-8.0 KB]: 43989 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
@@ -123,17 +123,17 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 64.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 15]
+    [ALLOC_TEMP_Background Job.Worker 2]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 2]
+    [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
@@ -183,12 +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
@@ -204,28 +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]: 1 frames
+  Peak usage frame count: [64.0 KB-128.0 KB]: 43990 frames
   Requested Block Size 1.0 MB
   Peak Block count 1
-  Peak Allocated memory 103.0 KB
+  Peak Allocated memory 103.1 KB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 75
+  Peak main deferred allocation count 93
     [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]: 1 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 43990 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 5.1 MB
+      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]: 1 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 43990 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.6 MB
+      Peak Allocated memory 17.8 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -239,7 +239,7 @@ PlayerConnection::CleanupMemory Statistics:
   Overflow Count (full) 0
 [ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
   Initial Block Size 2.0 MB
-  Used Block Count 1
+  Used Block Count 2
   Overflow Count (too large) 0
   Overflow Count (full) 0
 [ALLOC_TEMP_JOB_ASYNC (Background)]
@@ -254,13 +254,13 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 0.7 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 43989 frames, [64.0 KB-128.0 KB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [128.0 KB-256.0 KB]: 1 frames
+      Peak usage frame count: [128.0 KB-256.0 KB]: 43990 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 151.2 KB
@@ -272,13 +272,13 @@ 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]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 43990 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 0.6 MB
       Peak Large allocation bytes 0 B
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [256.0 KB-0.5 MB]: 43989 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
       Peak Allocated memory 4.2 MB
@@ -290,19 +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]: 1 frames
+      Peak usage frame count: [0-1.0 KB]: 43990 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_TYPETREE_THREAD]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 1 frames
+      Peak usage frame count: [4.0 KB-8.0 KB]: 43989 frames, [8.0 KB-16.0 KB]: 1 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 9.3 KB
       Peak Large allocation bytes 0 B
 [ALLOC_PROFILER]
-  Peak usage frame count: [16.0 KB-32.0 KB]: 1 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 43990 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
   Peak Allocated memory 27.4 KB
@@ -311,4 +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":1666035791980,"processId":963,"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":1666040174431,"processId":1360,"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

@@ -1,8 +1,154 @@
 {
     "name": "root",
+    "gauges": {
+        "Worm.Policy.Entropy.mean": {
+            "value": 1.229241132736206,
+            "min": 1.229241132736206,
+            "max": 1.4045292139053345,
+            "count": 73
+        },
+        "Worm.Policy.Entropy.sum": {
+            "value": 36877.234375,
+            "min": 36877.234375,
+            "max": 42135.875,
+            "count": 73
+        },
+        "Worm.Environment.EpisodeLength.mean": {
+            "value": 999.0,
+            "min": 999.0,
+            "max": 999.0,
+            "count": 73
+        },
+        "Worm.Environment.EpisodeLength.sum": {
+            "value": 29970.0,
+            "min": 29970.0,
+            "max": 29970.0,
+            "count": 73
+        },
+        "Worm.Step.mean": {
+            "value": 2999000.0,
+            "min": 839000.0,
+            "max": 2999000.0,
+            "count": 73
+        },
+        "Worm.Step.sum": {
+            "value": 2999000.0,
+            "min": 839000.0,
+            "max": 2999000.0,
+            "count": 73
+        },
+        "Worm.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 93.465576171875,
+            "min": 2.8544962406158447,
+            "max": 93.465576171875,
+            "count": 73
+        },
+        "Worm.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2803.96728515625,
+            "min": 82.78038787841797,
+            "max": 2803.96728515625,
+            "count": 73
+        },
+        "Worm.Environment.CumulativeReward.mean": {
+            "value": 500.6077484130859,
+            "min": 35.615565635007,
+            "max": 502.77891438802084,
+            "count": 73
+        },
+        "Worm.Environment.CumulativeReward.sum": {
+            "value": 15018.232452392578,
+            "min": 1032.851403415203,
+            "max": 15083.367431640625,
+            "count": 73
+        },
+        "Worm.Policy.ExtrinsicReward.mean": {
+            "value": 500.6077484130859,
+            "min": 35.615565635007,
+            "max": 502.77891438802084,
+            "count": 73
+        },
+        "Worm.Policy.ExtrinsicReward.sum": {
+            "value": 15018.232452392578,
+            "min": 1032.851403415203,
+            "max": 15083.367431640625,
+            "count": 73
+        },
+        "Worm.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 73
+        },
+        "Worm.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 73
+        },
+        "Worm.Losses.PolicyLoss.mean": {
+            "value": 0.016588100611919628,
+            "min": 0.013904854820880462,
+            "max": 0.02259645519717153,
+            "count": 72
+        },
+        "Worm.Losses.PolicyLoss.sum": {
+            "value": 0.016588100611919628,
+            "min": 0.013904854820880462,
+            "max": 0.02259645519717153,
+            "count": 72
+        },
+        "Worm.Losses.ValueLoss.mean": {
+            "value": 6.791361593064808,
+            "min": 0.3025680315636453,
+            "max": 6.791361593064808,
+            "count": 72
+        },
+        "Worm.Losses.ValueLoss.sum": {
+            "value": 6.791361593064808,
+            "min": 0.3025680315636453,
+            "max": 6.791361593064808,
+            "count": 72
+        },
+        "Worm.Policy.LearningRate.mean": {
+            "value": 3.0000990000000026e-06,
+            "min": 3.0000990000000026e-06,
+            "max": 0.00021600002800000002,
+            "count": 72
+        },
+        "Worm.Policy.LearningRate.sum": {
+            "value": 3.0000990000000026e-06,
+            "min": 3.0000990000000026e-06,
+            "max": 0.00021600002800000002,
+            "count": 72
+        },
+        "Worm.Policy.Epsilon.mean": {
+            "value": 0.101,
+            "min": 0.101,
+            "max": 0.17199999999999996,
+            "count": 72
+        },
+        "Worm.Policy.Epsilon.sum": {
+            "value": 0.101,
+            "min": 0.101,
+            "max": 0.17199999999999996,
+            "count": 72
+        },
+        "Worm.Policy.Beta.mean": {
+            "value": 5.990000000000004e-05,
+            "min": 5.990000000000004e-05,
+            "max": 0.0036027999999999998,
+            "count": 72
+        },
+        "Worm.Policy.Beta.sum": {
+            "value": 5.990000000000004e-05,
+            "min": 5.990000000000004e-05,
+            "max": 0.0036027999999999998,
+            "count": 72
+        }
+    },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1666035784",
+        "start_time_seconds": "1666037378",
         "python_version": "3.7.15 (default, Oct 12 2022, 19:14:55) \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 --resume",
         "mlagents_version": "0.29.0.dev0",
@@ -10,41 +156,210 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.8.1+cu102",
         "numpy_version": "1.21.6",
-        "end_time_seconds": "1666035792"
+        "end_time_seconds": "1666040174"
     },
-    "total": 7.046008780000193,
+    "total": 2795.585059426001,
     "count": 1,
-    "self": 0.4276084950015502,
+    "self": 0.43695850200128916,
     "children": {
         "run_training.setup": {
-            "total": 0.03434168999956455,
+            "total": 0.03357971500008716,
             "count": 1,
-            "self": 0.03434168999956455
+            "self": 0.03357971500008716
         },
         "TrainerController.start_learning": {
-            "total": 6.584058594999078,
+            "total": 2795.1145212089996,
             "count": 1,
-            "self": 0.00014713899872731417,
+            "self": 4.019733900127903,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 6.414663907000431,
+                    "total": 6.480569323000964,
                     "count": 1,
-                    "self": 6.414663907000431
+                    "self": 6.480569323000964
+                },
+                "TrainerController.advance": {
+                    "total": 2784.4882801858694,
+                    "count": 220000,
+                    "self": 4.558426913774383,
+                    "children": {
+                        "env_step": {
+                            "total": 2263.2740849732563,
+                            "count": 220000,
+                            "self": 1974.7209297231639,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 286.01488853631054,
+                                    "count": 220000,
+                                    "self": 18.177517826858093,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 267.83737070945244,
+                                            "count": 220000,
+                                            "self": 65.32958338285061,
+                                            "children": {
+                                                "TorchPolicy.sample_actions": {
+                                                    "total": 202.50778732660183,
+                                                    "count": 220000,
+                                                    "self": 202.50778732660183
+                                                }
+                                            }
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 2.5382667137819226,
+                                    "count": 220000,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 2787.0640148304465,
+                                            "count": 220000,
+                                            "is_parallel": true,
+                                            "self": 1076.449595679831,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0011139419984829146,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.00036556099985318724,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0007483809986297274,
+                                                                    "count": 2,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0007483809986297274
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.031062957999893115,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0002357159974053502,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00040761300078884233,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00040761300078884233
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.029851909001081367,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.029851909001081367
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0005677200006175553,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0002312990000064019,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.00033642100061115343,
+                                                                            "count": 2,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.00033642100061115343
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 1710.6144191506155,
+                                                    "count": 219999,
+                                                    "is_parallel": true,
+                                                    "self": 37.60127453309906,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 68.68218915573561,
+                                                            "count": 219999,
+                                                            "is_parallel": true,
+                                                            "self": 68.68218915573561
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 1508.379839666486,
+                                                            "count": 219999,
+                                                            "is_parallel": true,
+                                                            "self": 1508.379839666486
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 95.95111579529475,
+                                                            "count": 219999,
+                                                            "is_parallel": true,
+                                                            "self": 39.10947331166426,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 56.841642483630494,
+                                                                    "count": 439998,
+                                                                    "is_parallel": true,
+                                                                    "self": 56.841642483630494
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 516.6557682988387,
+                            "count": 220000,
+                            "self": 5.211558121975031,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 143.5901288608784,
+                                    "count": 220000,
+                                    "self": 142.95464681787598,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.635482043002412,
+                                            "count": 5,
+                                            "self": 0.635482043002412
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 367.85408131598524,
+                                    "count": 73,
+                                    "self": 312.19023667705187,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 55.66384463893337,
+                                            "count": 3066,
+                                            "self": 55.66384463893337
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
                 },
                 "trainer_threads": {
-                    "total": 1.446000169380568e-06,
+                    "total": 1.5260011423379183e-06,
                     "count": 1,
-                    "self": 1.446000169380568e-06
+                    "self": 1.5260011423379183e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.1692461029997503,
+                    "total": 0.12593627400019614,
                     "count": 1,
-                    "self": 0.003433119998589973,
+                    "self": 0.0032265320005535614,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.16581298300116032,
+                            "total": 0.12270974199964257,
                             "count": 1,
-                            "self": 0.16581298300116032
+                            "self": 0.12270974199964257
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,49 +2,58 @@
     "Worm": {
         "checkpoints": [
             {
-                "steps": 0,
-                "file_path": "results/Worm Training/Worm/Worm-0.onnx",
-                "reward": null,
-                "creation_time": 1666034471.3089633,
+                "steps": 1499000,
+                "file_path": "results/Worm Training/Worm/Worm-1499000.onnx",
+                "reward": 203.0606468463766,
+                "creation_time": 1666038254.7243264,
                 "auxillary_file_paths": [
-                    "results/Worm Training/Worm/Worm-0.pt"
+                    "results/Worm Training/Worm/Worm-1499000.pt"
                 ]
             },
             {
-                "steps": 499000,
-                "file_path": "results/Worm Training/Worm/Worm-499000.onnx",
-                "reward": 5.651541089013718,
-                "creation_time": 1666035125.033573,
+                "steps": 1999000,
+                "file_path": "results/Worm Training/Worm/Worm-1999000.onnx",
+                "reward": 334.9367563348067,
+                "creation_time": 1666038889.9494998,
                 "auxillary_file_paths": [
-                    "results/Worm Training/Worm/Worm-499000.pt"
+                    "results/Worm Training/Worm/Worm-1999000.pt"
                 ]
             },
             {
-                "steps": 810000,
-                "file_path": "results/Worm Training/Worm/Worm-810000.onnx",
-                "reward": 39.625718625386554,
-                "creation_time": 1666035514.4797227,
+                "steps": 2499000,
+                "file_path": "results/Worm Training/Worm/Worm-2499000.onnx",
+                "reward": 463.07848103841144,
+                "creation_time": 1666039526.7448213,
                 "auxillary_file_paths": [
-                    "results/Worm Training/Worm/Worm-810000.pt"
+                    "results/Worm Training/Worm/Worm-2499000.pt"
                 ]
             },
             {
-                "steps": 810000,
-                "file_path": "results/Worm Training/Worm/Worm-810000.onnx",
-                "reward": null,
-                "creation_time": 1666035791.58613,
+                "steps": 2999000,
+                "file_path": "results/Worm Training/Worm/Worm-2999000.onnx",
+                "reward": 501.30250917632003,
+                "creation_time": 1666040157.1010897,
                 "auxillary_file_paths": [
-                    "results/Worm Training/Worm/Worm-810000.pt"
+                    "results/Worm Training/Worm/Worm-2999000.pt"
+                ]
+            },
+            {
+                "steps": 3010000,
+                "file_path": "results/Worm Training/Worm/Worm-3010000.onnx",
+                "reward": 498.17021484375,
+                "creation_time": 1666040174.0398881,
+                "auxillary_file_paths": [
+                    "results/Worm Training/Worm/Worm-3010000.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 810000,
+            "steps": 3010000,
             "file_path": "results/Worm Training/Worm.onnx",
-            "reward": null,
-            "creation_time": 1666035791.58613,
+            "reward": 498.17021484375,
+            "creation_time": 1666040174.0398881,
             "auxillary_file_paths": [
-                "results/Worm Training/Worm/Worm-810000.pt"
+                "results/Worm Training/Worm/Worm-3010000.pt"
             ]
         }
     },