Huggy

Huggy.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3171982d07bb7b80125dbcb94cb89d6825cb7fd5772dfdd681f5df5afbb84a4a
+oid sha256:3db8ff997373e64b0b68230aa4defe75f7d2ee2a37740cd63334a695f449f30c
 size 2271327

Huggy/{Huggy-199704.onnx → Huggy-1199995.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:703c2e25bee935b2cf13ca32a8362f516a7ca55102d7889b896dd74548e6b8e0
+oid sha256:3d0b6219479dc22ac3439e06d4163c3b04e7315c0d99c11192184f873cc42886
 size 2271327

Huggy/{Huggy-599365.pt → Huggy-1199995.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c42b09d35e8036b38478f10de73f59af054fdcf42250d2a0ae13cce8697f074b
+oid sha256:babb0e7f43f8affff498468d8bb94564c4a3aa4f6148f71faabbc5e594d6158b
 size 13503717

Huggy/{Huggy-599365.onnx → Huggy-1399977.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:181739a4d8bbf934e8bcf02a4565e4cefcff43c4e408b8ab0e91a9d2ec768c12
+oid sha256:d5c050379b7e024106aae7c82afc26d7d4d1713a66c53827b35ff5ed7074015a
 size 2271327

Huggy/{Huggy-199704.pt → Huggy-1399977.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ebc10cba6d866141252d5a3f2c57a169c279fdfe79da3874d103fa8bedfbd83
+oid sha256:8c5693e4fe6151a27ba2cec7eabf801b73510c4c699628ce1ab2cc86ff752fe9
 size 13503717

Huggy/{Huggy-399436.onnx → Huggy-1599951.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdb2bc3b86bdadcb1f65d7560dfe78384f281612452b98215d52737e6b76b717
+oid sha256:af825901abece22559c03da0fc1b33d446dea1699469dba9e95a900c24479a02
 size 2271327

Huggy/{Huggy-639115.pt → Huggy-1599951.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2dc37e274a584cf597aaa420338c8bca7e58f9fe31ff53d5a146ac7bac4feee
+oid sha256:6b047adf075158ae788a17f9834b04238eb68354a90666b33d8ad0e8183a6ce5
 size 13503717

Huggy/{Huggy-639115.onnx → Huggy-1799937.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3171982d07bb7b80125dbcb94cb89d6825cb7fd5772dfdd681f5df5afbb84a4a
+oid sha256:4b73e74d1ab906b83879265db3457b326de384410467cd6e5b881ddcf434407b
 size 2271327

Huggy/{Huggy-399436.pt → Huggy-1799937.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8af5a2a6b24607933c31a35a7cc50ed33d05afdfacf807293cc16ad782cada4c
+oid sha256:ef9212ae97c7eb46c47876103d1a93bf154e2f2585733eb8c8b818dbdf9062da
 size 13503717

Huggy/Huggy-199847.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8400c918b4cb37e0357fa1c3941f715549755498c0d8df8dd27c5f128efb1d98
+size 2271327

Huggy/Huggy-199847.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:774e38b86dbb5f8d25bac214f01099cdb4f984fc0e32dba5383a8030572283e8
+size 13503717

Huggy/Huggy-1999960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:553d9c95d4afe3161e2c5aa04c584e9fbaf74d56e04b4151e3c1a7d3f0539a58
+size 2271327

Huggy/Huggy-1999960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:353d6a7b2c07cabf18ec165dc0eeb1cc38c9b09de42801c33576b2bbce42bda8
+size 13503717

Huggy/Huggy-2000062.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3db8ff997373e64b0b68230aa4defe75f7d2ee2a37740cd63334a695f449f30c
+size 2271327

Huggy/Huggy-2000062.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0abddf35261e1f2f240046fbeaf0ca967e1cf5bdf38f8180849d3800621b54a
+size 13503717

Huggy/Huggy-399908.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:213e2325055224ddf1c489d9a8dc761752bac423ee988d518955e701113f0f98
+size 2271327

Huggy/Huggy-399908.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:911f874bbc5790af832df61f6fa12a752e3a2f3f9aeb1108715ea23146e862ac
+size 13503717

Huggy/Huggy-599992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:620047303f3b2de4cf1c02f7aa4a0870d02c67f165a877ed6287d4f09c1792ab
+size 2271327

Huggy/Huggy-599992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f7fedf38be1f77a77430d796a51746751f7eabd4a6eb1b658a2bd6383b27ea4
+size 13503717

Huggy/Huggy-799931.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec9c188a112c77e0b94534ba821913ee122420654c01c04c63b8425d59ed9a81
+size 2271327

Huggy/Huggy-799931.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e3a94eda62fdea3c82ca4b797afb87e1eec60ffb6350242ae6d44f3f3e3b3b1
+size 13503717

Huggy/Huggy-999768.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56710b69cd2a726f1ba7312294a149b988338b4ea72ada12f5ad4c0b00d0a385
+size 2271327

Huggy/Huggy-999768.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df270b82572d716ee14d80d4d95f978f4e8a9714f5542e42fc333f9682c1b03d
+size 13503717

Huggy/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2dc37e274a584cf597aaa420338c8bca7e58f9fe31ff53d5a146ac7bac4feee
+oid sha256:e0abddf35261e1f2f240046fbeaf0ca967e1cf5bdf38f8180849d3800621b54a
 size 13503717

Huggy/{events.out.tfevents.1679469957.deb6adb046ef.3186.0 → events.out.tfevents.1679474258.ccf4fe07fb45.1174.0}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:607f70c979545477416e7f3e9b77702f71aa66740e1a31c9c6167c274b3739ec
-size 98194
+oid sha256:1836456c9aa510872c7080370cf58f0f16b60da26e179daf56afcfe78fe44481
+size 265874

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"Huggy": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 1024, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 80, "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, "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": 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": 20, "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, "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": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -3,13 +3,13 @@ behaviors:
   Huggy:
     trainer_type: ppo
     hyperparameters:
-      batch_size: 1024
+      batch_size: 2048
       buffer_size: 20480
       learning_rate: 0.0003
       beta: 0.005
       epsilon: 0.2
       lambd: 0.95
-      num_epoch: 80
+      num_epoch: 20
       shared_critic: false
       learning_rate_schedule: linear
       beta_schedule: linear

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  0.082 seconds
+- Completed reload, in  0.081 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: 0.762781 ms
+UnloadTime: 0.876459 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]: 8624 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [4.0 KB-8.0 KB]: 26759 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 184 B
+      Peak Allocated Bytes 144 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 251
+  Peak main deferred allocation count 306
     [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]: 8625 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 26760 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 22.1 MB
+      Peak Allocated memory 23.3 MB
       Peak Large allocation bytes 16.0 MB
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [2.0 MB-4.0 MB]: 8625 frames
+      Peak usage frame count: [2.0 MB-4.0 MB]: 26760 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 2.5 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]: 8624 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 26759 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]: 8625 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 26760 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]: 8624 frames, [16.0 MB-32.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 26759 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]: 8624 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 26759 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]: 8625 frames
+      Peak usage frame count: [0-1.0 KB]: 26760 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]: 8625 frames
+      Peak usage frame count: [4.0 KB-8.0 KB]: 26760 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": -0.9997519254684448,
-            "min": -0.9997519254684448,
-            "max": 1.3444199562072754,
-            "count": 12
+            "value": 0.0024282624945044518,
+            "min": 0.0024282624945044518,
+            "max": 1.4094988107681274,
+            "count": 40
         },
         "Huggy.Policy.Entropy.sum": {
-            "value": -51449.234375,
-            "min": -51449.234375,
-            "max": 74374.65625,
-            "count": 12
+            "value": 121.88177490234375,
+            "min": 121.88177490234375,
+            "max": 76792.3125,
+            "count": 40
         },
         "Huggy.Environment.EpisodeLength.mean": {
-            "value": 736.4776119402985,
-            "min": 291.5813953488372,
-            "max": 749.0,
-            "count": 12
+            "value": 101.32719836400818,
+            "min": 77.36106750392464,
+            "max": 387.0769230769231,
+            "count": 40
         },
         "Huggy.Environment.EpisodeLength.sum": {
-            "value": 49344.0,
-            "min": 49344.0,
-            "max": 50434.0,
-            "count": 12
+            "value": 49549.0,
+            "min": 48883.0,
+            "max": 50320.0,
+            "count": 40
         },
         "Huggy.Step.mean": {
-            "value": 599365.0,
-            "min": 49816.0,
-            "max": 599365.0,
-            "count": 12
+            "value": 1999960.0,
+            "min": 49727.0,
+            "max": 1999960.0,
+            "count": 40
         },
         "Huggy.Step.sum": {
-            "value": 599365.0,
-            "min": 49816.0,
-            "max": 599365.0,
-            "count": 12
+            "value": 1999960.0,
+            "min": 49727.0,
+            "max": 1999960.0,
+            "count": 40
         },
         "Huggy.Policy.ExtrinsicValueEstimate.mean": {
-            "value": -0.03113461285829544,
-            "min": -0.03113461285829544,
-            "max": 0.9373863935470581,
-            "count": 12
+            "value": 2.3968558311462402,
+            "min": 0.07871465384960175,
+            "max": 2.4361143112182617,
+            "count": 40
         },
         "Huggy.Policy.ExtrinsicValueEstimate.sum": {
-            "value": -2.0860190391540527,
-            "min": -2.0860190391540527,
-            "max": 142.94837951660156,
-            "count": 12
+            "value": 1172.0625,
+            "min": 10.154190063476562,
+            "max": 1469.4005126953125,
+            "count": 40
         },
         "Huggy.Environment.CumulativeReward.mean": {
-            "value": -1.8258129038583877,
-            "min": -2.280529317446053,
-            "max": 2.8464112139718476,
-            "count": 12
+            "value": 3.719413958200404,
+            "min": 1.7469386622425198,
+            "max": 4.042474850438149,
+            "count": 40
         },
         "Huggy.Environment.CumulativeReward.sum": {
-            "value": -122.32946455851197,
-            "min": -155.0759935863316,
-            "max": 489.5827288031578,
-            "count": 12
+            "value": 1818.7934255599976,
+            "min": 225.35508742928505,
+            "max": 2435.1847646832466,
+            "count": 40
         },
         "Huggy.Policy.ExtrinsicReward.mean": {
-            "value": -1.8258129038583877,
-            "min": -2.280529317446053,
-            "max": 2.8464112139718476,
-            "count": 12
+            "value": 3.719413958200404,
+            "min": 1.7469386622425198,
+            "max": 4.042474850438149,
+            "count": 40
         },
         "Huggy.Policy.ExtrinsicReward.sum": {
-            "value": -122.32946455851197,
-            "min": -155.0759935863316,
-            "max": 489.5827288031578,
-            "count": 12
+            "value": 1818.7934255599976,
+            "min": 225.35508742928505,
+            "max": 2435.1847646832466,
+            "count": 40
         },
         "Huggy.Losses.PolicyLoss.mean": {
-            "value": 0.024143845412327777,
-            "min": 0.024143845412327777,
-            "max": 0.22492867085151375,
-            "count": 12
+            "value": 0.017866179117690992,
+            "min": 0.017866179117690992,
+            "max": 0.03031593307166986,
+            "count": 40
         },
         "Huggy.Losses.PolicyLoss.sum": {
-            "value": 0.04828769082465555,
-            "min": 0.04828769082465555,
-            "max": 0.4871628791210242,
-            "count": 12
+            "value": 0.053598537353072975,
+            "min": 0.03752353361767746,
+            "max": 0.09006754113579518,
+            "count": 40
         },
         "Huggy.Losses.ValueLoss.mean": {
-            "value": 0.00010986422367011528,
-            "min": 0.00010299552992506733,
-            "max": 0.010556814962110365,
-            "count": 12
+            "value": 0.03433602244903644,
+            "min": 0.012876519530545921,
+            "max": 0.03433602244903644,
+            "count": 40
         },
         "Huggy.Losses.ValueLoss.sum": {
-            "value": 0.00021972844734023057,
-            "min": 0.00020599105985013465,
-            "max": 0.02111362992422073,
-            "count": 12
+            "value": 0.10300806734710932,
+            "min": 0.025753039061091842,
+            "max": 0.10300806734710932,
+            "count": 40
         },
         "Huggy.Policy.LearningRate.mean": {
-            "value": 0.00021428867857044994,
-            "min": 0.00021428867857044994,
-            "max": 0.000295372576542475,
-            "count": 12
+            "value": 3.287398904233337e-06,
+            "min": 3.287398904233337e-06,
+            "max": 0.000295331926556025,
+            "count": 40
         },
         "Huggy.Policy.LearningRate.sum": {
-            "value": 0.0004285773571408999,
-            "min": 0.0004285773571408999,
-            "max": 0.0008440629186457,
-            "count": 12
+            "value": 9.862196712700011e-06,
+            "min": 9.862196712700011e-06,
+            "max": 0.0008442852185716002,
+            "count": 40
         },
         "Huggy.Policy.Epsilon.mean": {
-            "value": 0.17142954999999999,
-            "min": 0.17142954999999999,
-            "max": 0.198457525,
-            "count": 12
+            "value": 0.10109576666666668,
+            "min": 0.10109576666666668,
+            "max": 0.19844397500000005,
+            "count": 40
         },
         "Huggy.Policy.Epsilon.sum": {
-            "value": 0.34285909999999997,
-            "min": 0.34285909999999997,
-            "max": 0.5813543000000001,
-            "count": 12
+            "value": 0.30328730000000004,
+            "min": 0.20737310000000006,
+            "max": 0.5814284,
+            "count": 40
         },
         "Huggy.Policy.Beta.mean": {
-            "value": 0.003574334545000001,
-            "min": 0.003574334545000001,
-            "max": 0.0049230304975,
-            "count": 12
+            "value": 6.467875666666675e-05,
+            "min": 6.467875666666675e-05,
+            "max": 0.004922354352500001,
+            "count": 40
         },
         "Huggy.Policy.Beta.sum": {
-            "value": 0.007148669090000002,
-            "min": 0.007148669090000002,
-            "max": 0.01406957957,
-            "count": 12
+            "value": 0.00019403627000000025,
+            "min": 0.00019403627000000025,
+            "max": 0.014073277160000001,
+            "count": 40
         },
         "Huggy.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 12
+            "count": 40
         },
         "Huggy.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 12
+            "count": 40
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1679469951",
+        "start_time_seconds": "1679474252",
         "python_version": "3.9.16 (main, Dec  7 2022, 01:11:51) \n[GCC 9.4.0]",
         "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics",
         "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": "1679473560"
+        "end_time_seconds": "1679478397"
     },
-    "total": 3609.1329525349997,
+    "total": 4144.746547039,
     "count": 1,
-    "self": 0.5558727650000037,
+    "self": 0.5300964620000741,
     "children": {
         "run_training.setup": {
-            "total": 0.1907406360001005,
+            "total": 0.11238969800001541,
             "count": 1,
-            "self": 0.1907406360001005
+            "self": 0.11238969800001541
         },
         "TrainerController.start_learning": {
-            "total": 3608.3863391339996,
+            "total": 4144.104060879,
             "count": 1,
-            "self": 1.276497031926283,
+            "self": 4.022551818038664,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 8.60012459799998,
+                    "total": 8.899378284000022,
                     "count": 1,
-                    "self": 8.60012459799998
+                    "self": 8.899378284000022
                 },
                 "TrainerController.advance": {
-                    "total": 3598.2700294030733,
-                    "count": 72573,
-                    "self": 1.4732234929861079,
+                    "total": 4131.003274655961,
+                    "count": 232310,
+                    "self": 4.511735430941371,
                     "children": {
                         "env_step": {
-                            "total": 607.735694285022,
-                            "count": 72573,
-                            "self": 510.3403054160889,
+                            "total": 1766.1016543360577,
+                            "count": 232310,
+                            "self": 1480.6118819039093,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 96.4992278729726,
-                                    "count": 72573,
-                                    "self": 6.98783421805615,
+                                    "total": 282.65204874007645,
+                                    "count": 232310,
+                                    "self": 17.271373965118357,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 89.51139365491645,
-                                            "count": 71875,
-                                            "self": 89.51139365491645
+                                            "total": 265.3806747749581,
+                                            "count": 222996,
+                                            "self": 265.3806747749581
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.8961609959604857,
-                                    "count": 72572,
+                                    "total": 2.837723692072018,
+                                    "count": 232310,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 3605.7992072760235,
-                                            "count": 72572,
+                                            "total": 4136.086511574963,
+                                            "count": 232310,
                                             "is_parallel": true,
-                                            "self": 3190.863189739011,
+                                            "self": 2936.804771202991,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -217,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0009796609999739303,
+                                                            "total": 0.0012255760000243754,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.00028537099990444403,
+                                                            "self": 0.00032889900006694006,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0006942900000694863,
+                                                                    "total": 0.0008966769999574353,
                                                                     "count": 2,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0006942900000694863
+                                                                    "self": 0.0008966769999574353
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.03005337599995528,
+                                                            "total": 0.029671286999985114,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.00034108799991372507,
+                                                            "self": 0.0003100299999800882,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0002267160000428703,
+                                                                    "total": 0.0002037579999978334,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0002267160000428703
+                                                                    "self": 0.0002037579999978334
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.028759551999996802,
+                                                                    "total": 0.028449517000012747,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.028759551999996802
+                                                                    "self": 0.028449517000012747
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0007260200000018813,
+                                                                    "total": 0.0007079819999944448,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00021467599992774922,
+                                                                    "self": 0.00023608899999771893,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0005113440000741321,
+                                                                            "total": 0.00047189299999672585,
                                                                             "count": 2,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0005113440000741321
+                                                                            "self": 0.00047189299999672585
                                                                         }
                                                                     }
                                                                 }
@@ -267,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 414.9360175370126,
-                                                    "count": 72571,
+                                                    "total": 1199.281740371972,
+                                                    "count": 232309,
                                                     "is_parallel": true,
-                                                    "self": 12.123275139162388,
+                                                    "self": 37.31301674010024,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 26.367381723899598,
-                                                            "count": 72571,
+                                                            "total": 75.46833451715844,
+                                                            "count": 232309,
                                                             "is_parallel": true,
-                                                            "self": 26.367381723899598
+                                                            "self": 75.46833451715844
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 347.47698185493687,
-                                                            "count": 72571,
+                                                            "total": 998.9619793668649,
+                                                            "count": 232309,
                                                             "is_parallel": true,
-                                                            "self": 347.47698185493687
+                                                            "self": 998.9619793668649
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 28.968378819013765,
-                                                            "count": 72571,
+                                                            "total": 87.53840974784868,
+                                                            "count": 232309,
                                                             "is_parallel": true,
-                                                            "self": 11.605077786976494,
+                                                            "self": 32.994573091928146,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 17.36330103203727,
-                                                                    "count": 145142,
+                                                                    "total": 54.54383665592053,
+                                                                    "count": 464618,
                                                                     "is_parallel": true,
-                                                                    "self": 17.36330103203727
+                                                                    "self": 54.54383665592053
                                                                 }
                                                             }
                                                         }
@@ -307,31 +307,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 2989.061111625065,
-                            "count": 72572,
-                            "self": 2.1907922180675996,
+                            "total": 2360.389884888962,
+                            "count": 232310,
+                            "self": 6.2217306960628775,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 33.179333187996804,
-                                    "count": 72572,
-                                    "self": 32.685874117996605,
+                                    "total": 136.41652813389635,
+                                    "count": 232310,
+                                    "self": 135.0728810488963,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.49345907000019906,
-                                            "count": 3,
-                                            "self": 0.49345907000019906
+                                            "total": 1.3436470850000433,
+                                            "count": 10,
+                                            "self": 1.3436470850000433
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 2953.690986219001,
-                                    "count": 30,
-                                    "self": 2378.3034116300378,
+                                    "total": 2217.751626059003,
+                                    "count": 97,
+                                    "self": 1843.9692946929913,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 575.387574588963,
-                                            "count": 48000,
-                                            "self": 575.387574588963
+                                            "total": 373.78233136601153,
+                                            "count": 19400,
+                                            "self": 373.78233136601153
                                         }
                                     }
                                 }
@@ -340,19 +340,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.4380002539837733e-06,
+                    "total": 1.2150003385613672e-06,
                     "count": 1,
-                    "self": 1.4380002539837733e-06
+                    "self": 1.2150003385613672e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.2396866629997021,
+                    "total": 0.17885490600019693,
                     "count": 1,
-                    "self": 0.004467471999305417,
+                    "self": 0.0027192440002181684,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.23521919100039668,
+                            "total": 0.17613566199997877,
                             "count": 1,
-                            "self": 0.23521919100039668
+                            "self": 0.17613566199997877
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,49 +2,112 @@
     "Huggy": {
         "checkpoints": [
             {
-                "steps": 199704,
-                "file_path": "results/Huggy/Huggy/Huggy-199704.onnx",
-                "reward": 3.0943431153893473,
-                "creation_time": 1679471044.4947164,
+                "steps": 199847,
+                "file_path": "results/Huggy/Huggy/Huggy-199847.onnx",
+                "reward": 3.3398273072830618,
+                "creation_time": 1679474655.5939345,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-199704.pt"
+                    "results/Huggy/Huggy/Huggy-199847.pt"
                 ]
             },
             {
-                "steps": 399436,
-                "file_path": "results/Huggy/Huggy/Huggy-399436.onnx",
-                "reward": -2.1291646994650364,
-                "creation_time": 1679472230.6567485,
+                "steps": 399908,
+                "file_path": "results/Huggy/Huggy/Huggy-399908.onnx",
+                "reward": 3.713761279832071,
+                "creation_time": 1679475071.4325223,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-399436.pt"
+                    "results/Huggy/Huggy/Huggy-399908.pt"
                 ]
             },
             {
-                "steps": 599365,
-                "file_path": "results/Huggy/Huggy/Huggy-599365.onnx",
-                "reward": -2.1034353372330465,
-                "creation_time": 1679473319.8183784,
+                "steps": 599992,
+                "file_path": "results/Huggy/Huggy/Huggy-599992.onnx",
+                "reward": 4.303998399864543,
+                "creation_time": 1679475494.313536,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-599365.pt"
+                    "results/Huggy/Huggy/Huggy-599992.pt"
                 ]
             },
             {
-                "steps": 639115,
-                "file_path": "results/Huggy/Huggy/Huggy-639115.onnx",
-                "reward": -3.980861658602953,
-                "creation_time": 1679473559.8596787,
+                "steps": 799931,
+                "file_path": "results/Huggy/Huggy/Huggy-799931.onnx",
+                "reward": 3.867483305749554,
+                "creation_time": 1679475884.7164605,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-639115.pt"
+                    "results/Huggy/Huggy/Huggy-799931.pt"
+                ]
+            },
+            {
+                "steps": 999768,
+                "file_path": "results/Huggy/Huggy/Huggy-999768.onnx",
+                "reward": 3.7985709354180055,
+                "creation_time": 1679476307.1492262,
+                "auxillary_file_paths": [
+                    "results/Huggy/Huggy/Huggy-999768.pt"
+                ]
+            },
+            {
+                "steps": 1199995,
+                "file_path": "results/Huggy/Huggy/Huggy-1199995.onnx",
+                "reward": 4.117473165194194,
+                "creation_time": 1679476737.1748662,
+                "auxillary_file_paths": [
+                    "results/Huggy/Huggy/Huggy-1199995.pt"
+                ]
+            },
+            {
+                "steps": 1399977,
+                "file_path": "results/Huggy/Huggy/Huggy-1399977.onnx",
+                "reward": 4.03873997926712,
+                "creation_time": 1679477164.3829093,
+                "auxillary_file_paths": [
+                    "results/Huggy/Huggy/Huggy-1399977.pt"
+                ]
+            },
+            {
+                "steps": 1599951,
+                "file_path": "results/Huggy/Huggy/Huggy-1599951.onnx",
+                "reward": 3.362104951102158,
+                "creation_time": 1679477566.528787,
+                "auxillary_file_paths": [
+                    "results/Huggy/Huggy/Huggy-1599951.pt"
+                ]
+            },
+            {
+                "steps": 1799937,
+                "file_path": "results/Huggy/Huggy/Huggy-1799937.onnx",
+                "reward": 3.5458122606981886,
+                "creation_time": 1679477983.0181205,
+                "auxillary_file_paths": [
+                    "results/Huggy/Huggy/Huggy-1799937.pt"
+                ]
+            },
+            {
+                "steps": 1999960,
+                "file_path": "results/Huggy/Huggy/Huggy-1999960.onnx",
+                "reward": 3.975877057422291,
+                "creation_time": 1679478396.6934578,
+                "auxillary_file_paths": [
+                    "results/Huggy/Huggy/Huggy-1999960.pt"
+                ]
+            },
+            {
+                "steps": 2000062,
+                "file_path": "results/Huggy/Huggy/Huggy-2000062.onnx",
+                "reward": 4.090453813473384,
+                "creation_time": 1679478396.8779893,
+                "auxillary_file_paths": [
+                    "results/Huggy/Huggy/Huggy-2000062.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 639115,
+            "steps": 2000062,
             "file_path": "results/Huggy/Huggy.onnx",
-            "reward": -3.980861658602953,
-            "creation_time": 1679473559.8596787,
+            "reward": 4.090453813473384,
+            "creation_time": 1679478396.8779893,
             "auxillary_file_paths": [
-                "results/Huggy/Huggy/Huggy-639115.pt"
+                "results/Huggy/Huggy/Huggy-2000062.pt"
             ]
         }
     },