Huggy

Huggy.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04a534339158e401895601eb0a40da23c787cae727ae63c0b76496ee2eeb5d9b
+oid sha256:c2fc96150e2e9c24a8d876582fac6ee36186e410c6d4d05801e960cc0a7ead12
 size 2271327

Huggy/Huggy-1199956.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8de1768eed2d0b9e1b67f3a6e219ea91f31ed3e3aefde7aebe0e04d6aada840
+size 2271327

Huggy/Huggy-1199956.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60ca93031571321d5737d39441f7129c9d73e1ef12f3ff8c4d21dc9b0614e6ec
+size 13503717

Huggy/Huggy-1499982.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4bad02c95186741ba5d4fa116d784bc46a7afef6915986ecdbd0ecd92952c64
+size 2271327

Huggy/Huggy-1499982.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95d8d07ffab09a36737bf51194335c6c6c5e6f405e621964e9214e4a71a2c518
+size 13503717

Huggy/Huggy-1799979.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:136a7c3adb62f7f69c8a740004eebe72a6291959e27f83e08fd966da29bd3b5a
+size 2271327

Huggy/Huggy-1799979.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b9e52193a6ff5dc79efa161ff043976b782474e87769a3d494cc56ef5fe5e05
+size 13503717

Huggy/Huggy-2099972.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aaab095f378d3074df1679296556c46dfe1338a0cde5f63816210b80b22f21ab
+size 2271327

Huggy/Huggy-2099972.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c66b5cc7899fc7db8e9e961193a13dc6ed237bb538a3f1f82ffeed18930a3f8
+size 13503717

Huggy/Huggy-2399995.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38eab405f98471d0444f8b5841124aa2a9143a0308b61322c183a550c8bbb27b
+size 2271327

Huggy/Huggy-2399995.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df95078fe676d74213a31c658c8beae4107e302b0d3693e68c68c9e132c73aa1
+size 13503717

Huggy/Huggy-2699959.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:219d3da6eef492b61296dec02300982ef5ecb85dc31b41eec4dd728721504339
+size 2271327

Huggy/Huggy-2699959.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9171873bc1bdf45035b87392e8291d92bf6c1e5e553844c073a946e9c2e267af
+size 13503717

Huggy/Huggy-299880.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbd764067a2d038838542d23e99adb3f968cb04c96e97efc454e9e80b1056004
+size 2271327

Huggy/Huggy-299880.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:802dc971de121af1e85d6ba48a5219c5b1381eab617765d1a5a4cfdc9b609c81
+size 13503717

Huggy/Huggy-2999822.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae7c368360f7d4486b90d99fab7b38546ce9c2c8cd23f9beaf0dcb3e84a3caef
+size 2271327

Huggy/Huggy-2999822.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f77c4e8cc088b41bc7cd27f30d4de439f3413cfa36fcfe180f6626afd87bc2f
+size 13503717

Huggy/Huggy-3000572.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2fc96150e2e9c24a8d876582fac6ee36186e410c6d4d05801e960cc0a7ead12
+size 2271327

Huggy/Huggy-3000572.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:940d785b7c5d706730e974362c5bb4c01446add02b08f3da3cb0bfdb9bcb4fa1
+size 13503717

Huggy/Huggy-599415.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:340a9cd1a5ac23856d0c0ee7f8f99bff3d519cf7cd6b3ec5097e21e20d9d110b
+size 2271327

Huggy/Huggy-599415.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa0111afc1b3c7d6da6ee076d5db17706484de86dc96ec0dbc7d0ec19ce8100a
+size 13503717

Huggy/Huggy-899965.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a819e4d224ce39578de5f35f1fe70508c399c32fdd7b112316a8f703337515dd
+size 2271327

Huggy/Huggy-899965.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88fe7bf53e5527daed7dad0e112b83c8ac4c6d357b7b00515e71a571dfef38ba
+size 13503717

Huggy/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19a0e32df80662e354ce8c0e378200fe37d4a53625c39c486c6f61226b6dd19c
-size 13502693
+oid sha256:940d785b7c5d706730e974362c5bb4c01446add02b08f3da3cb0bfdb9bcb4fa1
+size 13503717

Huggy/events.out.tfevents.1689060455.760359cde87d.1665.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9109c088a830279d3d3e066240d6697ade3aff29fa7338261234c13cf4a8d92e
+size 542994

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"Huggy": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0002, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 6, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": true, "hidden_units": 512, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.995, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 15, "even_checkpoints": false, "max_steps": 2000000, "time_horizon": 1000, "summary_freq": 100000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "/content/drive/MyDrive/RL_HuggingFace/Huggy_Stick/trained-envs-executables/linux/Huggy/Huggy", "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": "Huggy", "initialize_from": null, "load_model": false, "resume": false, "force": true, "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": 300000, "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": "/content/drive/MyDrive/RL_HuggingFace/Huggy_Stick/trained-envs-executables/linux/Huggy/Huggy", "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": "Huggy", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -5,16 +5,16 @@ behaviors:
     hyperparameters:
       batch_size: 2048
       buffer_size: 20480
-      learning_rate: 0.0002
+      learning_rate: 0.0003
       beta: 0.005
       epsilon: 0.2
       lambd: 0.95
-      num_epoch: 6
+      num_epoch: 3
       shared_critic: false
       learning_rate_schedule: linear
       beta_schedule: linear
       epsilon_schedule: linear
-    checkpoint_interval: 500000
+    checkpoint_interval: 300000
     network_settings:
       normalize: true
       hidden_units: 512
@@ -38,9 +38,9 @@ behaviors:
     init_path: null
     keep_checkpoints: 15
     even_checkpoints: false
-    max_steps: 2000000
+    max_steps: 3000000
     time_horizon: 1000
-    summary_freq: 100000
+    summary_freq: 50000
     threaded: false
     self_play: null
     behavioral_cloning: null

run_logs/Player-0.log

@@ -34,7 +34,7 @@ ALSA lib pcm.c:2642:(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  1.761 seconds
+- Completed reload, in  1.266 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 +78,14 @@ 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: 0.706560 ms
+UnloadTime: 0.969354 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]: 26759 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [4.0 KB-8.0 KB]: 40133 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 +93,7 @@ Memory Statistics:
     [ALLOC_TEMP_Loading.AsyncRead]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
-      Peak Allocated Bytes 248 B
+      Peak Allocated Bytes 129 B
       Overflow Count 0
     [ALLOC_TEMP_Loading.PreloadManager]
       Initial Block Size 256.0 KB
@@ -201,19 +201,19 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 174
+  Peak main deferred allocation count 210
     [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]: 26760 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 40134 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 23.4 MB
+      Peak Allocated memory 24.9 MB
       Peak Large allocation bytes 16.0 MB
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [2.0 MB-4.0 MB]: 26760 frames
+      Peak usage frame count: [2.0 MB-4.0 MB]: 40134 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 2.6 MB
@@ -245,13 +245,13 @@ 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]: 26759 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 40133 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]: 26760 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 40134 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 81.8 KB
@@ -263,13 +263,13 @@ 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]: 26759 frames, [16.0 MB-32.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 40133 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]: 26759 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 40133 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 +281,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.4 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 26760 frames
+      Peak usage frame count: [0-1.0 KB]: 40134 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]: 26760 frames
+      Peak usage frame count: [4.0 KB-8.0 KB]: 40134 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 7.3 KB

run_logs/timers.json

@@ -2,153 +2,153 @@
     "name": "root",
     "gauges": {
         "Huggy.Policy.Entropy.mean": {
-            "value": 1.3900960683822632,
-            "min": 1.3900960683822632,
-            "max": 1.4224711656570435,
-            "count": 20
+            "value": 1.3888742923736572,
+            "min": 1.3888742923736572,
+            "max": 1.426063895225525,
+            "count": 60
         },
         "Huggy.Policy.Entropy.sum": {
-            "value": 139341.84375,
-            "min": 138489.859375,
-            "max": 146852.40625,
-            "count": 20
+            "value": 70504.8125,
+            "min": 66749.9140625,
+            "max": 79825.453125,
+            "count": 60
         },
         "Huggy.Environment.EpisodeLength.mean": {
-            "value": 94.5915627996165,
-            "min": 80.20389926888708,
-            "max": 379.5361216730038,
-            "count": 20
+            "value": 104.8909853249476,
+            "min": 80.92950819672132,
+            "max": 381.3863636363636,
+            "count": 60
         },
         "Huggy.Environment.EpisodeLength.sum": {
-            "value": 98659.0,
-            "min": 98659.0,
-            "max": 99818.0,
-            "count": 20
+            "value": 50033.0,
+            "min": 48886.0,
+            "max": 50343.0,
+            "count": 60
         },
         "Huggy.Step.mean": {
-            "value": 1999387.0,
-            "min": 99876.0,
-            "max": 1999387.0,
-            "count": 20
+            "value": 2999822.0,
+            "min": 49754.0,
+            "max": 2999822.0,
+            "count": 60
         },
         "Huggy.Step.sum": {
-            "value": 1999387.0,
-            "min": 99876.0,
-            "max": 1999387.0,
-            "count": 20
+            "value": 2999822.0,
+            "min": 49754.0,
+            "max": 2999822.0,
+            "count": 60
         },
         "Huggy.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 2.408686637878418,
-            "min": 0.19250328838825226,
-            "max": 2.4421067237854004,
-            "count": 20
+            "value": 2.4710183143615723,
+            "min": 0.0629943460226059,
+            "max": 2.480475425720215,
+            "count": 60
         },
         "Huggy.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 2512.26025390625,
-            "min": 50.43585968017578,
-            "max": 2986.97412109375,
-            "count": 20
+            "value": 1178.67578125,
+            "min": 8.252259254455566,
+            "max": 1472.9415283203125,
+            "count": 60
         },
         "Huggy.Environment.CumulativeReward.mean": {
-            "value": 3.776210833258734,
-            "min": 2.1582188136477507,
-            "max": 3.9183933731888523,
-            "count": 20
+            "value": 3.816625628956209,
+            "min": 1.7483285571100147,
+            "max": 4.023540446259054,
+            "count": 60
         },
         "Huggy.Environment.CumulativeReward.sum": {
-            "value": 3938.5878990888596,
-            "min": 565.4533291757107,
-            "max": 4786.76173633337,
-            "count": 20
+            "value": 1820.5304250121117,
+            "min": 229.03104098141193,
+            "max": 2419.5150841474533,
+            "count": 60
         },
         "Huggy.Policy.ExtrinsicReward.mean": {
-            "value": 3.776210833258734,
-            "min": 2.1582188136477507,
-            "max": 3.9183933731888523,
-            "count": 20
+            "value": 3.816625628956209,
+            "min": 1.7483285571100147,
+            "max": 4.023540446259054,
+            "count": 60
         },
         "Huggy.Policy.ExtrinsicReward.sum": {
-            "value": 3938.5878990888596,
-            "min": 565.4533291757107,
-            "max": 4786.76173633337,
-            "count": 20
+            "value": 1820.5304250121117,
+            "min": 229.03104098141193,
+            "max": 2419.5150841474533,
+            "count": 60
         },
         "Huggy.Losses.PolicyLoss.mean": {
-            "value": 0.016202029427722663,
-            "min": 0.015938638651787185,
-            "max": 0.01806502788836951,
-            "count": 20
+            "value": 0.01812783560775036,
+            "min": 0.013020951706049444,
+            "max": 0.020749712573888243,
+            "count": 60
         },
         "Huggy.Losses.PolicyLoss.sum": {
-            "value": 0.06480811771089065,
-            "min": 0.06480811771089065,
-            "max": 0.09032513944184756,
-            "count": 20
+            "value": 0.03625567121550072,
+            "min": 0.029045066535278843,
+            "max": 0.06224913772166473,
+            "count": 60
         },
         "Huggy.Losses.ValueLoss.mean": {
-            "value": 0.04883075722803672,
-            "min": 0.021893177845825753,
-            "max": 0.05174445406844219,
-            "count": 20
+            "value": 0.04747502878308296,
+            "min": 0.021944243057320515,
+            "max": 0.05808159367491801,
+            "count": 60
         },
         "Huggy.Losses.ValueLoss.sum": {
-            "value": 0.19532302891214687,
-            "min": 0.09566779248416425,
-            "max": 0.25872227034221096,
-            "count": 20
+            "value": 0.09495005756616592,
+            "min": 0.04388848611464103,
+            "max": 0.1662211953351895,
+            "count": 60
         },
         "Huggy.Policy.LearningRate.mean": {
-            "value": 5.1318224341375035e-06,
-            "min": 5.1318224341375035e-06,
-            "max": 0.0001947953776023125,
-            "count": 20
+            "value": 2.282049239350004e-06,
+            "min": 2.282049239350004e-06,
+            "max": 0.0002968899510366833,
+            "count": 60
         },
         "Huggy.Policy.LearningRate.sum": {
-            "value": 2.0527289736550014e-05,
-            "min": 2.0527289736550014e-05,
-            "max": 0.0009271921364039502,
-            "count": 20
+            "value": 4.564098478700008e-06,
+            "min": 4.564098478700008e-06,
+            "max": 0.0008628153123949,
+            "count": 60
         },
         "Huggy.Policy.Epsilon.mean": {
-            "value": 0.1025658625,
-            "min": 0.1025658625,
-            "max": 0.1973976875,
-            "count": 20
+            "value": 0.10076065000000001,
+            "min": 0.10076065000000001,
+            "max": 0.19896331666666667,
+            "count": 60
         },
         "Huggy.Policy.Epsilon.sum": {
-            "value": 0.41026345,
-            "min": 0.41026345,
-            "max": 0.96359605,
-            "count": 20
+            "value": 0.20152130000000001,
+            "min": 0.20152130000000001,
+            "max": 0.5876051,
+            "count": 60
         },
         "Huggy.Policy.Beta.mean": {
-            "value": 0.00013803653875000012,
-            "min": 0.00013803653875000012,
-            "max": 0.004870144606250001,
-            "count": 20
+            "value": 4.795643500000008e-05,
+            "min": 4.795643500000008e-05,
+            "max": 0.004948269501666665,
+            "count": 60
         },
         "Huggy.Policy.Beta.sum": {
-            "value": 0.0005521461550000005,
-            "min": 0.0005521461550000005,
-            "max": 0.023183442895,
-            "count": 20
+            "value": 9.591287000000015e-05,
+            "min": 9.591287000000015e-05,
+            "max": 0.01438149449,
+            "count": 60
         },
         "Huggy.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 20
+            "count": 60
         },
         "Huggy.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 20
+            "count": 60
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1689043423",
+        "start_time_seconds": "1689060451",
         "python_version": "3.10.12 (main, Jun  7 2023, 12:45:35) [GCC 9.4.0]",
         "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/Huggy.yaml --env=/content/drive/MyDrive/RL_HuggingFace/Huggy_Stick/trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics --force",
         "mlagents_version": "0.31.0.dev0",
@@ -156,59 +156,59 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.11.0+cu102",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1689050483"
+        "end_time_seconds": "1689064119"
     },
-    "total": 7059.804142261,
+    "total": 3668.6535292910003,
     "count": 1,
-    "self": 0.8390949930007991,
+    "self": 1.3920536060004451,
     "children": {
         "run_training.setup": {
-            "total": 0.04582911900001818,
+            "total": 0.04153957800002672,
             "count": 1,
-            "self": 0.04582911900001818
+            "self": 0.04153957800002672
         },
         "TrainerController.start_learning": {
-            "total": 7058.919218149,
+            "total": 3667.2199361069997,
             "count": 1,
-            "self": 7.073509209982149,
+            "self": 6.3126323028936895,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 3.449003614999981,
+                    "total": 9.415993806000017,
                     "count": 1,
-                    "self": 3.449003614999981
+                    "self": 9.415993806000017
                 },
                 "TrainerController.advance": {
-                    "total": 7048.304288099017,
-                    "count": 232281,
-                    "self": 7.003648692098977,
+                    "total": 3651.305028483106,
+                    "count": 348721,
+                    "self": 6.760530343135997,
                     "children": {
                         "env_step": {
-                            "total": 2264.9355251590528,
-                            "count": 232281,
-                            "self": 1853.9446226727653,
+                            "total": 2822.069021078028,
+                            "count": 348721,
+                            "self": 2379.0849059781904,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 406.4296757631121,
-                                    "count": 232281,
-                                    "self": 20.214286799228773,
+                                    "total": 438.7020990219911,
+                                    "count": 348721,
+                                    "self": 25.38750974392235,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 386.2153889638833,
-                                            "count": 222998,
-                                            "self": 386.2153889638833
+                                            "total": 413.31458927806875,
+                                            "count": 334446,
+                                            "self": 413.31458927806875
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 4.56122672317548,
-                                    "count": 232281,
+                                    "total": 4.282016077846606,
+                                    "count": 348721,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 7047.824596302967,
-                                            "count": 232281,
+                                            "total": 3656.05097367094,
+                                            "count": 348721,
                                             "is_parallel": true,
-                                            "self": 5605.753828100915,
+                                            "self": 1721.1318872069874,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -217,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0006860299999971176,
+                                                            "total": 0.0010919549999925948,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.00014199999998254498,
+                                                            "self": 0.00027607699996679,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0005440300000145726,
+                                                                    "total": 0.0008158780000258048,
                                                                     "count": 2,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0005440300000145726
+                                                                    "self": 0.0008158780000258048
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.02786219000000756,
+                                                            "total": 0.029764903999989656,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0003215600000316954,
+                                                            "self": 0.0003203720000328758,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00020018999998683285,
+                                                                    "total": 0.0002171230000271862,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00020018999998683285
+                                                                    "self": 0.0002171230000271862
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.026715469999999186,
+                                                                    "total": 0.028449354999963816,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.026715469999999186
+                                                                    "self": 0.028449354999963816
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0006249699999898439,
+                                                                    "total": 0.0007780539999657776,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0001670099999842023,
+                                                                    "self": 0.00022241199997097283,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.00045796000000564163,
+                                                                            "total": 0.0005556419999948048,
                                                                             "count": 2,
                                                                             "is_parallel": true,
-                                                                            "self": 0.00045796000000564163
+                                                                            "self": 0.0005556419999948048
                                                                         }
                                                                     }
                                                                 }
@@ -267,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1442.0707682020522,
-                                                    "count": 232280,
+                                                    "total": 1934.9190864639527,
+                                                    "count": 348720,
                                                     "is_parallel": true,
-                                                    "self": 45.391544223155506,
+                                                    "self": 59.27825931375537,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 65.3275124480515,
-                                                            "count": 232280,
+                                                            "total": 120.18818974723229,
+                                                            "count": 348720,
                                                             "is_parallel": true,
-                                                            "self": 65.3275124480515
+                                                            "self": 120.18818974723229
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1221.9360586060059,
-                                                            "count": 232280,
+                                                            "total": 1610.8801602340134,
+                                                            "count": 348720,
                                                             "is_parallel": true,
-                                                            "self": 1221.9360586060059
+                                                            "self": 1610.8801602340134
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 109.41565292483932,
-                                                            "count": 232280,
+                                                            "total": 144.5724771689516,
+                                                            "count": 348720,
                                                             "is_parallel": true,
-                                                            "self": 34.298282821638054,
+                                                            "self": 50.72425635189188,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 75.11737010320127,
-                                                                    "count": 464560,
+                                                                    "total": 93.84822081705971,
+                                                                    "count": 697440,
                                                                     "is_parallel": true,
-                                                                    "self": 75.11737010320127
+                                                                    "self": 93.84822081705971
                                                                 }
                                                             }
                                                         }
@@ -307,31 +307,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 4776.365114247865,
-                            "count": 232281,
-                            "self": 10.868885661878267,
+                            "total": 822.475477061942,
+                            "count": 348721,
+                            "self": 9.575893661007399,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 245.6721494549878,
-                                    "count": 232281,
-                                    "self": 245.1592509469873,
+                                    "total": 209.32758550793199,
+                                    "count": 348721,
+                                    "self": 207.7472441129314,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.5128985080004895,
-                                            "count": 4,
-                                            "self": 0.5128985080004895
+                                            "total": 1.5803413950005734,
+                                            "count": 10,
+                                            "self": 1.5803413950005734
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 4519.824079130999,
-                                    "count": 96,
-                                    "self": 600.2832575970069,
+                                    "total": 603.5719978930026,
+                                    "count": 145,
+                                    "self": 513.0613833860061,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 3919.540821533992,
-                                            "count": 5760,
-                                            "self": 3919.540821533992
+                                            "total": 90.51061450699649,
+                                            "count": 4350,
+                                            "self": 90.51061450699649
                                         }
                                     }
                                 }
@@ -340,19 +340,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 7.900007403804921e-07,
+                    "total": 1.3119997674948536e-06,
                     "count": 1,
-                    "self": 7.900007403804921e-07
+                    "self": 1.3119997674948536e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.0924164349999046,
+                    "total": 0.1862802030000239,
                     "count": 1,
-                    "self": 0.0018749090004348545,
+                    "self": 0.002615233000142325,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.09054152599946974,
+                            "total": 0.18366496999988158,
                             "count": 1,
-                            "self": 0.09054152599946974
+                            "self": 0.18366496999988158
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,58 +2,112 @@
     "Huggy": {
         "checkpoints": [
             {
-                "steps": 499973,
-                "file_path": "results/Huggy/Huggy/Huggy-499973.onnx",
-                "reward": 3.6815677612058577,
-                "creation_time": 1689045181.9602325,
+                "steps": 299880,
+                "file_path": "results/Huggy/Huggy/Huggy-299880.onnx",
+                "reward": 3.58493920551105,
+                "creation_time": 1689060823.8227375,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-499973.pt"
+                    "results/Huggy/Huggy/Huggy-299880.pt"
                 ]
             },
             {
-                "steps": 999995,
-                "file_path": "results/Huggy/Huggy/Huggy-999995.onnx",
-                "reward": 3.7918808400028885,
-                "creation_time": 1689046945.3197372,
+                "steps": 599415,
+                "file_path": "results/Huggy/Huggy/Huggy-599415.onnx",
+                "reward": 4.118598353862763,
+                "creation_time": 1689061194.2573714,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-999995.pt"
+                    "results/Huggy/Huggy/Huggy-599415.pt"
                 ]
             },
             {
-                "steps": 1499956,
-                "file_path": "results/Huggy/Huggy/Huggy-1499956.onnx",
-                "reward": 4.105031424202025,
-                "creation_time": 1689048711.8133729,
+                "steps": 899965,
+                "file_path": "results/Huggy/Huggy/Huggy-899965.onnx",
+                "reward": 4.041936094917002,
+                "creation_time": 1689061558.9132643,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-1499956.pt"
+                    "results/Huggy/Huggy/Huggy-899965.pt"
                 ]
             },
             {
-                "steps": 1999387,
-                "file_path": "results/Huggy/Huggy/Huggy-1999387.onnx",
-                "reward": 3.907636265553052,
-                "creation_time": 1689050482.2719421,
+                "steps": 1199956,
+                "file_path": "results/Huggy/Huggy/Huggy-1199956.onnx",
+                "reward": 3.511973680721389,
+                "creation_time": 1689061927.0584104,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-1999387.pt"
+                    "results/Huggy/Huggy/Huggy-1199956.pt"
                 ]
             },
             {
-                "steps": 2000137,
-                "file_path": "results/Huggy/Huggy/Huggy-2000137.onnx",
-                "reward": 3.8728576677270454,
-                "creation_time": 1689050482.4196668,
+                "steps": 1499982,
+                "file_path": "results/Huggy/Huggy/Huggy-1499982.onnx",
+                "reward": 3.940342487970201,
+                "creation_time": 1689062291.3708022,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-2000137.pt"
+                    "results/Huggy/Huggy/Huggy-1499982.pt"
+                ]
+            },
+            {
+                "steps": 1799979,
+                "file_path": "results/Huggy/Huggy/Huggy-1799979.onnx",
+                "reward": 3.7988859377124093,
+                "creation_time": 1689062659.708961,
+                "auxillary_file_paths": [
+                    "results/Huggy/Huggy/Huggy-1799979.pt"
+                ]
+            },
+            {
+                "steps": 2099972,
+                "file_path": "results/Huggy/Huggy/Huggy-2099972.onnx",
+                "reward": 3.6797601605687187,
+                "creation_time": 1689063022.536307,
+                "auxillary_file_paths": [
+                    "results/Huggy/Huggy/Huggy-2099972.pt"
+                ]
+            },
+            {
+                "steps": 2399995,
+                "file_path": "results/Huggy/Huggy/Huggy-2399995.onnx",
+                "reward": 3.747740807674699,
+                "creation_time": 1689063388.2258859,
+                "auxillary_file_paths": [
+                    "results/Huggy/Huggy/Huggy-2399995.pt"
+                ]
+            },
+            {
+                "steps": 2699959,
+                "file_path": "results/Huggy/Huggy/Huggy-2699959.onnx",
+                "reward": 2.4891218185424804,
+                "creation_time": 1689063755.5943968,
+                "auxillary_file_paths": [
+                    "results/Huggy/Huggy/Huggy-2699959.pt"
+                ]
+            },
+            {
+                "steps": 2999822,
+                "file_path": "results/Huggy/Huggy/Huggy-2999822.onnx",
+                "reward": 4.0429560233806745,
+                "creation_time": 1689064118.342833,
+                "auxillary_file_paths": [
+                    "results/Huggy/Huggy/Huggy-2999822.pt"
+                ]
+            },
+            {
+                "steps": 3000572,
+                "file_path": "results/Huggy/Huggy/Huggy-3000572.onnx",
+                "reward": 3.990235247163691,
+                "creation_time": 1689064118.5685806,
+                "auxillary_file_paths": [
+                    "results/Huggy/Huggy/Huggy-3000572.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 2000137,
+            "steps": 3000572,
             "file_path": "results/Huggy/Huggy.onnx",
-            "reward": 3.8728576677270454,
-            "creation_time": 1689050482.4196668,
+            "reward": 3.990235247163691,
+            "creation_time": 1689064118.5685806,
             "auxillary_file_paths": [
-                "results/Huggy/Huggy/Huggy-2000137.pt"
+                "results/Huggy/Huggy/Huggy-3000572.pt"
             ]
         }
     },