devjwsong commited on
Commit
3e3e5e7
·
verified ·
1 Parent(s): 6b5e08f

Trained the first Huggy agent based on PPO.

Browse files
Huggy.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09ef6eb1c5ec9652e8f9cd2d281891c378b1139b7ab45f28704bbda80c9ae7a5
3
+ size 2273984
Huggy/Huggy-1199949.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e6e484af44e194f41e108e183861e742b91614440d7960ef3396c285d073671
3
+ size 2273984
Huggy/Huggy-1199949.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b812a69fad831585236bd7f0197c123a2e7f14b424d6a7bbeef73992db2ddec3
3
+ size 13509473
Huggy/Huggy-1399956.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70efea2b3781882d415372146b85706b37e03fc126766bcd3a9c75ac0e097755
3
+ size 2273984
Huggy/Huggy-1399956.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f015cc660393364ed9df6bb9a95e36d94f8f7b31133f72084f303ee111398c6f
3
+ size 13509473
Huggy/Huggy-1599989.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6730a78b89b54fda470b399823d0341df92ae21ff225e5edcd7b53b2c5b8500a
3
+ size 2273984
Huggy/Huggy-1599989.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a9f56216884f088db16af8d654fbdbd031dcd9b51c2069be6fcf1c05bc216c9
3
+ size 13509473
Huggy/Huggy-1799927.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bc820505ed6fa8049bed2f808f3e5df707017b98d1d91ba6394160768a291ba
3
+ size 2273984
Huggy/Huggy-1799927.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39dbfbcd48642dea3f532e7270f940d6db23340452d12a440d3a26b5c7eca743
3
+ size 13509473
Huggy/Huggy-199870.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b162684e98c70e863e173323b912e9babe90d6b872f0b520648cb35b3beac5e0
3
+ size 2273984
Huggy/Huggy-199870.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccfc6aecbab35bcbed58497563fbd77da78c0311311417c01359ed1f7a3d9440
3
+ size 13509388
Huggy/Huggy-1999989.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1aa240e79234554e027226b3b29eea32e6209d33c3296b0610aba61d31715813
3
+ size 2273984
Huggy/Huggy-1999989.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21fad2e98365388a4db346462dbb70627f11f16edaa5053d3ba1608a460ec251
3
+ size 13509473
Huggy/Huggy-2000026.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09ef6eb1c5ec9652e8f9cd2d281891c378b1139b7ab45f28704bbda80c9ae7a5
3
+ size 2273984
Huggy/Huggy-2000026.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a252b7f6938ee29aa65ec17e1d0ad0eb6dcbe68597998362a489fd7dc7660bc
3
+ size 13509473
Huggy/Huggy-399961.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4efbd28e55f9c2c56a2c0edf562cf5b3b18f9dfc6c10887dae931e9e8cc86403
3
+ size 2273984
Huggy/Huggy-399961.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2706f86a3f3edbea9498dab5cf2d9795cd3b492ff7198fc4142480375cb27833
3
+ size 13509388
Huggy/Huggy-599951.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4439166c058db77d6ecfbc9c14d2aa9152e49d84454fa3cb817e993e6288aa12
3
+ size 2273984
Huggy/Huggy-599951.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85de46439baa31f36ef2823dbdf91e53532715f14f5d184af3fae8e96249d013
3
+ size 13509388
Huggy/Huggy-799965.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a7674bfaca925a97e093202116d4f3beac7d63d150f9a2e43409330c8d339ca
3
+ size 2273984
Huggy/Huggy-799965.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13928fe086a31e805c2e753306a043cec203e5fa839fa071184505a345f22f7a
3
+ size 13509388
Huggy/Huggy-999974.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65f333696936156a892e0b707ed548c3fc880dafbf3e7c1be58edd0f946fd79c
3
+ size 2273984
Huggy/Huggy-999974.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:005ba13b1e3e834801b7a3485d14e786c3533d14bed1aeac9e9fa890bdd73af5
3
+ size 13509388
Huggy/checkpoint.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0f6c071880c453d4ca4fd39bed9e580856033b8c1e990d62c036e11299dad1a
3
+ size 13509218
Huggy/events.out.tfevents.1706752520.a548e0c4fd18.7678.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b3d5476d113b3ca689efe1ea9103d30947a724db89547681655509abed79ab3
3
+ size 378385
README.md ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: ml-agents
3
+ tags:
4
+ - Huggy
5
+ - deep-reinforcement-learning
6
+ - reinforcement-learning
7
+ - ML-Agents-Huggy
8
+ ---
9
+
10
+ # **ppo** Agent playing **Huggy**
11
+ This is a trained model of a **ppo** agent playing **Huggy**
12
+ using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
13
+
14
+ ## Usage (with ML-Agents)
15
+ The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
16
+
17
+ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
18
+ - A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
19
+ browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
20
+ - A *longer tutorial* to understand how works ML-Agents:
21
+ https://huggingface.co/learn/deep-rl-course/unit5/introduction
22
+
23
+ ### Resume the training
24
+ ```bash
25
+ mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
26
+ ```
27
+
28
+ ### Watch your Agent play
29
+ You can watch your agent **playing directly in your browser**
30
+
31
+ 1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
32
+ 2. Step 1: Find your model_id: devjwsong/ppo-Huggy
33
+ 3. Step 2: Select your *.nn /*.onnx file
34
+ 4. Click on Watch the agent play 👀
35
+
config.json ADDED
@@ -0,0 +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": "Huggy", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ default_settings: null
2
+ behaviors:
3
+ Huggy:
4
+ trainer_type: ppo
5
+ hyperparameters:
6
+ batch_size: 2048
7
+ buffer_size: 20480
8
+ learning_rate: 0.0003
9
+ beta: 0.005
10
+ epsilon: 0.2
11
+ lambd: 0.95
12
+ num_epoch: 3
13
+ shared_critic: false
14
+ learning_rate_schedule: linear
15
+ beta_schedule: linear
16
+ epsilon_schedule: linear
17
+ checkpoint_interval: 200000
18
+ network_settings:
19
+ normalize: true
20
+ hidden_units: 512
21
+ num_layers: 3
22
+ vis_encode_type: simple
23
+ memory: null
24
+ goal_conditioning_type: hyper
25
+ deterministic: false
26
+ reward_signals:
27
+ extrinsic:
28
+ gamma: 0.995
29
+ strength: 1.0
30
+ network_settings:
31
+ normalize: false
32
+ hidden_units: 128
33
+ num_layers: 2
34
+ vis_encode_type: simple
35
+ memory: null
36
+ goal_conditioning_type: hyper
37
+ deterministic: false
38
+ init_path: null
39
+ keep_checkpoints: 15
40
+ even_checkpoints: false
41
+ max_steps: 2000000
42
+ time_horizon: 1000
43
+ summary_freq: 50000
44
+ threaded: false
45
+ self_play: null
46
+ behavioral_cloning: null
47
+ env_settings:
48
+ env_path: ./trained-envs-executables/linux/Huggy/Huggy
49
+ env_args: null
50
+ base_port: 5005
51
+ num_envs: 1
52
+ num_areas: 1
53
+ timeout_wait: 60
54
+ seed: -1
55
+ max_lifetime_restarts: 10
56
+ restarts_rate_limit_n: 1
57
+ restarts_rate_limit_period_s: 60
58
+ engine_settings:
59
+ width: 84
60
+ height: 84
61
+ quality_level: 5
62
+ time_scale: 20
63
+ target_frame_rate: -1
64
+ capture_frame_rate: 60
65
+ no_graphics: true
66
+ no_graphics_monitor: false
67
+ environment_parameters: null
68
+ checkpoint_settings:
69
+ run_id: Huggy
70
+ initialize_from: null
71
+ load_model: false
72
+ resume: false
73
+ force: true
74
+ train_model: false
75
+ inference: false
76
+ results_dir: results
77
+ torch_settings:
78
+ device: null
79
+ debug: false
run_logs/Player-0.log ADDED
@@ -0,0 +1,294 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Mono path[0] = '/content/ml-agents/trained-envs-executables/linux/Huggy/Huggy_Data/Managed'
2
+ Mono config path = '/content/ml-agents/trained-envs-executables/linux/Huggy/Huggy_Data/MonoBleedingEdge/etc'
3
+ Preloaded 'lib_burst_generated.so'
4
+ Preloaded 'libgrpc_csharp_ext.x64.so'
5
+ PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face
6
+ PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face/Huggy
7
+ Unable to load player prefs
8
+ Initialize engine version: 2021.3.14f1 (eee1884e7226)
9
+ [Subsystems] Discovering subsystems at path /content/ml-agents/trained-envs-executables/linux/Huggy/Huggy_Data/UnitySubsystems
10
+ Forcing GfxDevice: Null
11
+ GfxDevice: creating device client; threaded=0; jobified=0
12
+ NullGfxDevice:
13
+ Version: NULL 1.0 [1.0]
14
+ Renderer: Null Device
15
+ Vendor: Unity Technologies
16
+ ALSA lib confmisc.c:855:(parse_card) cannot find card '0'
17
+ ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
18
+ ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
19
+ ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
20
+ ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
21
+ ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
22
+ ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
23
+ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
24
+ FMOD failed to initialize the output device.: "Error initializing output device. " (60)
25
+ Forced to initialize FMOD to to the device driver's system output rate 48000, this may impact performance and/or give inconsistent experiences compared to selected sample rate 48000
26
+ ALSA lib confmisc.c:855:(parse_card) cannot find card '0'
27
+ ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
28
+ ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
29
+ ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
30
+ ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
31
+ ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
32
+ ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
33
+ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
34
+ FMOD failed to initialize the output device.: "Error initializing output device. " (60)
35
+ FMOD initialized on nosound output
36
+ Begin MonoManager ReloadAssembly
37
+ - Completed reload, in 0.193 seconds
38
+ ERROR: Shader Hidden/Universal Render Pipeline/Blit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
39
+ ERROR: Shader Hidden/Universal Render Pipeline/CopyDepth shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
40
+ ERROR: Shader Hidden/Universal Render Pipeline/ScreenSpaceShadows shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
41
+ ERROR: Shader Hidden/Universal Render Pipeline/Sampling shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
42
+ ERROR: Shader Hidden/Universal Render Pipeline/LutBuilderLdr shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
43
+ ERROR: Shader Hidden/Universal Render Pipeline/LutBuilderHdr shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
44
+ ERROR: Shader Hidden/Universal Render Pipeline/UberPost shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
45
+ WARNING: Shader Unsupported: 'Hidden/Universal Render Pipeline/FallbackError' - All subshaders removed
46
+ WARNING: Shader Did you use #pragma only_renderers and omit this platform?
47
+ WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
48
+ ERROR: Shader Hidden/Universal Render Pipeline/FallbackError shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
49
+ WARNING: Shader Unsupported: 'Hidden/Universal Render Pipeline/FallbackError' - All subshaders removed
50
+ WARNING: Shader Did you use #pragma only_renderers and omit this platform?
51
+ WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
52
+ ERROR: Shader Hidden/Universal Render Pipeline/Stop NaN shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
53
+ ERROR: Shader Hidden/Universal Render Pipeline/SubpixelMorphologicalAntialiasing shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
54
+ ERROR: Shader Hidden/Universal Render Pipeline/GaussianDepthOfField shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
55
+ ERROR: Shader Hidden/Universal Render Pipeline/BokehDepthOfField shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
56
+ ERROR: Shader Hidden/Universal Render Pipeline/CameraMotionBlur shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
57
+ ERROR: Shader Hidden/Universal Render Pipeline/PaniniProjection shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
58
+ ERROR: Shader Hidden/Universal Render Pipeline/Bloom shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
59
+ ERROR: Shader Hidden/Universal Render Pipeline/FinalPost shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
60
+ WARNING: Shader Unsupported: 'Hidden/Universal Render Pipeline/StencilDeferred' - All subshaders removed
61
+ WARNING: Shader Did you use #pragma only_renderers and omit this platform?
62
+ WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
63
+ WARNING: Shader Unsupported: 'Hidden/Universal Render Pipeline/StencilDeferred' - All subshaders removed
64
+ WARNING: Shader Did you use #pragma only_renderers and omit this platform?
65
+ WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
66
+ ERROR: Shader Hidden/Universal Render Pipeline/LensFlareDataDriven shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
67
+ ERROR: Shader Hidden/Universal Render Pipeline/Scaling Setup shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
68
+ ERROR: Shader Hidden/Universal Render Pipeline/Edge Adaptive Spatial Upsampling shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
69
+ ERROR: Shader Hidden/Universal Render Pipeline/Debug/DebugReplacement shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
70
+ ERROR: Shader Hidden/kMotion/CameraMotionVectors shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
71
+ ERROR: Shader Hidden/kMotion/ObjectMotionVectors shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
72
+ ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
73
+ ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
74
+ WARNING: Shader Unsupported: 'Universal Render Pipeline/Lit' - All subshaders removed
75
+ WARNING: Shader Did you use #pragma only_renderers and omit this platform?
76
+ WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
77
+ ERROR: Shader Universal Render Pipeline/Lit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
78
+ WARNING: Shader Unsupported: 'Universal Render Pipeline/Lit' - All subshaders removed
79
+ WARNING: Shader Did you use #pragma only_renderers and omit this platform?
80
+ WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
81
+ UnloadTime: 1.065432 ms
82
+ requesting resize 84 x 84
83
+ Setting up 1 worker threads for Enlighten.
84
+ Memory Statistics:
85
+ [ALLOC_TEMP_TLS] TLS Allocator
86
+ StackAllocators :
87
+ [ALLOC_TEMP_MAIN]
88
+ Peak usage frame count: [4.0 KB-8.0 KB]: 26757 frames, [2.0 MB-4.0 MB]: 1 frames
89
+ Initial Block Size 4.0 MB
90
+ Current Block Size 4.0 MB
91
+ Peak Allocated Bytes 3.6 MB
92
+ Overflow Count 0
93
+ [ALLOC_TEMP_Loading.AsyncRead]
94
+ Initial Block Size 64.0 KB
95
+ Current Block Size 64.0 KB
96
+ Peak Allocated Bytes 128 B
97
+ Overflow Count 0
98
+ [ALLOC_TEMP_Loading.PreloadManager]
99
+ Initial Block Size 256.0 KB
100
+ Current Block Size 296.0 KB
101
+ Peak Allocated Bytes 211.5 KB
102
+ Overflow Count 4
103
+ [ALLOC_TEMP_Background Job.Worker 8]
104
+ Initial Block Size 32.0 KB
105
+ Current Block Size 32.0 KB
106
+ Peak Allocated Bytes 0 B
107
+ Overflow Count 0
108
+ [ALLOC_TEMP_Background Job.Worker 9]
109
+ Initial Block Size 32.0 KB
110
+ Current Block Size 32.0 KB
111
+ Peak Allocated Bytes 0 B
112
+ Overflow Count 0
113
+ [ALLOC_TEMP_Job.Worker 0]
114
+ Initial Block Size 256.0 KB
115
+ Current Block Size 256.0 KB
116
+ Peak Allocated Bytes 0 B
117
+ Overflow Count 0
118
+ [ALLOC_TEMP_Background Job.Worker 10]
119
+ Initial Block Size 32.0 KB
120
+ Current Block Size 32.0 KB
121
+ Peak Allocated Bytes 0 B
122
+ Overflow Count 0
123
+ [ALLOC_TEMP_Background Job.Worker 14]
124
+ Initial Block Size 32.0 KB
125
+ Current Block Size 32.0 KB
126
+ Peak Allocated Bytes 0 B
127
+ Overflow Count 0
128
+ [ALLOC_TEMP_Background Job.Worker 6]
129
+ Initial Block Size 32.0 KB
130
+ Current Block Size 32.0 KB
131
+ Peak Allocated Bytes 0 B
132
+ Overflow Count 0
133
+ [ALLOC_TEMP_Background Job.Worker 12]
134
+ Initial Block Size 32.0 KB
135
+ Current Block Size 32.0 KB
136
+ Peak Allocated Bytes 0 B
137
+ Overflow Count 0
138
+ [ALLOC_TEMP_EnlightenWorker]
139
+ Initial Block Size 64.0 KB
140
+ Current Block Size 64.0 KB
141
+ Peak Allocated Bytes 0 B
142
+ Overflow Count 0
143
+ [ALLOC_TEMP_Background Job.Worker 15]
144
+ Initial Block Size 32.0 KB
145
+ Current Block Size 32.0 KB
146
+ Peak Allocated Bytes 0 B
147
+ Overflow Count 0
148
+ [ALLOC_TEMP_Background Job.Worker 1]
149
+ Initial Block Size 32.0 KB
150
+ Current Block Size 32.0 KB
151
+ Peak Allocated Bytes 0 B
152
+ Overflow Count 0
153
+ [ALLOC_TEMP_Background Job.Worker 2]
154
+ Initial Block Size 32.0 KB
155
+ Current Block Size 32.0 KB
156
+ Peak Allocated Bytes 0 B
157
+ Overflow Count 0
158
+ [ALLOC_TEMP_Background Job.Worker 7]
159
+ Initial Block Size 32.0 KB
160
+ Current Block Size 32.0 KB
161
+ Peak Allocated Bytes 0 B
162
+ Overflow Count 0
163
+ [ALLOC_TEMP_AssetGarbageCollectorHelper]
164
+ Initial Block Size 64.0 KB
165
+ Current Block Size 64.0 KB
166
+ Peak Allocated Bytes 0 B
167
+ Overflow Count 0
168
+ [ALLOC_TEMP_Background Job.Worker 5]
169
+ Initial Block Size 32.0 KB
170
+ Current Block Size 32.0 KB
171
+ Peak Allocated Bytes 0 B
172
+ Overflow Count 0
173
+ [ALLOC_TEMP_Background Job.Worker 13]
174
+ Initial Block Size 32.0 KB
175
+ Current Block Size 32.0 KB
176
+ Peak Allocated Bytes 0 B
177
+ Overflow Count 0
178
+ [ALLOC_TEMP_Background Job.Worker 11]
179
+ Initial Block Size 32.0 KB
180
+ Current Block Size 32.0 KB
181
+ Peak Allocated Bytes 0 B
182
+ Overflow Count 0
183
+ [ALLOC_TEMP_Background Job.Worker 3]
184
+ Initial Block Size 32.0 KB
185
+ Current Block Size 32.0 KB
186
+ Peak Allocated Bytes 0 B
187
+ Overflow Count 0
188
+ [ALLOC_TEMP_Background Job.Worker 0]
189
+ Initial Block Size 32.0 KB
190
+ Current Block Size 32.0 KB
191
+ Peak Allocated Bytes 0 B
192
+ Overflow Count 0
193
+ [ALLOC_TEMP_Background Job.Worker 4]
194
+ Initial Block Size 32.0 KB
195
+ Current Block Size 32.0 KB
196
+ Peak Allocated Bytes 0 B
197
+ Overflow Count 0
198
+ [ALLOC_TEMP_BatchDeleteObjects]
199
+ Initial Block Size 64.0 KB
200
+ Current Block Size 64.0 KB
201
+ Peak Allocated Bytes 0 B
202
+ Overflow Count 0
203
+ [ALLOC_DEFAULT] Dual Thread Allocator
204
+ Peak main deferred allocation count 157
205
+ [ALLOC_BUCKET]
206
+ Large Block size 4.0 MB
207
+ Used Block count 1
208
+ Peak Allocated bytes 1.4 MB
209
+ [ALLOC_DEFAULT_MAIN]
210
+ Peak usage frame count: [16.0 MB-32.0 MB]: 26758 frames
211
+ Requested Block Size 16.0 MB
212
+ Peak Block count 1
213
+ Peak Allocated memory 23.9 MB
214
+ Peak Large allocation bytes 16.0 MB
215
+ [ALLOC_DEFAULT_THREAD]
216
+ Peak usage frame count: [1.0 MB-2.0 MB]: 6 frames, [2.0 MB-4.0 MB]: 26752 frames
217
+ Requested Block Size 16.0 MB
218
+ Peak Block count 1
219
+ Peak Allocated memory 2.2 MB
220
+ Peak Large allocation bytes 0 B
221
+ [ALLOC_TEMP_JOB_1_FRAME]
222
+ Initial Block Size 2.0 MB
223
+ Used Block Count 1
224
+ Overflow Count (too large) 0
225
+ Overflow Count (full) 0
226
+ [ALLOC_TEMP_JOB_2_FRAMES]
227
+ Initial Block Size 2.0 MB
228
+ Used Block Count 1
229
+ Overflow Count (too large) 0
230
+ Overflow Count (full) 0
231
+ [ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
232
+ Initial Block Size 2.0 MB
233
+ Used Block Count 2
234
+ Overflow Count (too large) 0
235
+ Overflow Count (full) 0
236
+ [ALLOC_TEMP_JOB_ASYNC (Background)]
237
+ Initial Block Size 1.0 MB
238
+ Used Block Count 3
239
+ Overflow Count (too large) 0
240
+ Overflow Count (full) 0
241
+ [ALLOC_GFX] Dual Thread Allocator
242
+ Peak main deferred allocation count 0
243
+ [ALLOC_BUCKET]
244
+ Large Block size 4.0 MB
245
+ Used Block count 1
246
+ Peak Allocated bytes 1.4 MB
247
+ [ALLOC_GFX_MAIN]
248
+ Peak usage frame count: [32.0 KB-64.0 KB]: 26757 frames, [64.0 KB-128.0 KB]: 1 frames
249
+ Requested Block Size 16.0 MB
250
+ Peak Block count 1
251
+ Peak Allocated memory 65.6 KB
252
+ Peak Large allocation bytes 0 B
253
+ [ALLOC_GFX_THREAD]
254
+ Peak usage frame count: [64.0 KB-128.0 KB]: 26758 frames
255
+ Requested Block Size 16.0 MB
256
+ Peak Block count 1
257
+ Peak Allocated memory 81.8 KB
258
+ Peak Large allocation bytes 0 B
259
+ [ALLOC_CACHEOBJECTS] Dual Thread Allocator
260
+ Peak main deferred allocation count 0
261
+ [ALLOC_BUCKET]
262
+ Large Block size 4.0 MB
263
+ Used Block count 1
264
+ Peak Allocated bytes 1.4 MB
265
+ [ALLOC_CACHEOBJECTS_MAIN]
266
+ Peak usage frame count: [1.0 MB-2.0 MB]: 26757 frames, [16.0 MB-32.0 MB]: 1 frames
267
+ Requested Block Size 4.0 MB
268
+ Peak Block count 2
269
+ Peak Allocated memory 30.6 MB
270
+ Peak Large allocation bytes 24.9 MB
271
+ [ALLOC_CACHEOBJECTS_THREAD]
272
+ Peak usage frame count: [0.5 MB-1.0 MB]: 26757 frames, [2.0 MB-4.0 MB]: 1 frames
273
+ Requested Block Size 4.0 MB
274
+ Peak Block count 1
275
+ Peak Allocated memory 2.6 MB
276
+ Peak Large allocation bytes 0 B
277
+ [ALLOC_TYPETREE] Dual Thread Allocator
278
+ Peak main deferred allocation count 0
279
+ [ALLOC_BUCKET]
280
+ Large Block size 4.0 MB
281
+ Used Block count 1
282
+ Peak Allocated bytes 1.4 MB
283
+ [ALLOC_TYPETREE_MAIN]
284
+ Peak usage frame count: [0-1.0 KB]: 26758 frames
285
+ Requested Block Size 2.0 MB
286
+ Peak Block count 1
287
+ Peak Allocated memory 1.0 KB
288
+ Peak Large allocation bytes 0 B
289
+ [ALLOC_TYPETREE_THREAD]
290
+ Peak usage frame count: [4.0 KB-8.0 KB]: 26758 frames
291
+ Requested Block Size 2.0 MB
292
+ Peak Block count 1
293
+ Peak Allocated memory 7.3 KB
294
+ Peak Large allocation bytes 0 B
run_logs/timers.json ADDED
@@ -0,0 +1,362 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "root",
3
+ "gauges": {
4
+ "Huggy.Policy.Entropy.mean": {
5
+ "value": 1.4027626514434814,
6
+ "min": 1.4027626514434814,
7
+ "max": 1.4292452335357666,
8
+ "count": 40
9
+ },
10
+ "Huggy.Policy.Entropy.sum": {
11
+ "value": 69474.625,
12
+ "min": 68290.25,
13
+ "max": 76629.34375,
14
+ "count": 40
15
+ },
16
+ "Huggy.Environment.EpisodeLength.mean": {
17
+ "value": 97.18886679920477,
18
+ "min": 82.14285714285714,
19
+ "max": 400.064,
20
+ "count": 40
21
+ },
22
+ "Huggy.Environment.EpisodeLength.sum": {
23
+ "value": 48886.0,
24
+ "min": 48867.0,
25
+ "max": 50139.0,
26
+ "count": 40
27
+ },
28
+ "Huggy.Step.mean": {
29
+ "value": 1999989.0,
30
+ "min": 49534.0,
31
+ "max": 1999989.0,
32
+ "count": 40
33
+ },
34
+ "Huggy.Step.sum": {
35
+ "value": 1999989.0,
36
+ "min": 49534.0,
37
+ "max": 1999989.0,
38
+ "count": 40
39
+ },
40
+ "Huggy.Policy.ExtrinsicValueEstimate.mean": {
41
+ "value": 2.463482618331909,
42
+ "min": 0.10775356739759445,
43
+ "max": 2.472022294998169,
44
+ "count": 40
45
+ },
46
+ "Huggy.Policy.ExtrinsicValueEstimate.sum": {
47
+ "value": 1239.1317138671875,
48
+ "min": 13.361442565917969,
49
+ "max": 1453.549072265625,
50
+ "count": 40
51
+ },
52
+ "Huggy.Environment.CumulativeReward.mean": {
53
+ "value": 3.7962356208569963,
54
+ "min": 1.8236981704831123,
55
+ "max": 3.913876270357504,
56
+ "count": 40
57
+ },
58
+ "Huggy.Environment.CumulativeReward.sum": {
59
+ "value": 1909.506517291069,
60
+ "min": 226.13857313990593,
61
+ "max": 2259.570232331753,
62
+ "count": 40
63
+ },
64
+ "Huggy.Policy.ExtrinsicReward.mean": {
65
+ "value": 3.7962356208569963,
66
+ "min": 1.8236981704831123,
67
+ "max": 3.913876270357504,
68
+ "count": 40
69
+ },
70
+ "Huggy.Policy.ExtrinsicReward.sum": {
71
+ "value": 1909.506517291069,
72
+ "min": 226.13857313990593,
73
+ "max": 2259.570232331753,
74
+ "count": 40
75
+ },
76
+ "Huggy.Losses.PolicyLoss.mean": {
77
+ "value": 0.019307712080383982,
78
+ "min": 0.013247698470756101,
79
+ "max": 0.02031691347947344,
80
+ "count": 40
81
+ },
82
+ "Huggy.Losses.PolicyLoss.sum": {
83
+ "value": 0.057923136241151946,
84
+ "min": 0.026495396941512202,
85
+ "max": 0.057923136241151946,
86
+ "count": 40
87
+ },
88
+ "Huggy.Losses.ValueLoss.mean": {
89
+ "value": 0.05089032749334971,
90
+ "min": 0.021669185192634662,
91
+ "max": 0.06362011147042115,
92
+ "count": 40
93
+ },
94
+ "Huggy.Losses.ValueLoss.sum": {
95
+ "value": 0.15267098248004912,
96
+ "min": 0.043338370385269324,
97
+ "max": 0.1800985146313906,
98
+ "count": 40
99
+ },
100
+ "Huggy.Policy.LearningRate.mean": {
101
+ "value": 3.3785488738499998e-06,
102
+ "min": 3.3785488738499998e-06,
103
+ "max": 0.0002953413015529,
104
+ "count": 40
105
+ },
106
+ "Huggy.Policy.LearningRate.sum": {
107
+ "value": 1.013564662155e-05,
108
+ "min": 1.013564662155e-05,
109
+ "max": 0.0008440375686541499,
110
+ "count": 40
111
+ },
112
+ "Huggy.Policy.Epsilon.mean": {
113
+ "value": 0.10112614999999998,
114
+ "min": 0.10112614999999998,
115
+ "max": 0.19844709999999993,
116
+ "count": 40
117
+ },
118
+ "Huggy.Policy.Epsilon.sum": {
119
+ "value": 0.30337844999999997,
120
+ "min": 0.20742484999999994,
121
+ "max": 0.5813458499999999,
122
+ "count": 40
123
+ },
124
+ "Huggy.Policy.Beta.mean": {
125
+ "value": 6.619488500000001e-05,
126
+ "min": 6.619488500000001e-05,
127
+ "max": 0.00492251029,
128
+ "count": 40
129
+ },
130
+ "Huggy.Policy.Beta.sum": {
131
+ "value": 0.00019858465500000003,
132
+ "min": 0.00019858465500000003,
133
+ "max": 0.014069157914999998,
134
+ "count": 40
135
+ },
136
+ "Huggy.IsTraining.mean": {
137
+ "value": 1.0,
138
+ "min": 1.0,
139
+ "max": 1.0,
140
+ "count": 40
141
+ },
142
+ "Huggy.IsTraining.sum": {
143
+ "value": 1.0,
144
+ "min": 1.0,
145
+ "max": 1.0,
146
+ "count": 40
147
+ }
148
+ },
149
+ "metadata": {
150
+ "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1706752519",
152
+ "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
153
+ "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics --force",
154
+ "mlagents_version": "1.1.0.dev0",
155
+ "mlagents_envs_version": "1.1.0.dev0",
156
+ "communication_protocol_version": "1.5.0",
157
+ "pytorch_version": "2.2.0+cu121",
158
+ "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1706755022"
160
+ },
161
+ "total": 2503.6983222589997,
162
+ "count": 1,
163
+ "self": 0.43430491700019047,
164
+ "children": {
165
+ "run_training.setup": {
166
+ "total": 0.0757888709999861,
167
+ "count": 1,
168
+ "self": 0.0757888709999861
169
+ },
170
+ "TrainerController.start_learning": {
171
+ "total": 2503.1882284709995,
172
+ "count": 1,
173
+ "self": 4.855238051993638,
174
+ "children": {
175
+ "TrainerController._reset_env": {
176
+ "total": 4.193587248000085,
177
+ "count": 1,
178
+ "self": 4.193587248000085
179
+ },
180
+ "TrainerController.advance": {
181
+ "total": 2494.027991920005,
182
+ "count": 232095,
183
+ "self": 4.9839214308181,
184
+ "children": {
185
+ "env_step": {
186
+ "total": 1996.6991066640403,
187
+ "count": 232095,
188
+ "self": 1652.7253726701188,
189
+ "children": {
190
+ "SubprocessEnvManager._take_step": {
191
+ "total": 340.753420066859,
192
+ "count": 232095,
193
+ "self": 17.425684225772557,
194
+ "children": {
195
+ "TorchPolicy.evaluate": {
196
+ "total": 323.32773584108645,
197
+ "count": 222978,
198
+ "self": 323.32773584108645
199
+ }
200
+ }
201
+ },
202
+ "workers": {
203
+ "total": 3.2203139270625343,
204
+ "count": 232095,
205
+ "self": 0.0,
206
+ "children": {
207
+ "worker_root": {
208
+ "total": 2495.6089489699184,
209
+ "count": 232095,
210
+ "is_parallel": true,
211
+ "self": 1148.5556726648247,
212
+ "children": {
213
+ "run_training.setup": {
214
+ "total": 0.0,
215
+ "count": 0,
216
+ "is_parallel": true,
217
+ "self": 0.0,
218
+ "children": {
219
+ "steps_from_proto": {
220
+ "total": 0.001050991000056456,
221
+ "count": 1,
222
+ "is_parallel": true,
223
+ "self": 0.0003031190001365758,
224
+ "children": {
225
+ "_process_rank_one_or_two_observation": {
226
+ "total": 0.0007478719999198802,
227
+ "count": 2,
228
+ "is_parallel": true,
229
+ "self": 0.0007478719999198802
230
+ }
231
+ }
232
+ },
233
+ "UnityEnvironment.step": {
234
+ "total": 0.03210064399991097,
235
+ "count": 1,
236
+ "is_parallel": true,
237
+ "self": 0.000319063999768332,
238
+ "children": {
239
+ "UnityEnvironment._generate_step_input": {
240
+ "total": 0.00022948300011194078,
241
+ "count": 1,
242
+ "is_parallel": true,
243
+ "self": 0.00022948300011194078
244
+ },
245
+ "communicator.exchange": {
246
+ "total": 0.030804017000036765,
247
+ "count": 1,
248
+ "is_parallel": true,
249
+ "self": 0.030804017000036765
250
+ },
251
+ "steps_from_proto": {
252
+ "total": 0.0007480799999939336,
253
+ "count": 1,
254
+ "is_parallel": true,
255
+ "self": 0.00018958399982693663,
256
+ "children": {
257
+ "_process_rank_one_or_two_observation": {
258
+ "total": 0.000558496000166997,
259
+ "count": 2,
260
+ "is_parallel": true,
261
+ "self": 0.000558496000166997
262
+ }
263
+ }
264
+ }
265
+ }
266
+ }
267
+ }
268
+ },
269
+ "UnityEnvironment.step": {
270
+ "total": 1347.0532763050937,
271
+ "count": 232094,
272
+ "is_parallel": true,
273
+ "self": 42.79424322732552,
274
+ "children": {
275
+ "UnityEnvironment._generate_step_input": {
276
+ "total": 85.4027541489802,
277
+ "count": 232094,
278
+ "is_parallel": true,
279
+ "self": 85.4027541489802
280
+ },
281
+ "communicator.exchange": {
282
+ "total": 1122.3223586119213,
283
+ "count": 232094,
284
+ "is_parallel": true,
285
+ "self": 1122.3223586119213
286
+ },
287
+ "steps_from_proto": {
288
+ "total": 96.53392031686667,
289
+ "count": 232094,
290
+ "is_parallel": true,
291
+ "self": 33.92946340492699,
292
+ "children": {
293
+ "_process_rank_one_or_two_observation": {
294
+ "total": 62.60445691193968,
295
+ "count": 464188,
296
+ "is_parallel": true,
297
+ "self": 62.60445691193968
298
+ }
299
+ }
300
+ }
301
+ }
302
+ }
303
+ }
304
+ }
305
+ }
306
+ }
307
+ }
308
+ },
309
+ "trainer_advance": {
310
+ "total": 492.3449638251468,
311
+ "count": 232095,
312
+ "self": 7.657434308235452,
313
+ "children": {
314
+ "process_trajectory": {
315
+ "total": 154.42602840791392,
316
+ "count": 232095,
317
+ "self": 153.21933608491327,
318
+ "children": {
319
+ "RLTrainer._checkpoint": {
320
+ "total": 1.2066923230006523,
321
+ "count": 10,
322
+ "self": 1.2066923230006523
323
+ }
324
+ }
325
+ },
326
+ "_update_policy": {
327
+ "total": 330.26150110899744,
328
+ "count": 97,
329
+ "self": 264.82815544999517,
330
+ "children": {
331
+ "TorchPPOOptimizer.update": {
332
+ "total": 65.43334565900227,
333
+ "count": 2910,
334
+ "self": 65.43334565900227
335
+ }
336
+ }
337
+ }
338
+ }
339
+ }
340
+ }
341
+ },
342
+ "trainer_threads": {
343
+ "total": 4.924000677419826e-06,
344
+ "count": 1,
345
+ "self": 4.924000677419826e-06
346
+ },
347
+ "TrainerController._save_models": {
348
+ "total": 0.1114063269997132,
349
+ "count": 1,
350
+ "self": 0.0019295629990665475,
351
+ "children": {
352
+ "RLTrainer._checkpoint": {
353
+ "total": 0.10947676400064665,
354
+ "count": 1,
355
+ "self": 0.10947676400064665
356
+ }
357
+ }
358
+ }
359
+ }
360
+ }
361
+ }
362
+ }
run_logs/training_status.json ADDED
@@ -0,0 +1,119 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "Huggy": {
3
+ "checkpoints": [
4
+ {
5
+ "steps": 199870,
6
+ "file_path": "results/Huggy/Huggy/Huggy-199870.onnx",
7
+ "reward": 3.239726749019346,
8
+ "creation_time": 1706752778.3750024,
9
+ "auxillary_file_paths": [
10
+ "results/Huggy/Huggy/Huggy-199870.pt"
11
+ ]
12
+ },
13
+ {
14
+ "steps": 399961,
15
+ "file_path": "results/Huggy/Huggy/Huggy-399961.onnx",
16
+ "reward": 3.953016260214019,
17
+ "creation_time": 1706753035.0462224,
18
+ "auxillary_file_paths": [
19
+ "results/Huggy/Huggy/Huggy-399961.pt"
20
+ ]
21
+ },
22
+ {
23
+ "steps": 599951,
24
+ "file_path": "results/Huggy/Huggy/Huggy-599951.onnx",
25
+ "reward": 4.068377274274826,
26
+ "creation_time": 1706753293.9180725,
27
+ "auxillary_file_paths": [
28
+ "results/Huggy/Huggy/Huggy-599951.pt"
29
+ ]
30
+ },
31
+ {
32
+ "steps": 799965,
33
+ "file_path": "results/Huggy/Huggy/Huggy-799965.onnx",
34
+ "reward": 4.229364575795185,
35
+ "creation_time": 1706753551.395465,
36
+ "auxillary_file_paths": [
37
+ "results/Huggy/Huggy/Huggy-799965.pt"
38
+ ]
39
+ },
40
+ {
41
+ "steps": 999974,
42
+ "file_path": "results/Huggy/Huggy/Huggy-999974.onnx",
43
+ "reward": 3.623603868054914,
44
+ "creation_time": 1706753809.868829,
45
+ "auxillary_file_paths": [
46
+ "results/Huggy/Huggy/Huggy-999974.pt"
47
+ ]
48
+ },
49
+ {
50
+ "steps": 1199949,
51
+ "file_path": "results/Huggy/Huggy/Huggy-1199949.onnx",
52
+ "reward": 3.3977674815965737,
53
+ "creation_time": 1706754068.7863774,
54
+ "auxillary_file_paths": [
55
+ "results/Huggy/Huggy/Huggy-1199949.pt"
56
+ ]
57
+ },
58
+ {
59
+ "steps": 1399956,
60
+ "file_path": "results/Huggy/Huggy/Huggy-1399956.onnx",
61
+ "reward": 3.8804917310789433,
62
+ "creation_time": 1706754324.0964925,
63
+ "auxillary_file_paths": [
64
+ "results/Huggy/Huggy/Huggy-1399956.pt"
65
+ ]
66
+ },
67
+ {
68
+ "steps": 1599989,
69
+ "file_path": "results/Huggy/Huggy/Huggy-1599989.onnx",
70
+ "reward": 3.6322373390197753,
71
+ "creation_time": 1706754558.731017,
72
+ "auxillary_file_paths": [
73
+ "results/Huggy/Huggy/Huggy-1599989.pt"
74
+ ]
75
+ },
76
+ {
77
+ "steps": 1799927,
78
+ "file_path": "results/Huggy/Huggy/Huggy-1799927.onnx",
79
+ "reward": 3.7924101460547672,
80
+ "creation_time": 1706754788.9555855,
81
+ "auxillary_file_paths": [
82
+ "results/Huggy/Huggy/Huggy-1799927.pt"
83
+ ]
84
+ },
85
+ {
86
+ "steps": 1999989,
87
+ "file_path": "results/Huggy/Huggy/Huggy-1999989.onnx",
88
+ "reward": 4.153508087863093,
89
+ "creation_time": 1706755022.321119,
90
+ "auxillary_file_paths": [
91
+ "results/Huggy/Huggy/Huggy-1999989.pt"
92
+ ]
93
+ },
94
+ {
95
+ "steps": 2000026,
96
+ "file_path": "results/Huggy/Huggy/Huggy-2000026.onnx",
97
+ "reward": 4.0362441291411715,
98
+ "creation_time": 1706755022.4348104,
99
+ "auxillary_file_paths": [
100
+ "results/Huggy/Huggy/Huggy-2000026.pt"
101
+ ]
102
+ }
103
+ ],
104
+ "final_checkpoint": {
105
+ "steps": 2000026,
106
+ "file_path": "results/Huggy/Huggy.onnx",
107
+ "reward": 4.0362441291411715,
108
+ "creation_time": 1706755022.4348104,
109
+ "auxillary_file_paths": [
110
+ "results/Huggy/Huggy/Huggy-2000026.pt"
111
+ ]
112
+ }
113
+ },
114
+ "metadata": {
115
+ "stats_format_version": "0.3.0",
116
+ "mlagents_version": "1.1.0.dev0",
117
+ "torch_version": "2.2.0+cu121"
118
+ }
119
+ }