Huggy with 768 hidden units

Huggy.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6dfb28d1307798bba2695fc32d3935693c8210d377eb4b4846c95935c97e8ac
-size 2274020
+oid sha256:920d53c7274cf1d1884daff1788b6b36b202f6e14c38dfd4b7fe1cec8fdadfdf
+size 4974430

Huggy/Huggy-2020885.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:920d53c7274cf1d1884daff1788b6b36b202f6e14c38dfd4b7fe1cec8fdadfdf
+size 4974430

Huggy/Huggy-2020885.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:273e4d9e05cb6ff356b7e13cccec4a36b36f557ce3568d7af8c519ce1f39ee1e
+size 18902330

Huggy/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79adc4fdf829b08716dbcb8bc8939501d1ad79a943365e72a9b50be9f3a6c492
-size 13509685
+oid sha256:b9ff9b354485db145d935c43b7894a0a652070a55296223085db8fe70c4ce19d
+size 18902069

Huggy/events.out.tfevents.1751645367.35a174338985.20686.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99cb7cf351e68437a863cdd18dce8eedce35ef65b0fdc25eef1d3cde08c235ee
+size 1121

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"Huggy": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 200000, "network_settings": {"normalize": true, "hidden_units": 512, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.995, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 15, "even_checkpoints": false, "max_steps": 2000000, "time_horizon": 1000, "summary_freq": 50000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./trained-envs-executables/linux/Huggy/Huggy", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Huggy2", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"Huggy": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0005, "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": 768, "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": 4000000, "time_horizon": 1000, "summary_freq": 50000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./trained-envs-executables/linux/Huggy/Huggy", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Huggy2", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -5,7 +5,7 @@ behaviors:
     hyperparameters:
       batch_size: 2048
       buffer_size: 20480
-      learning_rate: 0.0003
+      learning_rate: 0.0005
       beta: 0.005
       epsilon: 0.2
       lambd: 0.95
@@ -17,7 +17,7 @@ behaviors:
     checkpoint_interval: 200000
     network_settings:
       normalize: true
-      hidden_units: 512
+      hidden_units: 768
       num_layers: 3
       vis_encode_type: simple
       memory: null
@@ -38,7 +38,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 15
     even_checkpoints: false
-    max_steps: 2000000
+    max_steps: 4000000
     time_horizon: 1000
     summary_freq: 50000
     threaded: false
@@ -69,7 +69,7 @@ checkpoint_settings:
   run_id: Huggy2
   initialize_from: null
   load_model: false
-  resume: false
+  resume: true
   force: false
   train_model: false
   inference: false

run_logs/Player-0.log

@@ -2,9 +2,6 @@ Mono path[0] = '/content/ml-agents/trained-envs-executables/linux/Huggy/Huggy_Da
 Mono config path = '/content/ml-agents/trained-envs-executables/linux/Huggy/Huggy_Data/MonoBleedingEdge/etc'
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
-PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face
-PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face/Huggy
-Unable to load player prefs
 Initialize engine version: 2021.3.14f1 (eee1884e7226)
 [Subsystems] Discovering subsystems at path /content/ml-agents/trained-envs-executables/linux/Huggy/Huggy_Data/UnitySubsystems
 Forcing GfxDevice: Null
@@ -34,7 +31,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.085 seconds
+- Completed reload, in  0.087 seconds
 ERROR: Shader Hidden/Universal Render Pipeline/Blit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Hidden/Universal Render Pipeline/CopyDepth shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Hidden/Universal Render Pipeline/ScreenSpaceShadows shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -78,14 +75,14 @@ ERROR: Shader Universal Render Pipeline/Lit shader is not supported on this GPU
 WARNING: Shader Unsupported: 'Universal Render Pipeline/Lit' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 0.698414 ms
+UnloadTime: 0.771483 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]: 26756 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [4.0 KB-8.0 KB]: 314 frames, [2.0 MB-4.0 MB]: 1 frames
       Initial Block Size 4.0 MB
       Current Block Size 4.0 MB
       Peak Allocated Bytes 3.6 MB
@@ -93,7 +90,7 @@ Memory Statistics:
     [ALLOC_TEMP_Loading.AsyncRead]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
-      Peak Allocated Bytes 256 B
+      Peak Allocated Bytes 168 B
       Overflow Count 0
     [ALLOC_TEMP_Loading.PreloadManager]
       Initial Block Size 256.0 KB
@@ -201,19 +198,19 @@ 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 231
     [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]: 26757 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 315 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 23.5 MB
+      Peak Allocated memory 21.9 MB
       Peak Large allocation bytes 16.0 MB
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [2.0 MB-4.0 MB]: 26757 frames
+      Peak usage frame count: [2.0 MB-4.0 MB]: 315 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 2.7 MB
@@ -245,13 +242,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.4 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 26756 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 314 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]: 26757 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 315 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 81.8 KB
@@ -263,13 +260,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.4 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [1.0 MB-2.0 MB]: 26756 frames, [16.0 MB-32.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 314 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]: 26756 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 314 frames, [2.0 MB-4.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 2.6 MB
@@ -281,13 +278,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.4 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 26757 frames
+      Peak usage frame count: [0-1.0 KB]: 315 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]: 26757 frames
+      Peak usage frame count: [4.0 KB-8.0 KB]: 315 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 7.3 KB

run_logs/timers.json

@@ -1,214 +1,68 @@
 {
     "name": "root",
-    "gauges": {
-        "Huggy.Policy.Entropy.mean": {
-            "value": 1.4024653434753418,
-            "min": 1.4024611711502075,
-            "max": 1.4246020317077637,
-            "count": 40
-        },
-        "Huggy.Policy.Entropy.sum": {
-            "value": 70180.765625,
-            "min": 68907.796875,
-            "max": 77627.234375,
-            "count": 40
-        },
-        "Huggy.Environment.EpisodeLength.mean": {
-            "value": 78.62101910828025,
-            "min": 78.62101910828025,
-            "max": 410.60655737704917,
-            "count": 40
-        },
-        "Huggy.Environment.EpisodeLength.sum": {
-            "value": 49374.0,
-            "min": 48868.0,
-            "max": 50094.0,
-            "count": 40
-        },
-        "Huggy.Step.mean": {
-            "value": 1999979.0,
-            "min": 49745.0,
-            "max": 1999979.0,
-            "count": 40
-        },
-        "Huggy.Step.sum": {
-            "value": 1999979.0,
-            "min": 49745.0,
-            "max": 1999979.0,
-            "count": 40
-        },
-        "Huggy.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 2.4192636013031006,
-            "min": -0.0025130566209554672,
-            "max": 2.501685380935669,
-            "count": 40
-        },
-        "Huggy.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 1519.297607421875,
-            "min": -0.3040798604488373,
-            "max": 1519.297607421875,
-            "count": 40
-        },
-        "Huggy.Environment.CumulativeReward.mean": {
-            "value": 3.7550513258405553,
-            "min": 1.7636375855808415,
-            "max": 3.941425032262921,
-            "count": 40
-        },
-        "Huggy.Environment.CumulativeReward.sum": {
-            "value": 2358.1722326278687,
-            "min": 213.40014785528183,
-            "max": 2358.1722326278687,
-            "count": 40
-        },
-        "Huggy.Policy.ExtrinsicReward.mean": {
-            "value": 3.7550513258405553,
-            "min": 1.7636375855808415,
-            "max": 3.941425032262921,
-            "count": 40
-        },
-        "Huggy.Policy.ExtrinsicReward.sum": {
-            "value": 2358.1722326278687,
-            "min": 213.40014785528183,
-            "max": 2358.1722326278687,
-            "count": 40
-        },
-        "Huggy.Losses.PolicyLoss.mean": {
-            "value": 0.019437453959512317,
-            "min": 0.013154487390177867,
-            "max": 0.020448919088812544,
-            "count": 40
-        },
-        "Huggy.Losses.PolicyLoss.sum": {
-            "value": 0.05831236187853695,
-            "min": 0.026308974780355734,
-            "max": 0.058845233608250655,
-            "count": 40
-        },
-        "Huggy.Losses.ValueLoss.mean": {
-            "value": 0.06192786188589202,
-            "min": 0.024715210683643817,
-            "max": 0.06192786188589202,
-            "count": 40
-        },
-        "Huggy.Losses.ValueLoss.sum": {
-            "value": 0.18578358565767605,
-            "min": 0.04943042136728763,
-            "max": 0.18578358565767605,
-            "count": 40
-        },
-        "Huggy.Policy.LearningRate.mean": {
-            "value": 3.5610988130000025e-06,
-            "min": 3.5610988130000025e-06,
-            "max": 0.00029535555154814995,
-            "count": 40
-        },
-        "Huggy.Policy.LearningRate.sum": {
-            "value": 1.0683296439000008e-05,
-            "min": 1.0683296439000008e-05,
-            "max": 0.00084436936854355,
-            "count": 40
-        },
-        "Huggy.Policy.Epsilon.mean": {
-            "value": 0.10118700000000001,
-            "min": 0.10118700000000001,
-            "max": 0.19845185000000004,
-            "count": 40
-        },
-        "Huggy.Policy.Epsilon.sum": {
-            "value": 0.303561,
-            "min": 0.20750249999999998,
-            "max": 0.58145645,
-            "count": 40
-        },
-        "Huggy.Policy.Beta.mean": {
-            "value": 6.923130000000008e-05,
-            "min": 6.923130000000008e-05,
-            "max": 0.004922747315000002,
-            "count": 40
-        },
-        "Huggy.Policy.Beta.sum": {
-            "value": 0.00020769390000000023,
-            "min": 0.00020769390000000023,
-            "max": 0.014074676854999999,
-            "count": 40
-        },
-        "Huggy.IsTraining.mean": {
-            "value": 1.0,
-            "min": 1.0,
-            "max": 1.0,
-            "count": 40
-        },
-        "Huggy.IsTraining.sum": {
-            "value": 1.0,
-            "min": 1.0,
-            "max": 1.0,
-            "count": 40
-        }
-    },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1751641922",
+        "start_time_seconds": "1751645366",
         "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics --resume",
         "mlagents_version": "1.2.0.dev0",
         "mlagents_envs_version": "1.2.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.7.1+cu126",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1751644275"
+        "end_time_seconds": "1751645394"
     },
-    "total": 2352.506928205,
+    "total": 27.54719525499968,
     "count": 1,
-    "self": 0.4473314219999338,
+    "self": 0.43896833599956153,
     "children": {
         "run_training.setup": {
-            "total": 0.02276233200018396,
+            "total": 0.020887939000203914,
             "count": 1,
-            "self": 0.02276233200018396
+            "self": 0.020887939000203914
         },
         "TrainerController.start_learning": {
-            "total": 2352.036834451,
+            "total": 27.087338979999913,
             "count": 1,
-            "self": 3.967809140126519,
+            "self": 0.047543480016429385,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 3.6092142850000073,
+                    "total": 2.1814104189998034,
                     "count": 1,
-                    "self": 3.6092142850000073
+                    "self": 2.1814104189998034
                 },
                 "TrainerController.advance": {
-                    "total": 2344.359346892873,
-                    "count": 232386,
-                    "self": 4.197441562889253,
+                    "total": 24.663333993983542,
+                    "count": 2646,
+                    "self": 0.04908445394903538,
                     "children": {
                         "env_step": {
-                            "total": 1865.6333278490324,
-                            "count": 232386,
-                            "self": 1475.9833234240145,
+                            "total": 22.66613306303134,
+                            "count": 2646,
+                            "self": 17.778558622032506,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 387.1712299789817,
-                                    "count": 232386,
-                                    "self": 14.84460483583348,
+                                    "total": 4.856940778993703,
+                                    "count": 2646,
+                                    "self": 0.1792201970338283,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 372.32662514314825,
-                                            "count": 222973,
-                                            "self": 372.32662514314825
+                                            "total": 4.677720581959875,
+                                            "count": 2624,
+                                            "self": 4.677720581959875
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 2.478774446036141,
-                                    "count": 232386,
+                                    "total": 0.030633662005129736,
+                                    "count": 2646,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2344.724542141909,
-                                            "count": 232386,
+                                            "total": 25.952712525024253,
+                                            "count": 2646,
                                             "is_parallel": true,
-                                            "self": 1139.8208920437528,
+                                            "self": 11.377316265031368,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -217,48 +71,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0008826670000416925,
+                                                            "total": 0.0008873100005075685,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.00023058299984768382,
+                                                            "self": 0.00028413700147211784,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0006520840001940087,
+                                                                    "total": 0.0006031729990354506,
                                                                     "count": 2,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0006520840001940087
+                                                                    "self": 0.0006031729990354506
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.02867772900003729,
+                                                            "total": 0.03509373900033097,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.00030823399993096245,
+                                                            "self": 0.0003337920015837881,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0002123190001839248,
+                                                                    "total": 0.0002063309993900475,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0002123190001839248
+                                                                    "self": 0.0002063309993900475
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.027495603000033952,
+                                                                    "total": 0.03387185900010081,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.027495603000033952
+                                                                    "self": 0.03387185900010081
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.000661572999888449,
+                                                                    "total": 0.0006817569992563222,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0001748820000102569,
+                                                                    "self": 0.00019762199917749967,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0004866909998781921,
+                                                                            "total": 0.0004841350000788225,
                                                                             "count": 2,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0004866909998781921
+                                                                            "self": 0.0004841350000788225
                                                                         }
                                                                     }
                                                                 }
@@ -267,34 +121,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1204.903650098156,
-                                                    "count": 232385,
+                                                    "total": 14.575396259992885,
+                                                    "count": 2645,
                                                     "is_parallel": true,
-                                                    "self": 36.41909589106672,
+                                                    "self": 0.4272878900537762,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 77.60592023796266,
-                                                            "count": 232385,
+                                                            "total": 0.9064299919627956,
+                                                            "count": 2645,
                                                             "is_parallel": true,
-                                                            "self": 77.60592023796266
+                                                            "self": 0.9064299919627956
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1006.1514981541054,
-                                                            "count": 232385,
+                                                            "total": 12.262378791991978,
+                                                            "count": 2645,
                                                             "is_parallel": true,
-                                                            "self": 1006.1514981541054
+                                                            "self": 12.262378791991978
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 84.72713581502126,
-                                                            "count": 232385,
+                                                            "total": 0.9792995859843359,
+                                                            "count": 2645,
                                                             "is_parallel": true,
-                                                            "self": 29.545321300937303,
+                                                            "self": 0.3288493579866554,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 55.18181451408395,
-                                                                    "count": 464770,
+                                                                    "total": 0.6504502279976805,
+                                                                    "count": 5290,
                                                                     "is_parallel": true,
-                                                                    "self": 55.18181451408395
+                                                                    "self": 0.6504502279976805
                                                                 }
                                                             }
                                                         }
@@ -307,31 +161,24 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 474.52857748095107,
-                            "count": 232386,
-                            "self": 6.176880183946423,
+                            "total": 1.9481164770031683,
+                            "count": 2646,
+                            "self": 0.06999894899217907,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 155.61212156900365,
-                                    "count": 232386,
-                                    "self": 154.4001984300039,
-                                    "children": {
-                                        "RLTrainer._checkpoint": {
-                                            "total": 1.2119231389997367,
-                                            "count": 10,
-                                            "self": 1.2119231389997367
-                                        }
-                                    }
+                                    "total": 1.018353674010541,
+                                    "count": 2646,
+                                    "self": 1.018353674010541
                                 },
                                 "_update_policy": {
-                                    "total": 312.739575728001,
-                                    "count": 97,
-                                    "self": 249.88159040599749,
+                                    "total": 0.8597638540004482,
+                                    "count": 1,
+                                    "self": 0.7145959150002454,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 62.857985322003515,
-                                            "count": 2910,
-                                            "self": 62.857985322003515
+                                            "total": 0.14516793900020275,
+                                            "count": 1,
+                                            "self": 0.14516793900020275
                                         }
                                     }
                                 }
@@ -339,20 +186,15 @@
                         }
                     }
                 },
-                "trainer_threads": {
-                    "total": 8.450001587334555e-07,
-                    "count": 1,
-                    "self": 8.450001587334555e-07
-                },
                 "TrainerController._save_models": {
-                    "total": 0.10046328799990079,
+                    "total": 0.19505108700013807,
                     "count": 1,
-                    "self": 0.0015098919998308702,
+                    "self": 0.004097906999959378,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.09895339600006992,
+                            "total": 0.1909531800001787,
                             "count": 1,
-                            "self": 0.09895339600006992
+                            "self": 0.1909531800001787
                         }
                     }
                 }

run_logs/training_status.json

@@ -99,15 +99,24 @@
                 "auxillary_file_paths": [
                     "results/Huggy2/Huggy/Huggy-2000059.pt"
                 ]
+            },
+            {
+                "steps": 2020885,
+                "file_path": "results/Huggy2/Huggy/Huggy-2020885.onnx",
+                "reward": null,
+                "creation_time": 1751645393.754694,
+                "auxillary_file_paths": [
+                    "results/Huggy2/Huggy/Huggy-2020885.pt"
+                ]
             }
         ],
         "final_checkpoint": {
-            "steps": 2000059,
+            "steps": 2020885,
             "file_path": "results/Huggy2/Huggy.onnx",
-            "reward": 3.943948956330617,
-            "creation_time": 1751644274.6419823,
+            "reward": null,
+            "creation_time": 1751645393.754694,
             "auxillary_file_paths": [
-                "results/Huggy2/Huggy/Huggy-2000059.pt"
+                "results/Huggy2/Huggy/Huggy-2020885.pt"
             ]
         }
     },