Huggy

Huggy.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2d808515a6063cf6e542de21bc579a465d3eed17b1c4dd8bb221115fd8f7694
-size 2270373
+oid sha256:78696cd15fba20d8cb649e8a0499d3bf90b88becb32f0c65ffd2984254eed514
+size 2271327

Huggy/{Huggy-1199965.onnx → Huggy-1199976.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b870751e8e48738021a3a5d06ddcb6eca76998425a11b95ae52f788f15ca4594
-size 2270373
+oid sha256:13ffb320e46c3986875a21b6cc653157aacc9aac3e70a405c834925b8a350360
+size 2271327

Huggy/{Huggy-1199965.pt → Huggy-1199976.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:999a11939dd3dd1557dc9db6513034d6192f34c571569232d791ec740a9f1931
-size 13505248
+oid sha256:f67b7857ca49ceaf32c70dccffcd3e87157c7a716dbdfcb1b29278c0683bc80b
+size 13503717

Huggy/{Huggy-1599963.onnx → Huggy-1399929.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3bf399ae6c161e7d26a6506410b5ff7daa83bedb6d8b660c5f9eef2d64b39c1
-size 2270373
+oid sha256:0b3082d2a704d2776a86795524c917ce827528dd9ad0faf2118337c077968a3f
+size 2271327

Huggy/{Huggy-1399970.pt → Huggy-1399929.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e148a2d997b25db11493621effcc8076d6ed6f650dea65aba7a466f6c7c8a8f4
-size 13505248
+oid sha256:095b26ccdc6bc6b7e69b63feeacd1c8a6aa150c0645f08ccb7c3f7745e1c459e
+size 13503717

Huggy/Huggy-1599963.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3323ac4fb61288c4a6f65d144305e0117aa062adb24994d05d7c4716f99f0b7e
-size 13505248

Huggy/{Huggy-1399970.onnx → Huggy-1599966.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f03e3b92ad3ba304134643b9ca5421a7d4598a60420b9e3b33171928b1a81236
-size 2270373
+oid sha256:81e8fa2e31a2df60fa7723857bd87802da0e6efab73c6950d67a3ccf7bf8d892
+size 2271327

Huggy/Huggy-1599966.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35bcee29b445c18d4bd6fd0aa2d899020e91083e1c7f2a9c673e616c0866054e
+size 13503717

Huggy/{Huggy-1799950.onnx → Huggy-1799929.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7faaf3d4e781cd96b9462a5a4dcebe1f12b2b282944b403e3efa8178ae829908
-size 2270373
+oid sha256:d92ef05e3a04bb0a3cb46f93765462396c649a3dbcd081d72e7758274d308ea5
+size 2271327

Huggy/Huggy-1799929.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e515b0f2cdd6194826e656e4b767f879975c2439be0a6264aa1cc45b2e40a1d
+size 13503717

Huggy/Huggy-1799950.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:39d6ef17408868386ea2c5300b443865736fc477976e37a3da035fb326b5410f
-size 13505248

Huggy/Huggy-199915.onnx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f6cdfad16dc10b0f342bd47df92219384cf84762145daa164af82667ba6386d3
-size 2270373

Huggy/Huggy-199915.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5792805d8bdd5058614425a8a9d43ea67c8caaea9feadec17c0fdeb4919e3e89
-size 13505248

Huggy/Huggy-199983.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2478e9b3d13931a56d6e6acb25bf5c1a651de7c705d268b4d0ab0870e14ee91e
+size 2271327

Huggy/Huggy-199983.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:950655c2192bda9dcf2b212037083edf6b8cc85c926ba3d88d56646ce221e645
+size 13503717

Huggy/Huggy-1999946.onnx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c062dde4491490b3137a0e53b256eae34558cb65c068207277b26b98ce05456c
-size 2270373

Huggy/Huggy-1999946.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2975198850d59d0261615f1cd3cd0d90d8d35425f0af5fd3cc8c87bbce0f3873
-size 13505248

Huggy/Huggy-1999992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7e23727fa42439b36d367c9930eaa80280a68e09c11607bd7891f98cc09b05f
+size 2271327

Huggy/Huggy-1999992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6038fa5114ccfb16564a24edab41b8d99cd739defca182193a199b0b67672754
+size 13503717

Huggy/Huggy-2000016.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78696cd15fba20d8cb649e8a0499d3bf90b88becb32f0c65ffd2984254eed514
+size 2271327

Huggy/Huggy-2000016.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0c94442c0eb9cf5c77bc999372afbd44feeef3c95a8f9e7c53fd65f4a9dbf17
+size 13503717

Huggy/Huggy-2000043.onnx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f2d808515a6063cf6e542de21bc579a465d3eed17b1c4dd8bb221115fd8f7694
-size 2270373

Huggy/Huggy-2000043.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c54039a52d557cfc25216fa9b7f6ffd8929048139883f2abc3ba489bf6de0327
-size 13505248

Huggy/Huggy-399889.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81a19ac33f52635d67a1f00c88141b15c4369d99765b4b895c7b115b6db680be
+size 2271327

Huggy/Huggy-399889.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:626da5d1d5bbe7df1e5a80478dd976a840841071a1e8a2376314c7c37083e9ea
+size 13503717

Huggy/Huggy-399915.onnx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3df251995dd1d09051cb3ba18278814e5e97b651f73be004f2ef80b47ab90995
-size 2270373

Huggy/Huggy-399915.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5874a2d69f82cf0e35f8f1d4f36ffeb2eeb7383e770cb2612e60e3a8bf636f06
-size 13505248

Huggy/Huggy-599942.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffd9601027f8a878a163c9babd87e88fb73cfec96ab0105e8fc2b454de1e030d
+size 2271327

Huggy/Huggy-599942.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f0880c6c379c41dd0ab0c76c3de21cd68427d34f3921aa75fc0e9ba10183f48
+size 13503717

Huggy/Huggy-599999.onnx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:cc6b614bc26e2edf264a58cef01572b1094011e64d85f1a41bb40fdf41de4571
-size 2270373

Huggy/Huggy-599999.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:33d7ca015df8faa39eff9cd1916f7188fc2d99aee7f696cb285faa50420ee8a3
-size 13505248

Huggy/Huggy-799320.onnx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:63136d4228c021d7f8a430d16f0d8dbd9cb4d72bf0041417700e7d38961c00ef
-size 2270373

Huggy/Huggy-799320.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6d77e4ae1626cbba046c4d958fdfe6ca717d8424dbe8024c0b2c81ebcca8f800
-size 13505248

Huggy/Huggy-799970.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:841cc8f8730f7a5d6069c17c74b7dac22599ae25973458c7ea2802a40aca1bd1
+size 2271327

Huggy/Huggy-799970.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00c552fcb02bab5cb9296365f45628be60f40bacef2e77ad9eb7e87dd967af68
+size 13503717

Huggy/Huggy-999880.onnx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d84da1275640376c3b19d231ab96a1f95111cef6ee65ab0010eb253c4fb27c64
-size 2270373

Huggy/Huggy-999880.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9f31c2a617e5a7e38bf4e7d6e2f44e589096f46e28341128e29293a29a55f46e
-size 13505248

Huggy/Huggy-999960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8ec342330565362d2bf06f3005239895d3ba1f8c2bc82d6d89fb06669c7e9d8
+size 2271327

Huggy/Huggy-999960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0972e0ac711f903611113859eb2919625c09152f349bd263dade72ac82123bf3
+size 13503717

Huggy/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c54039a52d557cfc25216fa9b7f6ffd8929048139883f2abc3ba489bf6de0327
-size 13505248
+oid sha256:f0c94442c0eb9cf5c77bc999372afbd44feeef3c95a8f9e7c53fd65f4a9dbf17
+size 13503717

Huggy/{events.out.tfevents.1677697769.5ac59dca34b5.2584.0 → events.out.tfevents.1679690671.8d968452644e.1733.0}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b62739d4fe8d6c668b8320b9aa7521dc26e639ea3b089a4a057e7704661e5915
-size 407744
+oid sha256:f10bfaaf80c3b9ec06cd09073d8fe8449addc45a3f56f8aa6cfc979b3fa9faff
+size 380097

README.md

@@ -1,12 +1,10 @@
-
 ---
-      tags:
-      - unity-ml-agents
-      - ml-agents
-      - deep-reinforcement-learning
-      - reinforcement-learning
-      - ML-Agents-Huggy
-      library_name: ml-agents
+library_name: ml-agents
+tags:
+- Huggy
+- deep-reinforcement-learning
+- reinforcement-learning
+- ML-Agents-Huggy
 ---
     
   # **ppo** Agent playing **Huggy**

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, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "network_settings": {"normalize": true, "hidden_units": 512, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.995, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 15, "checkpoint_interval": 200000, "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": 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, "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

@@ -10,9 +10,11 @@ behaviors:
       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
@@ -35,7 +37,7 @@ behaviors:
           deterministic: false
     init_path: null
     keep_checkpoints: 15
-    checkpoint_interval: 200000
+    even_checkpoints: false
     max_steps: 2000000
     time_horizon: 1000
     summary_freq: 50000

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  0.085 seconds
+- Completed reload, in  0.124 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: 0.803104 ms
+UnloadTime: 0.962519 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]: 26746 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [4.0 KB-8.0 KB]: 26764 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 160 B
+      Peak Allocated Bytes 208 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 326
+  Peak main deferred allocation count 345
     [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]: 26747 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 26765 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 23.2 MB
+      Peak Allocated memory 23.4 MB
       Peak Large allocation bytes 16.0 MB
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [2.0 MB-4.0 MB]: 26747 frames
+      Peak usage frame count: [2.0 MB-4.0 MB]: 26765 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]: 26746 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 26764 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]: 26747 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 26765 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]: 26746 frames, [16.0 MB-32.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 26764 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]: 26746 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 26764 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]: 26747 frames
+      Peak usage frame count: [0-1.0 KB]: 26765 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]: 26747 frames
+      Peak usage frame count: [4.0 KB-8.0 KB]: 26765 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 7.3 KB

run_logs/timers.json

@@ -2,135 +2,135 @@
     "name": "root",
     "gauges": {
         "Huggy.Policy.Entropy.mean": {
-            "value": 1.404802918434143,
-            "min": 1.404802918434143,
-            "max": 1.4267228841781616,
+            "value": 1.4025402069091797,
+            "min": 1.4025402069091797,
+            "max": 1.4245027303695679,
             "count": 40
         },
         "Huggy.Policy.Entropy.sum": {
-            "value": 68176.4921875,
-            "min": 67854.3125,
-            "max": 78659.9375,
+            "value": 70258.8515625,
+            "min": 68535.140625,
+            "max": 77408.328125,
             "count": 40
         },
         "Huggy.Environment.EpisodeLength.mean": {
-            "value": 118.31503579952268,
-            "min": 101.14545454545454,
-            "max": 411.0406504065041,
+            "value": 94.03625954198473,
+            "min": 91.35674676524954,
+            "max": 409.91803278688525,
             "count": 40
         },
         "Huggy.Environment.EpisodeLength.sum": {
-            "value": 49574.0,
-            "min": 48919.0,
-            "max": 50558.0,
+            "value": 49275.0,
+            "min": 49040.0,
+            "max": 50010.0,
             "count": 40
         },
         "Huggy.Step.mean": {
-            "value": 1999946.0,
-            "min": 49931.0,
-            "max": 1999946.0,
+            "value": 1999992.0,
+            "min": 49559.0,
+            "max": 1999992.0,
             "count": 40
         },
         "Huggy.Step.sum": {
-            "value": 1999946.0,
-            "min": 49931.0,
-            "max": 1999946.0,
+            "value": 1999992.0,
+            "min": 49559.0,
+            "max": 1999992.0,
             "count": 40
         },
         "Huggy.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 2.267110586166382,
-            "min": 0.1609315574169159,
-            "max": 2.4067299365997314,
+            "value": 2.4083993434906006,
+            "min": 0.08785222470760345,
+            "max": 2.456249713897705,
             "count": 40
         },
         "Huggy.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 949.9193725585938,
-            "min": 19.633649826049805,
-            "max": 1166.51123046875,
+            "value": 1262.001220703125,
+            "min": 10.630119323730469,
+            "max": 1292.97705078125,
             "count": 40
         },
         "Huggy.Environment.CumulativeReward.mean": {
-            "value": 3.4517717237688763,
-            "min": 1.866492737389979,
-            "max": 3.7933397055167912,
+            "value": 3.6215579612109496,
+            "min": 1.91974040693488,
+            "max": 3.8944474041001675,
             "count": 40
         },
         "Huggy.Environment.CumulativeReward.sum": {
-            "value": 1446.292352259159,
-            "min": 227.71211396157742,
-            "max": 1824.5963983535767,
+            "value": 1897.6963716745377,
+            "min": 232.28858923912048,
+            "max": 2017.3237553238869,
             "count": 40
         },
         "Huggy.Policy.ExtrinsicReward.mean": {
-            "value": 3.4517717237688763,
-            "min": 1.866492737389979,
-            "max": 3.7933397055167912,
+            "value": 3.6215579612109496,
+            "min": 1.91974040693488,
+            "max": 3.8944474041001675,
             "count": 40
         },
         "Huggy.Policy.ExtrinsicReward.sum": {
-            "value": 1446.292352259159,
-            "min": 227.71211396157742,
-            "max": 1824.5963983535767,
+            "value": 1897.6963716745377,
+            "min": 232.28858923912048,
+            "max": 2017.3237553238869,
             "count": 40
         },
         "Huggy.Losses.PolicyLoss.mean": {
-            "value": 0.015343147134747898,
-            "min": 0.013288712732780063,
-            "max": 0.020048397752301148,
+            "value": 0.018413776876372544,
+            "min": 0.01324789439192197,
+            "max": 0.019262995963799767,
             "count": 40
         },
         "Huggy.Losses.PolicyLoss.sum": {
-            "value": 0.030686294269495797,
-            "min": 0.026577425465560127,
-            "max": 0.05706798822066048,
+            "value": 0.05524133062911763,
+            "min": 0.02649578878384394,
+            "max": 0.05728803027886898,
             "count": 40
         },
         "Huggy.Losses.ValueLoss.mean": {
-            "value": 0.04606515715519587,
-            "min": 0.020765541835377613,
-            "max": 0.06654205725838741,
+            "value": 0.055665835655397844,
+            "min": 0.020341297083844738,
+            "max": 0.06209323480725289,
             "count": 40
         },
         "Huggy.Losses.ValueLoss.sum": {
-            "value": 0.09213031431039174,
-            "min": 0.041531083670755226,
-            "max": 0.1835729256272316,
+            "value": 0.16699750696619353,
+            "min": 0.040682594167689476,
+            "max": 0.1671121843159199,
             "count": 40
         },
         "Huggy.Policy.LearningRate.mean": {
-            "value": 3.7559487480499878e-06,
-            "min": 3.7559487480499878e-06,
-            "max": 0.0002952820515726499,
+            "value": 3.3062988979333373e-06,
+            "min": 3.3062988979333373e-06,
+            "max": 0.0002953548015484,
             "count": 40
         },
         "Huggy.Policy.LearningRate.sum": {
-            "value": 7.5118974960999756e-06,
-            "min": 7.5118974960999756e-06,
-            "max": 0.0008438631187123,
+            "value": 9.918896693800011e-06,
+            "min": 9.918896693800011e-06,
+            "max": 0.0008442865685711499,
             "count": 40
         },
         "Huggy.Policy.Epsilon.mean": {
-            "value": 0.10125195,
-            "min": 0.10125195,
-            "max": 0.19842734999999995,
+            "value": 0.1011020666666667,
+            "min": 0.1011020666666667,
+            "max": 0.19845160000000006,
             "count": 40
         },
         "Huggy.Policy.Epsilon.sum": {
-            "value": 0.2025039,
-            "min": 0.2025039,
-            "max": 0.5812877000000001,
+            "value": 0.3033062000000001,
+            "min": 0.20734560000000002,
+            "max": 0.5814288500000001,
             "count": 40
         },
         "Huggy.Policy.Beta.mean": {
-            "value": 7.247230499999979e-05,
-            "min": 7.247230499999979e-05,
-            "max": 0.004921524765000001,
+            "value": 6.499312666666674e-05,
+            "min": 6.499312666666674e-05,
+            "max": 0.00492273484,
             "count": 40
         },
         "Huggy.Policy.Beta.sum": {
-            "value": 0.00014494460999999958,
-            "min": 0.00014494460999999958,
-            "max": 0.01406625623,
+            "value": 0.00019497938000000023,
+            "min": 0.00019497938000000023,
+            "max": 0.014073299615000001,
             "count": 40
         },
         "Huggy.IsTraining.mean": {
@@ -148,74 +148,67 @@
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1677697763",
-        "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
+        "start_time_seconds": "1679690664",
+        "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": "0.29.0.dev0",
-        "mlagents_envs_version": "0.29.0.dev0",
+        "mlagents_version": "0.31.0.dev0",
+        "mlagents_envs_version": "0.31.0.dev0",
         "communication_protocol_version": "1.5.0",
-        "pytorch_version": "1.8.1+cu102",
-        "numpy_version": "1.22.4",
-        "end_time_seconds": "1677700310"
+        "pytorch_version": "1.11.0+cu102",
+        "numpy_version": "1.21.2",
+        "end_time_seconds": "1679693086"
     },
-    "total": 2547.700488548,
+    "total": 2421.799608962,
     "count": 1,
-    "self": 0.6465202579997822,
+    "self": 0.6538370620000933,
     "children": {
         "run_training.setup": {
-            "total": 0.12337811300005797,
+            "total": 0.18884839099996498,
             "count": 1,
-            "self": 0.12337811300005797
+            "self": 0.18884839099996498
         },
         "TrainerController.start_learning": {
-            "total": 2546.9305901770003,
+            "total": 2420.956923509,
             "count": 1,
-            "self": 4.521163493920994,
+            "self": 4.390861847987708,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 10.149546101000055,
+                    "total": 9.355135537000024,
                     "count": 1,
-                    "self": 10.149546101000055
+                    "self": 9.355135537000024
                 },
                 "TrainerController.advance": {
-                    "total": 2532.0743929520795,
-                    "count": 230865,
-                    "self": 5.098670624156512,
+                    "total": 2407.0345228730116,
+                    "count": 231917,
+                    "self": 4.869387009989168,
                     "children": {
                         "env_step": {
-                            "total": 1985.878349552022,
-                            "count": 230865,
-                            "self": 1661.766109405125,
+                            "total": 1888.8564764429962,
+                            "count": 231917,
+                            "self": 1588.9076231740103,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 321.1448448910228,
-                                    "count": 230865,
-                                    "self": 17.0645879451057,
+                                    "total": 297.01542189998816,
+                                    "count": 231917,
+                                    "self": 17.252571867874508,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 304.0802569459171,
-                                            "count": 222888,
-                                            "self": 75.43333737892135,
-                                            "children": {
-                                                "TorchPolicy.sample_actions": {
-                                                    "total": 228.64691956699573,
-                                                    "count": 222888,
-                                                    "self": 228.64691956699573
-                                                }
-                                            }
+                                            "total": 279.76285003211365,
+                                            "count": 223040,
+                                            "self": 279.76285003211365
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 2.967395255874294,
-                                    "count": 230865,
+                                    "total": 2.933431368997674,
+                                    "count": 231917,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2537.6329634619638,
-                                            "count": 230865,
+                                            "total": 2412.688104053024,
+                                            "count": 231917,
                                             "is_parallel": true,
-                                            "self": 1192.1279314029894,
+                                            "self": 1124.6026517799646,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -224,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.001037663999909455,
+                                                            "total": 0.0011898839999844313,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0004797029998826474,
+                                                            "self": 0.0003415459999587256,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0005579610000268076,
+                                                                    "total": 0.0008483380000257057,
                                                                     "count": 2,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0005579610000268076
+                                                                    "self": 0.0008483380000257057
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.03212543099994036,
+                                                            "total": 0.029469876999996814,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.00031662300000334653,
+                                                            "self": 0.00031085500000926913,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00021203999995123013,
+                                                                    "total": 0.00022203600002512758,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00021203999995123013
+                                                                    "self": 0.00022203600002512758
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.028798876999985623,
+                                                                    "total": 0.028237982999996802,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.028798876999985623
+                                                                    "self": 0.028237982999996802
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0027978910000001633,
+                                                                    "total": 0.0006990029999656144,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00029976800010445004,
+                                                                    "self": 0.00021717800001397336,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0024981229998957133,
+                                                                            "total": 0.0004818249999516411,
                                                                             "count": 2,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0024981229998957133
+                                                                            "self": 0.0004818249999516411
                                                                         }
                                                                     }
                                                                 }
@@ -274,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1345.5050320589744,
-                                                    "count": 230864,
+                                                    "total": 1288.0854522730592,
+                                                    "count": 231916,
                                                     "is_parallel": true,
-                                                    "self": 39.91973135400394,
+                                                    "self": 38.06529567600887,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 85.60510566700009,
-                                                            "count": 230864,
+                                                            "total": 79.71929237007527,
+                                                            "count": 231916,
                                                             "is_parallel": true,
-                                                            "self": 85.60510566700009
+                                                            "self": 79.71929237007527
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1123.4666237709603,
-                                                            "count": 230864,
+                                                            "total": 1078.8027817390016,
+                                                            "count": 231916,
                                                             "is_parallel": true,
-                                                            "self": 1123.4666237709603
+                                                            "self": 1078.8027817390016
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 96.5135712670101,
-                                                            "count": 230864,
+                                                            "total": 91.49808248797348,
+                                                            "count": 231916,
                                                             "is_parallel": true,
-                                                            "self": 41.266799099923105,
+                                                            "self": 36.392665674998,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 55.24677216708699,
-                                                                    "count": 461728,
+                                                                    "total": 55.10541681297548,
+                                                                    "count": 463832,
                                                                     "is_parallel": true,
-                                                                    "self": 55.24677216708699
+                                                                    "self": 55.10541681297548
                                                                 }
                                                             }
                                                         }
@@ -314,31 +307,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 541.097372775901,
-                            "count": 230865,
-                            "self": 6.987421608971431,
+                            "total": 513.3086594200262,
+                            "count": 231917,
+                            "self": 6.89963468704417,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 169.21816589293087,
-                                    "count": 230865,
-                                    "self": 167.96726902093087,
+                                    "total": 147.7529423379816,
+                                    "count": 231917,
+                                    "self": 146.4423840709817,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 1.2508968719999984,
+                                            "total": 1.3105582669999194,
                                             "count": 10,
-                                            "self": 1.2508968719999984
+                                            "self": 1.3105582669999194
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 364.8917852739987,
-                                    "count": 96,
-                                    "self": 306.54927436000366,
+                                    "total": 358.6560823950004,
+                                    "count": 97,
+                                    "self": 299.65566617898963,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 58.342510913995056,
-                                            "count": 2880,
-                                            "self": 58.342510913995056
+                                            "total": 59.00041621601076,
+                                            "count": 2910,
+                                            "self": 59.00041621601076
                                         }
                                     }
                                 }
@@ -347,19 +340,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.2929999684274662e-06,
+                    "total": 1.401000190526247e-06,
                     "count": 1,
-                    "self": 1.2929999684274662e-06
+                    "self": 1.401000190526247e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.18548633699992934,
+                    "total": 0.17640185000027486,
                     "count": 1,
-                    "self": 0.002967826999793033,
+                    "self": 0.002707839000322565,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.1825185100001363,
+                            "total": 0.1736940109999523,
                             "count": 1,
-                            "self": 0.1825185100001363
+                            "self": 0.1736940109999523
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,118 +2,118 @@
     "Huggy": {
         "checkpoints": [
             {
-                "steps": 199915,
-                "file_path": "results/Huggy/Huggy/Huggy-199915.onnx",
-                "reward": 3.1146259531378746,
-                "creation_time": 1677698020.945621,
+                "steps": 199983,
+                "file_path": "results/Huggy/Huggy/Huggy-199983.onnx",
+                "reward": 3.3457605759302775,
+                "creation_time": 1679690909.3011253,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-199915.pt"
+                    "results/Huggy/Huggy/Huggy-199983.pt"
                 ]
             },
             {
-                "steps": 399915,
-                "file_path": "results/Huggy/Huggy/Huggy-399915.onnx",
-                "reward": 3.4472700586685767,
-                "creation_time": 1677698273.6690817,
+                "steps": 399889,
+                "file_path": "results/Huggy/Huggy/Huggy-399889.onnx",
+                "reward": 3.744452214241028,
+                "creation_time": 1679691154.1306283,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-399915.pt"
+                    "results/Huggy/Huggy/Huggy-399889.pt"
                 ]
             },
             {
-                "steps": 599999,
-                "file_path": "results/Huggy/Huggy/Huggy-599999.onnx",
-                "reward": 4.309198220570882,
-                "creation_time": 1677698531.2108574,
+                "steps": 599942,
+                "file_path": "results/Huggy/Huggy/Huggy-599942.onnx",
+                "reward": 3.598223002893584,
+                "creation_time": 1679691399.6091504,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-599999.pt"
+                    "results/Huggy/Huggy/Huggy-599942.pt"
                 ]
             },
             {
-                "steps": 799320,
-                "file_path": "results/Huggy/Huggy/Huggy-799320.onnx",
-                "reward": 3.6679738556796853,
-                "creation_time": 1677698781.4041173,
+                "steps": 799970,
+                "file_path": "results/Huggy/Huggy/Huggy-799970.onnx",
+                "reward": 3.851994901384626,
+                "creation_time": 1679691644.1959786,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-799320.pt"
+                    "results/Huggy/Huggy/Huggy-799970.pt"
                 ]
             },
             {
-                "steps": 999880,
-                "file_path": "results/Huggy/Huggy/Huggy-999880.onnx",
-                "reward": 3.6124744171737344,
-                "creation_time": 1677699042.0877016,
+                "steps": 999960,
+                "file_path": "results/Huggy/Huggy/Huggy-999960.onnx",
+                "reward": 4.011924490884498,
+                "creation_time": 1679691889.5424368,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-999880.pt"
+                    "results/Huggy/Huggy/Huggy-999960.pt"
                 ]
             },
             {
-                "steps": 1199965,
-                "file_path": "results/Huggy/Huggy/Huggy-1199965.onnx",
-                "reward": 3.618754888574282,
-                "creation_time": 1677699297.5349429,
+                "steps": 1199976,
+                "file_path": "results/Huggy/Huggy/Huggy-1199976.onnx",
+                "reward": 3.699399713313941,
+                "creation_time": 1679692135.9807248,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-1199965.pt"
+                    "results/Huggy/Huggy/Huggy-1199976.pt"
                 ]
             },
             {
-                "steps": 1399970,
-                "file_path": "results/Huggy/Huggy/Huggy-1399970.onnx",
-                "reward": 3.5206354596987874,
-                "creation_time": 1677699549.2530198,
+                "steps": 1399929,
+                "file_path": "results/Huggy/Huggy/Huggy-1399929.onnx",
+                "reward": 3.70279788609707,
+                "creation_time": 1679692373.3203995,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-1399970.pt"
+                    "results/Huggy/Huggy/Huggy-1399929.pt"
                 ]
             },
             {
-                "steps": 1599963,
-                "file_path": "results/Huggy/Huggy/Huggy-1599963.onnx",
-                "reward": 3.755335281421612,
-                "creation_time": 1677699805.3244987,
+                "steps": 1599966,
+                "file_path": "results/Huggy/Huggy/Huggy-1599966.onnx",
+                "reward": 3.497054300374455,
+                "creation_time": 1679692611.95537,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-1599963.pt"
+                    "results/Huggy/Huggy/Huggy-1599966.pt"
                 ]
             },
             {
-                "steps": 1799950,
-                "file_path": "results/Huggy/Huggy/Huggy-1799950.onnx",
-                "reward": 3.957658366153115,
-                "creation_time": 1677700061.852063,
+                "steps": 1799929,
+                "file_path": "results/Huggy/Huggy/Huggy-1799929.onnx",
+                "reward": 3.818619439768237,
+                "creation_time": 1679692849.2364964,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-1799950.pt"
+                    "results/Huggy/Huggy/Huggy-1799929.pt"
                 ]
             },
             {
-                "steps": 1999946,
-                "file_path": "results/Huggy/Huggy/Huggy-1999946.onnx",
-                "reward": 3.6023076446551197,
-                "creation_time": 1677700309.8688579,
+                "steps": 1999992,
+                "file_path": "results/Huggy/Huggy/Huggy-1999992.onnx",
+                "reward": 3.8084478278954825,
+                "creation_time": 1679693085.8297596,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-1999946.pt"
+                    "results/Huggy/Huggy/Huggy-1999992.pt"
                 ]
             },
             {
-                "steps": 2000043,
-                "file_path": "results/Huggy/Huggy/Huggy-2000043.onnx",
-                "reward": 3.6226995693188964,
-                "creation_time": 1677700310.0615625,
+                "steps": 2000016,
+                "file_path": "results/Huggy/Huggy/Huggy-2000016.onnx",
+                "reward": 3.7090988826751707,
+                "creation_time": 1679693086.0081086,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-2000043.pt"
+                    "results/Huggy/Huggy/Huggy-2000016.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 2000043,
+            "steps": 2000016,
             "file_path": "results/Huggy/Huggy.onnx",
-            "reward": 3.6226995693188964,
-            "creation_time": 1677700310.0615625,
+            "reward": 3.7090988826751707,
+            "creation_time": 1679693086.0081086,
             "auxillary_file_paths": [
-                "results/Huggy/Huggy/Huggy-2000043.pt"
+                "results/Huggy/Huggy/Huggy-2000016.pt"
             ]
         }
     },
     "metadata": {
         "stats_format_version": "0.3.0",
-        "mlagents_version": "0.29.0.dev0",
-        "torch_version": "1.8.1+cu102"
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "1.11.0+cu102"
     }
 }