Huggy

Huggy.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9850a7e4c61c4f540d38cbab430ddf8de59f089edd7fb6ea7548303a6dfd114e
+oid sha256:19d890ef7fec31af35b312bb0437aeda7e528b30551a59339390f1a146efbdc9
 size 2273984

Huggy/Huggy-2199988.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d36a6b66afd4f8c395da74244bd9c3c0a16584756d75cb7ca33a6c0184a2335
+size 2273984

Huggy/Huggy-2199988.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f36de17a8bc513759e53ef22f9d1e4311953a374199fb5a984f14a03a2c45d5
+size 13509473

Huggy/Huggy-2399969.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64d3e6c7425a0baa076b2fb8f14bc071acf038054780797aad4ac97db13f85f8
+size 2273984

Huggy/Huggy-2399969.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e81807516455eb2d32372dc3e817420332e68332c439ca401b56a52d5ba9198
+size 13509473

Huggy/Huggy-2599926.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ac130e550b6d23bfce611ea6ed5e79393ee65a1ee8db2735bc3532d5e9e1993
+size 2273984

Huggy/Huggy-2599926.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0f5d4ca421709a440d575860394b2f35236a0cba8b171155dd8f19f031f27ad
+size 13509473

Huggy/Huggy-2799973.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbf904f57e024b801980b01198f67bd0473c4e90fba3b69393cf97cd9baac6c7
+size 2273984

Huggy/Huggy-2799973.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d136958be5ec77b21f088786872a8da08f81c5f2e25e0185dad63b42aba7cb0
+size 13509473

Huggy/Huggy-2999431.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21e4e53b50100dc7d81186006374903d39febf09a3cdee618f14040d853248de
+size 2273984

Huggy/Huggy-2999431.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5aaa842d03fde9e04a8c43facaecaed6f76fe888b0ec0d03cef0ce285677ae1
+size 13509473

Huggy/Huggy-3000181.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19d890ef7fec31af35b312bb0437aeda7e528b30551a59339390f1a146efbdc9
+size 2273984

Huggy/Huggy-3000181.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:528c3d53ac8995c7d34957a8f9e91705f0795cdbbcd853f7f2d89a91d7eedc3e
+size 13509473

Huggy/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6442314da17c7a352ef2d4b0918c2a499cef73d2913059ef068671d6adc65f3
+oid sha256:cd5447fb4bf805b8742eb1a612e0c3388b95f3ec9674829157fd5d5a8c9e5389
 size 13509218

Huggy/events.out.tfevents.1709907819.e0b69161de45.22551.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a43e50e208248057dcdadb7ef858c1675ca0658bf68fda82aa57a6797892a38
+size 1121

Huggy/events.out.tfevents.1709907871.e0b69161de45.22834.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04d19e2bb128c65f91e4cc37abea02844d219457588084fdb95db249977ff67a
+size 204562

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"Huggy": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 200000, "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": 15, "even_checkpoints": false, "max_steps": 2000000, "time_horizon": 1000, "summary_freq": 50000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./trained-envs-executables/linux/Huggy/Huggy", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Huggy2", "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": {"Huggy": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 200000, "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": 15, "even_checkpoints": false, "max_steps": 3000000, "time_horizon": 1000, "summary_freq": 50000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./trained-envs-executables/linux/Huggy/Huggy", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20.0, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Huggy2", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -38,7 +38,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 15
     even_checkpoints: false
-    max_steps: 2000000
+    max_steps: 3000000
     time_horizon: 1000
     summary_freq: 50000
     threaded: false
@@ -59,7 +59,7 @@ engine_settings:
   width: 84
   height: 84
   quality_level: 5
-  time_scale: 20
+  time_scale: 20.0
   target_frame_rate: -1
   capture_frame_rate: 60
   no_graphics: true
@@ -69,7 +69,7 @@ checkpoint_settings:
   run_id: Huggy2
   initialize_from: null
   load_model: false
-  resume: false
+  resume: true
   force: false
   train_model: false
   inference: false

run_logs/Player-0.log

@@ -2,9 +2,6 @@ Mono path[0] = '/content/ml-agents/trained-envs-executables/linux/Huggy/Huggy_Da
 Mono config path = '/content/ml-agents/trained-envs-executables/linux/Huggy/Huggy_Data/MonoBleedingEdge/etc'
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
-PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face
-PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face/Huggy
-Unable to load player prefs
 Initialize engine version: 2021.3.14f1 (eee1884e7226)
 [Subsystems] Discovering subsystems at path /content/ml-agents/trained-envs-executables/linux/Huggy/Huggy_Data/UnitySubsystems
 Forcing GfxDevice: Null
@@ -34,7 +31,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.091 seconds
+- Completed reload, in  0.088 seconds
 ERROR: Shader Hidden/Universal Render Pipeline/Blit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Hidden/Universal Render Pipeline/CopyDepth shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Hidden/Universal Render Pipeline/ScreenSpaceShadows shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -78,14 +75,14 @@ ERROR: Shader Universal Render Pipeline/Lit shader is not supported on this GPU
 WARNING: Shader Unsupported: 'Universal Render Pipeline/Lit' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 0.771649 ms
+UnloadTime: 0.802651 ms
 requesting resize 84 x 84
 Setting up 1 worker threads for Enlighten.
 Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [4.0 KB-8.0 KB]: 26749 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [4.0 KB-8.0 KB]: 13405 frames, [2.0 MB-4.0 MB]: 1 frames
       Initial Block Size 4.0 MB
       Current Block Size 4.0 MB
       Peak Allocated Bytes 3.6 MB
@@ -93,7 +90,7 @@ Memory Statistics:
     [ALLOC_TEMP_Loading.AsyncRead]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
-      Peak Allocated Bytes 184 B
+      Peak Allocated Bytes 128 B
       Overflow Count 0
     [ALLOC_TEMP_Loading.PreloadManager]
       Initial Block Size 256.0 KB
@@ -201,22 +198,22 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 250
+  Peak main deferred allocation count 326
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 1.4 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 26750 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 13406 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 23.6 MB
+      Peak Allocated memory 23.5 MB
       Peak Large allocation bytes 16.0 MB
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [2.0 MB-4.0 MB]: 26750 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 13405 frames, [2.0 MB-4.0 MB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 2.6 MB
+      Peak Allocated memory 2.3 MB
       Peak Large allocation bytes 0 B
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -245,13 +242,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.4 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 26749 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 13405 frames, [64.0 KB-128.0 KB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 65.6 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [64.0 KB-128.0 KB]: 26750 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 13406 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 81.8 KB
@@ -263,13 +260,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.4 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [1.0 MB-2.0 MB]: 26749 frames, [16.0 MB-32.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 13405 frames, [16.0 MB-32.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
       Peak Allocated memory 30.6 MB
       Peak Large allocation bytes 24.9 MB
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 26749 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 13405 frames, [2.0 MB-4.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 2.6 MB
@@ -281,13 +278,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.4 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 26750 frames
+      Peak usage frame count: [0-1.0 KB]: 13406 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]: 26750 frames
+      Peak usage frame count: [4.0 KB-8.0 KB]: 13406 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 7.3 KB

run_logs/timers.json

@@ -2,213 +2,213 @@
     "name": "root",
     "gauges": {
         "Huggy.Policy.Entropy.mean": {
-            "value": 1.4055715799331665,
-            "min": 1.4055715799331665,
-            "max": 1.4297057390213013,
-            "count": 40
+            "value": 1.401002287864685,
+            "min": 1.401002287864685,
+            "max": 1.405309796333313,
+            "count": 20
         },
         "Huggy.Policy.Entropy.sum": {
-            "value": 69703.703125,
-            "min": 67397.5078125,
-            "max": 78767.1171875,
-            "count": 40
+            "value": 71074.25,
+            "min": 68209.1328125,
+            "max": 72693.265625,
+            "count": 20
         },
         "Huggy.Environment.EpisodeLength.mean": {
-            "value": 95.37890625,
-            "min": 90.22080291970804,
-            "max": 387.4418604651163,
-            "count": 40
+            "value": 83.54300168634065,
+            "min": 70.81635581061693,
+            "max": 91.0939226519337,
+            "count": 20
         },
         "Huggy.Environment.EpisodeLength.sum": {
-            "value": 48834.0,
-            "min": 48834.0,
-            "max": 50114.0,
-            "count": 40
+            "value": 49541.0,
+            "min": 48868.0,
+            "max": 49747.0,
+            "count": 20
         },
         "Huggy.Step.mean": {
-            "value": 1999282.0,
-            "min": 49712.0,
-            "max": 1999282.0,
-            "count": 40
+            "value": 2999431.0,
+            "min": 2049990.0,
+            "max": 2999431.0,
+            "count": 20
         },
         "Huggy.Step.sum": {
-            "value": 1999282.0,
-            "min": 49712.0,
-            "max": 1999282.0,
-            "count": 40
+            "value": 2999431.0,
+            "min": 2049990.0,
+            "max": 2999431.0,
+            "count": 20
         },
         "Huggy.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 2.3709049224853516,
-            "min": 0.13117161393165588,
-            "max": 2.423060655593872,
-            "count": 40
+            "value": 2.3975017070770264,
+            "min": 2.3975017070770264,
+            "max": 2.4892852306365967,
+            "count": 20
         },
         "Huggy.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 1213.9033203125,
-            "min": 16.789966583251953,
-            "max": 1294.873291015625,
-            "count": 40
+            "value": 1421.718505859375,
+            "min": 1313.0732421875,
+            "max": 1724.28125,
+            "count": 20
         },
         "Huggy.Environment.CumulativeReward.mean": {
-            "value": 3.7015058310935274,
-            "min": 1.885482969461009,
-            "max": 3.8801699185886647,
-            "count": 40
+            "value": 3.7457232952721,
+            "min": 3.7457232952721,
+            "max": 4.004129383521966,
+            "count": 20
         },
         "Huggy.Environment.CumulativeReward.sum": {
-            "value": 1895.170985519886,
-            "min": 241.34182009100914,
-            "max": 2088.111712574959,
-            "count": 40
+            "value": 2221.2139140963554,
+            "min": 2086.2555326223373,
+            "max": 2749.6239017248154,
+            "count": 20
         },
         "Huggy.Policy.ExtrinsicReward.mean": {
-            "value": 3.7015058310935274,
-            "min": 1.885482969461009,
-            "max": 3.8801699185886647,
-            "count": 40
+            "value": 3.7457232952721,
+            "min": 3.7457232952721,
+            "max": 4.004129383521966,
+            "count": 20
         },
         "Huggy.Policy.ExtrinsicReward.sum": {
-            "value": 1895.170985519886,
-            "min": 241.34182009100914,
-            "max": 2088.111712574959,
-            "count": 40
+            "value": 2221.2139140963554,
+            "min": 2086.2555326223373,
+            "max": 2749.6239017248154,
+            "count": 20
         },
         "Huggy.Losses.PolicyLoss.mean": {
-            "value": 0.017886117663389694,
-            "min": 0.014386471756248891,
-            "max": 0.020187868552360065,
-            "count": 40
+            "value": 0.015297950653378696,
+            "min": 0.014414844310279779,
+            "max": 0.01974766966110716,
+            "count": 20
         },
         "Huggy.Losses.PolicyLoss.sum": {
-            "value": 0.05365835299016908,
-            "min": 0.028772943512497783,
-            "max": 0.05933741452051133,
-            "count": 40
+            "value": 0.030595901306757392,
+            "min": 0.030595901306757392,
+            "max": 0.05354553505652196,
+            "count": 20
         },
         "Huggy.Losses.ValueLoss.mean": {
-            "value": 0.05057917713291116,
-            "min": 0.02314409806082646,
-            "max": 0.0540810481334726,
-            "count": 40
+            "value": 0.05586734482397636,
+            "min": 0.046268613636493684,
+            "max": 0.07523782992114623,
+            "count": 20
         },
         "Huggy.Losses.ValueLoss.sum": {
-            "value": 0.15173753139873347,
-            "min": 0.04628819612165292,
-            "max": 0.1619937828431527,
-            "count": 40
+            "value": 0.11173468964795272,
+            "min": 0.09253722727298737,
+            "max": 0.19532502045234046,
+            "count": 20
         },
         "Huggy.Policy.LearningRate.mean": {
-            "value": 3.3051988983000044e-06,
-            "min": 3.3051988983000044e-06,
-            "max": 0.0002953815015395,
-            "count": 40
+            "value": 2.217899260733331e-06,
+            "min": 2.217899260733331e-06,
+            "max": 9.691806769399999e-05,
+            "count": 20
         },
         "Huggy.Policy.LearningRate.sum": {
-            "value": 9.915596694900014e-06,
-            "min": 9.915596694900014e-06,
-            "max": 0.0008442624185792,
-            "count": 40
+            "value": 4.435798521466662e-06,
+            "min": 4.435798521466662e-06,
+            "max": 0.00026307251230923333,
+            "count": 20
         },
         "Huggy.Policy.Epsilon.mean": {
-            "value": 0.10110170000000002,
-            "min": 0.10110170000000002,
-            "max": 0.19846049999999998,
-            "count": 40
+            "value": 0.10073926666666666,
+            "min": 0.10073926666666666,
+            "max": 0.13230600000000003,
+            "count": 20
         },
         "Huggy.Policy.Epsilon.sum": {
-            "value": 0.30330510000000005,
-            "min": 0.20734580000000002,
-            "max": 0.5814208000000001,
-            "count": 40
+            "value": 0.20147853333333332,
+            "min": 0.20147853333333332,
+            "max": 0.3876907666666666,
+            "count": 20
         },
         "Huggy.Policy.Beta.mean": {
-            "value": 6.497483000000012e-05,
-            "min": 6.497483000000012e-05,
-            "max": 0.004923178949999999,
-            "count": 40
+            "value": 4.688940666666663e-05,
+            "min": 4.688940666666663e-05,
+            "max": 0.0016220694,
+            "count": 20
         },
         "Huggy.Policy.Beta.sum": {
-            "value": 0.00019492449000000034,
-            "min": 0.00019492449000000034,
-            "max": 0.01407289792,
-            "count": 40
+            "value": 9.377881333333325e-05,
+            "min": 9.377881333333325e-05,
+            "max": 0.004405769256666668,
+            "count": 20
         },
         "Huggy.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 40
+            "count": 20
         },
         "Huggy.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 40
+            "count": 20
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1709904169",
+        "start_time_seconds": "1709907871",
         "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/results/Huggy2/configuration.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics --resume",
         "mlagents_version": "1.1.0.dev0",
         "mlagents_envs_version": "1.1.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.2.1+cu121",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1709906489"
+        "end_time_seconds": "1709909115"
     },
-    "total": 2319.279273016,
+    "total": 1244.4501427220002,
     "count": 1,
-    "self": 0.44063287300014053,
+    "self": 0.4772971899992626,
     "children": {
         "run_training.setup": {
-            "total": 0.05338222999989739,
+            "total": 0.052141256000140856,
             "count": 1,
-            "self": 0.05338222999989739
+            "self": 0.052141256000140856
         },
         "TrainerController.start_learning": {
-            "total": 2318.785257913,
+            "total": 1243.9207042760008,
             "count": 1,
-            "self": 4.0336805339766215,
+            "self": 2.390526035728726,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 3.0950796560000526,
+                    "total": 2.1087124650002806,
                     "count": 1,
-                    "self": 3.0950796560000526
+                    "self": 2.1087124650002806
                 },
                 "TrainerController.advance": {
-                    "total": 2311.525542377023,
-                    "count": 231749,
-                    "self": 4.856409743111726,
+                    "total": 1239.3015913702711,
+                    "count": 117628,
+                    "self": 2.4878327934065965,
                     "children": {
                         "env_step": {
-                            "total": 1842.0626052759483,
-                            "count": 231749,
-                            "self": 1525.1558318310535,
+                            "total": 993.2267258938964,
+                            "count": 117628,
+                            "self": 823.9015365810892,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 314.27313197299986,
-                                    "count": 231749,
-                                    "self": 16.86885113398489,
+                                    "total": 167.81543739681183,
+                                    "count": 117628,
+                                    "self": 8.58352780974019,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 297.404280839015,
-                                            "count": 222914,
-                                            "self": 297.404280839015
+                                            "total": 159.23190958707164,
+                                            "count": 111710,
+                                            "self": 159.23190958707164
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 2.6336414718948618,
-                                    "count": 231749,
+                                    "total": 1.5097519159953663,
+                                    "count": 117628,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2312.0813975229726,
-                                            "count": 231749,
+                                            "total": 1240.0859183018856,
+                                            "count": 117628,
                                             "is_parallel": true,
-                                            "self": 1076.7531728090628,
+                                            "self": 572.93838735798,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -217,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0010314520000065386,
+                                                            "total": 0.0008681829995111912,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.00027144200021211873,
+                                                            "self": 0.00022270299996307585,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0007600099997944199,
+                                                                    "total": 0.0006454799995481153,
                                                                     "count": 2,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0007600099997944199
+                                                                    "self": 0.0006454799995481153
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.04907260699997096,
+                                                            "total": 0.03423497999938263,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0004002509999736503,
+                                                            "self": 0.00043053099943790585,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00019848199985972315,
+                                                                    "total": 0.0002341859999432927,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00019848199985972315
+                                                                    "self": 0.0002341859999432927
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.047570167000003494,
+                                                                    "total": 0.03271803299958265,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.047570167000003494
+                                                                    "self": 0.03271803299958265
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0009037070001340908,
+                                                                    "total": 0.0008522300004187855,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00027604799993241613,
+                                                                    "self": 0.00022006300150678726,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0006276590002016746,
+                                                                            "total": 0.0006321669989119982,
                                                                             "count": 2,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0006276590002016746
+                                                                            "self": 0.0006321669989119982
                                                                         }
                                                                     }
                                                                 }
@@ -267,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1235.3282247139098,
-                                                    "count": 231748,
+                                                    "total": 667.1475309439056,
+                                                    "count": 117627,
                                                     "is_parallel": true,
-                                                    "self": 38.62769267598969,
+                                                    "self": 20.40213940490412,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 79.81701341398616,
-                                                            "count": 231748,
+                                                            "total": 41.095434747968284,
+                                                            "count": 117627,
                                                             "is_parallel": true,
-                                                            "self": 79.81701341398616
+                                                            "self": 41.095434747968284
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1027.2230736529193,
-                                                            "count": 231748,
+                                                            "total": 558.1726376191491,
+                                                            "count": 117627,
                                                             "is_parallel": true,
-                                                            "self": 1027.2230736529193
+                                                            "self": 558.1726376191491
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 89.66044497101461,
-                                                            "count": 231748,
+                                                            "total": 47.47731917188412,
+                                                            "count": 117627,
                                                             "is_parallel": true,
-                                                            "self": 32.11277854304103,
+                                                            "self": 16.807764421974753,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 57.54766642797358,
-                                                                    "count": 463496,
+                                                                    "total": 30.669554749909366,
+                                                                    "count": 235254,
                                                                     "is_parallel": true,
-                                                                    "self": 57.54766642797358
+                                                                    "self": 30.669554749909366
                                                                 }
                                                             }
                                                         }
@@ -307,31 +307,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 464.6065273579634,
-                            "count": 231749,
-                            "self": 6.509828326086108,
+                            "total": 243.58703268296813,
+                            "count": 117628,
+                            "self": 3.7162205750273642,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 143.74814723187615,
-                                    "count": 231749,
-                                    "self": 142.569959859876,
+                                    "total": 83.8833658679414,
+                                    "count": 117628,
+                                    "self": 83.27058646594105,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 1.1781873720001386,
-                                            "count": 10,
-                                            "self": 1.1781873720001386
+                                            "total": 0.6127794020003421,
+                                            "count": 5,
+                                            "self": 0.6127794020003421
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 314.34855180000113,
-                                    "count": 97,
-                                    "self": 251.86083192599017,
+                                    "total": 155.98744623999937,
+                                    "count": 48,
+                                    "self": 124.32123011800832,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 62.48771987401096,
-                                            "count": 2910,
-                                            "self": 62.48771987401096
+                                            "total": 31.666216121991056,
+                                            "count": 1440,
+                                            "self": 31.666216121991056
                                         }
                                     }
                                 }
@@ -340,19 +340,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 8.749998414714355e-07,
+                    "total": 9.840005077421665e-07,
                     "count": 1,
-                    "self": 8.749998414714355e-07
+                    "self": 9.840005077421665e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.13095447100022284,
+                    "total": 0.11987342100019305,
                     "count": 1,
-                    "self": 0.002151288000277418,
+                    "self": 0.0027031320005335147,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.12880318299994542,
+                            "total": 0.11717028899965953,
                             "count": 1,
-                            "self": 0.12880318299994542
+                            "self": 0.11717028899965953
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,33 +1,6 @@
 {
     "Huggy": {
         "checkpoints": [
-            {
-                "steps": 199868,
-                "file_path": "results/Huggy2/Huggy/Huggy-199868.onnx",
-                "reward": 3.375885134851429,
-                "creation_time": 1709904396.6510506,
-                "auxillary_file_paths": [
-                    "results/Huggy2/Huggy/Huggy-199868.pt"
-                ]
-            },
-            {
-                "steps": 399908,
-                "file_path": "results/Huggy2/Huggy/Huggy-399908.onnx",
-                "reward": 4.034134862914918,
-                "creation_time": 1709904625.2356014,
-                "auxillary_file_paths": [
-                    "results/Huggy2/Huggy/Huggy-399908.pt"
-                ]
-            },
-            {
-                "steps": 599631,
-                "file_path": "results/Huggy2/Huggy/Huggy-599631.onnx",
-                "reward": 3.82219614037152,
-                "creation_time": 1709904859.7716813,
-                "auxillary_file_paths": [
-                    "results/Huggy2/Huggy/Huggy-599631.pt"
-                ]
-            },
             {
                 "steps": 799972,
                 "file_path": "results/Huggy2/Huggy/Huggy-799972.onnx",
@@ -99,15 +72,78 @@
                 "auxillary_file_paths": [
                     "results/Huggy2/Huggy/Huggy-2000032.pt"
                 ]
+            },
+            {
+                "steps": 2000032,
+                "file_path": "results/Huggy2/Huggy/Huggy-2000032.onnx",
+                "reward": null,
+                "creation_time": 1709907821.7469618,
+                "auxillary_file_paths": [
+                    "results/Huggy2/Huggy/Huggy-2000032.pt"
+                ]
+            },
+            {
+                "steps": 2199988,
+                "file_path": "results/Huggy2/Huggy/Huggy-2199988.onnx",
+                "reward": 3.755343417326609,
+                "creation_time": 1709908123.692099,
+                "auxillary_file_paths": [
+                    "results/Huggy2/Huggy/Huggy-2199988.pt"
+                ]
+            },
+            {
+                "steps": 2399969,
+                "file_path": "results/Huggy2/Huggy/Huggy-2399969.onnx",
+                "reward": 3.8597737611868443,
+                "creation_time": 1709908371.6613626,
+                "auxillary_file_paths": [
+                    "results/Huggy2/Huggy/Huggy-2399969.pt"
+                ]
+            },
+            {
+                "steps": 2599926,
+                "file_path": "results/Huggy2/Huggy/Huggy-2599926.onnx",
+                "reward": 4.089539177142656,
+                "creation_time": 1709908623.1275425,
+                "auxillary_file_paths": [
+                    "results/Huggy2/Huggy/Huggy-2599926.pt"
+                ]
+            },
+            {
+                "steps": 2799973,
+                "file_path": "results/Huggy2/Huggy/Huggy-2799973.onnx",
+                "reward": 3.796483116124266,
+                "creation_time": 1709908867.0716107,
+                "auxillary_file_paths": [
+                    "results/Huggy2/Huggy/Huggy-2799973.pt"
+                ]
+            },
+            {
+                "steps": 2999431,
+                "file_path": "results/Huggy2/Huggy/Huggy-2999431.onnx",
+                "reward": 3.767220799181912,
+                "creation_time": 1709909115.1144571,
+                "auxillary_file_paths": [
+                    "results/Huggy2/Huggy/Huggy-2999431.pt"
+                ]
+            },
+            {
+                "steps": 3000181,
+                "file_path": "results/Huggy2/Huggy/Huggy-3000181.onnx",
+                "reward": 3.721913618529403,
+                "creation_time": 1709909115.260167,
+                "auxillary_file_paths": [
+                    "results/Huggy2/Huggy/Huggy-3000181.pt"
+                ]
             }
         ],
         "final_checkpoint": {
-            "steps": 2000032,
+            "steps": 3000181,
             "file_path": "results/Huggy2/Huggy.onnx",
-            "reward": 3.652572731177012,
-            "creation_time": 1709906488.7096393,
+            "reward": 3.721913618529403,
+            "creation_time": 1709909115.260167,
             "auxillary_file_paths": [
-                "results/Huggy2/Huggy/Huggy-2000032.pt"
+                "results/Huggy2/Huggy/Huggy-3000181.pt"
             ]
         }
     },