Hugging Face's logo

heesup
/
ppo-Huggy

Reinforcement Learning
ml-agents
TensorBoard
ONNX
Huggy
deep-reinforcement-learning
ML-Agents-Huggy
Model card Files
xet
Metrics Community
heesup commited on
Commit
3db446d
·
verified ·
1 Parent(s): 21bda3a

Huggy

Browse files
Files changed (14) hide show
  1. Huggy.onnx +3 -0
  2. Huggy/Huggy-0.onnx +3 -0
  3. Huggy/Huggy-0.pt +3 -0
  4. Huggy/Huggy-199765.onnx +3 -0
  5. Huggy/Huggy-199765.pt +3 -0
  6. Huggy/Huggy-280924.onnx +3 -0
  7. Huggy/Huggy-280924.pt +3 -0
  8. Huggy/checkpoint.pt +3 -0
  9. Huggy/events.out.tfevents.1759017592.50f022a51f47.5554.0 +3 -0
  10. config.json +1 -1
  11. configuration.yaml +1 -1
  12. run_logs/Player-0.log +14 -17
  13. run_logs/timers.json +228 -75
  14. run_logs/training_status.json +31 -0
Huggy.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4f6ef7d69c9f93fdda657b5d94d3f63061ca9a1852cba89073697cec3a3d790
3
+ size 2274020
Huggy/Huggy-0.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ca4ba6450a46cc5c1b9f4a6ce852bd3ad8bcfd0b0c4f980d7225f598bdb0842
3
+ size 2270042
Huggy/Huggy-0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc5ebce8b3c36f3ce35e1896b4ba58e5de47e5e9a20181c7200743873eb721a1
3
+ size 4508233
Huggy/Huggy-199765.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f7c72fac27f0fc747926cc6d9a1a28ee9bbccb84dc8f3112143f9c8ca985ac1
3
+ size 2274020
Huggy/Huggy-199765.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42ef6186e5a09fde0076e63d029b44ea1974cbcb028dc65bb5d90afabea4421c
3
+ size 13509859
Huggy/Huggy-280924.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4f6ef7d69c9f93fdda657b5d94d3f63061ca9a1852cba89073697cec3a3d790
3
+ size 2274020
Huggy/Huggy-280924.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa996a391f3636902c4511fc43d388126071b4f9b97424eb6c7db8e0265c2674
3
+ size 13509859
Huggy/checkpoint.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a64560c4d23e6009d216283149f01dee45b6e881ce081b65168b346e4333d36
3
+ size 13509685
Huggy/events.out.tfevents.1759017592.50f022a51f47.5554.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac7960a0d43dbf36aa467bca44dec7763f5e1da9466c52ac01d7269d367bd480
3
+ size 34745
config.json CHANGED
@@ -1 +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}
 
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": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -70,7 +70,7 @@ checkpoint_settings:
70
  initialize_from: null
71
  load_model: false
72
  resume: false
73
- force: false
74
  train_model: false
75
  inference: false
76
  results_dir: results
 
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
run_logs/Player-0.log CHANGED
@@ -2,9 +2,6 @@ Mono path[0] = '/content/ml-agents/trained-envs-executables/linux/Huggy/Huggy_Da
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
@@ -34,7 +31,7 @@ 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 0.092 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)
@@ -78,14 +75,14 @@ ERROR: Shader Universal Render Pipeline/Lit shader is not supported on this GPU
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: 0.801417 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]: 516 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
@@ -93,7 +90,7 @@ Memory Statistics:
93
  [ALLOC_TEMP_Loading.AsyncRead]
94
  Initial Block Size 64.0 KB
95
  Current Block Size 64.0 KB
96
- Peak Allocated Bytes 208 B
97
  Overflow Count 0
98
  [ALLOC_TEMP_Loading.PreloadManager]
99
  Initial Block Size 256.0 KB
@@ -201,22 +198,22 @@ Memory Statistics:
201
  Peak Allocated Bytes 0 B
202
  Overflow Count 0
203
  [ALLOC_DEFAULT] Dual Thread Allocator
204
- Peak main deferred allocation count 231
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]: 517 frames
211
  Requested Block Size 16.0 MB
212
  Peak Block count 1
213
  Peak Allocated memory 22.5 MB
214
  Peak Large allocation bytes 16.0 MB
215
  [ALLOC_DEFAULT_THREAD]
216
- Peak usage frame count: [1.0 MB-2.0 MB]: 516 frames, [2.0 MB-4.0 MB]: 1 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
@@ -245,13 +242,13 @@ Memory Statistics:
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]: 516 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]: 517 frames
255
  Requested Block Size 16.0 MB
256
  Peak Block count 1
257
  Peak Allocated memory 81.8 KB
@@ -263,13 +260,13 @@ Memory Statistics:
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]: 516 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]: 516 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
@@ -281,13 +278,13 @@ Memory Statistics:
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]: 517 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]: 517 frames
291
  Requested Block Size 2.0 MB
292
  Peak Block count 1
293
  Peak Allocated memory 7.3 KB
 
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
  Initialize engine version: 2021.3.14f1 (eee1884e7226)
6
  [Subsystems] Discovering subsystems at path /content/ml-agents/trained-envs-executables/linux/Huggy/Huggy_Data/UnitySubsystems
7
  Forcing GfxDevice: Null
 
31
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
32
  FMOD initialized on nosound output
33
  Begin MonoManager ReloadAssembly
34
+ - Completed reload, in 0.085 seconds
35
  ERROR: Shader Hidden/Universal Render Pipeline/Blit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
36
  ERROR: Shader Hidden/Universal Render Pipeline/CopyDepth shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
37
  ERROR: Shader Hidden/Universal Render Pipeline/ScreenSpaceShadows shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 
75
  WARNING: Shader Unsupported: 'Universal Render Pipeline/Lit' - All subshaders removed
76
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
77
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
78
+ UnloadTime: 0.819059 ms
79
  requesting resize 84 x 84
80
  Setting up 1 worker threads for Enlighten.
81
  Memory Statistics:
82
  [ALLOC_TEMP_TLS] TLS Allocator
83
  StackAllocators :
84
  [ALLOC_TEMP_MAIN]
85
+ Peak usage frame count: [4.0 KB-8.0 KB]: 3768 frames, [2.0 MB-4.0 MB]: 1 frames
86
  Initial Block Size 4.0 MB
87
  Current Block Size 4.0 MB
88
  Peak Allocated Bytes 3.6 MB
 
90
  [ALLOC_TEMP_Loading.AsyncRead]
91
  Initial Block Size 64.0 KB
92
  Current Block Size 64.0 KB
93
+ Peak Allocated Bytes 152 B
94
  Overflow Count 0
95
  [ALLOC_TEMP_Loading.PreloadManager]
96
  Initial Block Size 256.0 KB
 
198
  Peak Allocated Bytes 0 B
199
  Overflow Count 0
200
  [ALLOC_DEFAULT] Dual Thread Allocator
201
+ Peak main deferred allocation count 307
202
  [ALLOC_BUCKET]
203
  Large Block size 4.0 MB
204
  Used Block count 1
205
  Peak Allocated bytes 1.4 MB
206
  [ALLOC_DEFAULT_MAIN]
207
+ Peak usage frame count: [16.0 MB-32.0 MB]: 3769 frames
208
  Requested Block Size 16.0 MB
209
  Peak Block count 1
210
  Peak Allocated memory 22.5 MB
211
  Peak Large allocation bytes 16.0 MB
212
  [ALLOC_DEFAULT_THREAD]
213
+ Peak usage frame count: [1.0 MB-2.0 MB]: 3769 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
+ Peak Allocated memory 2.0 MB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_TEMP_JOB_1_FRAME]
219
  Initial Block Size 2.0 MB
 
242
  Used Block count 1
243
  Peak Allocated bytes 1.4 MB
244
  [ALLOC_GFX_MAIN]
245
+ Peak usage frame count: [32.0 KB-64.0 KB]: 3768 frames, [64.0 KB-128.0 KB]: 1 frames
246
  Requested Block Size 16.0 MB
247
  Peak Block count 1
248
  Peak Allocated memory 65.6 KB
249
  Peak Large allocation bytes 0 B
250
  [ALLOC_GFX_THREAD]
251
+ Peak usage frame count: [64.0 KB-128.0 KB]: 3769 frames
252
  Requested Block Size 16.0 MB
253
  Peak Block count 1
254
  Peak Allocated memory 81.8 KB
 
260
  Used Block count 1
261
  Peak Allocated bytes 1.4 MB
262
  [ALLOC_CACHEOBJECTS_MAIN]
263
+ Peak usage frame count: [1.0 MB-2.0 MB]: 3768 frames, [16.0 MB-32.0 MB]: 1 frames
264
  Requested Block Size 4.0 MB
265
  Peak Block count 2
266
  Peak Allocated memory 30.6 MB
267
  Peak Large allocation bytes 24.9 MB
268
  [ALLOC_CACHEOBJECTS_THREAD]
269
+ Peak usage frame count: [0.5 MB-1.0 MB]: 3768 frames, [2.0 MB-4.0 MB]: 1 frames
270
  Requested Block Size 4.0 MB
271
  Peak Block count 1
272
  Peak Allocated memory 2.6 MB
 
278
  Used Block count 1
279
  Peak Allocated bytes 1.4 MB
280
  [ALLOC_TYPETREE_MAIN]
281
+ Peak usage frame count: [0-1.0 KB]: 3769 frames
282
  Requested Block Size 2.0 MB
283
  Peak Block count 1
284
  Peak Allocated memory 1.0 KB
285
  Peak Large allocation bytes 0 B
286
  [ALLOC_TYPETREE_THREAD]
287
+ Peak usage frame count: [4.0 KB-8.0 KB]: 3769 frames
288
  Requested Block Size 2.0 MB
289
  Peak Block count 1
290
  Peak Allocated memory 7.3 KB
run_logs/timers.json CHANGED
@@ -1,68 +1,214 @@
1
  {
2
  "name": "root",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  "metadata": {
4
  "timer_format_version": "0.1.0",
5
- "start_time_seconds": "1759017461",
6
  "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
7
- "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics",
8
  "mlagents_version": "1.2.0.dev0",
9
  "mlagents_envs_version": "1.2.0.dev0",
10
  "communication_protocol_version": "1.5.0",
11
  "pytorch_version": "2.8.0+cu128",
12
  "numpy_version": "1.23.5",
13
- "end_time_seconds": "1759017509"
14
  },
15
- "total": 47.59818087100007,
16
  "count": 1,
17
- "self": 0.43157610299977023,
18
  "children": {
19
  "run_training.setup": {
20
- "total": 0.02581803500015667,
21
  "count": 1,
22
- "self": 0.02581803500015667
23
  },
24
  "TrainerController.start_learning": {
25
- "total": 47.14078673300014,
26
  "count": 1,
27
- "self": 0.0714562479927281,
28
  "children": {
29
  "TrainerController._reset_env": {
30
- "total": 2.877732353999818,
31
  "count": 1,
32
- "self": 2.877732353999818
33
  },
34
  "TrainerController.advance": {
35
- "total": 44.191105997007526,
36
- "count": 4340,
37
- "self": 0.07827579099398463,
38
  "children": {
39
  "env_step": {
40
- "total": 38.332932754006606,
41
- "count": 4340,
42
- "self": 30.649914948015066,
43
  "children": {
44
  "SubprocessEnvManager._take_step": {
45
- "total": 7.637091314998997,
46
- "count": 4340,
47
- "self": 0.2905148570050642,
48
  "children": {
49
  "TorchPolicy.evaluate": {
50
- "total": 7.346576457993933,
51
- "count": 4302,
52
- "self": 7.346576457993933
53
  }
54
  }
55
  },
56
  "workers": {
57
- "total": 0.04592649099254231,
58
- "count": 4339,
59
  "self": 0.0,
60
  "children": {
61
  "worker_root": {
62
- "total": 46.89172503898976,
63
- "count": 4339,
64
  "is_parallel": true,
65
- "self": 22.086364374988534,
66
  "children": {
67
  "run_training.setup": {
68
  "total": 0.0,
@@ -71,48 +217,48 @@
71
  "self": 0.0,
72
  "children": {
73
  "steps_from_proto": {
74
- "total": 0.0008962619999692834,
75
  "count": 1,
76
  "is_parallel": true,
77
- "self": 0.00024727400000301714,
78
  "children": {
79
  "_process_rank_one_or_two_observation": {
80
- "total": 0.0006489879999662662,
81
  "count": 2,
82
  "is_parallel": true,
83
- "self": 0.0006489879999662662
84
  }
85
  }
86
  },
87
  "UnityEnvironment.step": {
88
- "total": 0.029010463000076925,
89
  "count": 1,
90
  "is_parallel": true,
91
- "self": 0.000333369000145467,
92
  "children": {
93
  "UnityEnvironment._generate_step_input": {
94
- "total": 0.0002191300000049523,
95
  "count": 1,
96
  "is_parallel": true,
97
- "self": 0.0002191300000049523
98
  },
99
  "communicator.exchange": {
100
- "total": 0.027778825000041252,
101
  "count": 1,
102
  "is_parallel": true,
103
- "self": 0.027778825000041252
104
  },
105
  "steps_from_proto": {
106
- "total": 0.0006791389998852537,
107
  "count": 1,
108
  "is_parallel": true,
109
- "self": 0.00018708799984779034,
110
  "children": {
111
  "_process_rank_one_or_two_observation": {
112
- "total": 0.0004920510000374634,
113
  "count": 2,
114
  "is_parallel": true,
115
- "self": 0.0004920510000374634
116
  }
117
  }
118
  }
@@ -121,34 +267,34 @@
121
  }
122
  },
123
  "UnityEnvironment.step": {
124
- "total": 24.805360664001228,
125
- "count": 4338,
126
  "is_parallel": true,
127
- "self": 0.7112881179971282,
128
  "children": {
129
  "UnityEnvironment._generate_step_input": {
130
- "total": 1.5677409130025808,
131
- "count": 4338,
132
  "is_parallel": true,
133
- "self": 1.5677409130025808
134
  },
135
  "communicator.exchange": {
136
- "total": 20.86175371299987,
137
- "count": 4338,
138
  "is_parallel": true,
139
- "self": 20.86175371299987
140
  },
141
  "steps_from_proto": {
142
- "total": 1.6645779200016477,
143
- "count": 4338,
144
  "is_parallel": true,
145
- "self": 0.5951853140093135,
146
  "children": {
147
  "_process_rank_one_or_two_observation": {
148
- "total": 1.0693926059923342,
149
- "count": 8676,
150
  "is_parallel": true,
151
- "self": 1.0693926059923342
152
  }
153
  }
154
  }
@@ -161,24 +307,31 @@
161
  }
162
  },
163
  "trainer_advance": {
164
- "total": 5.779897452006935,
165
- "count": 4339,
166
- "self": 0.10767833700356277,
167
  "children": {
168
  "process_trajectory": {
169
- "total": 1.8609225900033834,
170
- "count": 4339,
171
- "self": 1.8609225900033834
 
 
 
 
 
 
 
172
  },
173
  "_update_policy": {
174
- "total": 3.811296524999989,
175
- "count": 1,
176
- "self": 2.8638117780001267,
177
  "children": {
178
  "TorchPPOOptimizer.update": {
179
- "total": 0.9474847469998622,
180
- "count": 30,
181
- "self": 0.9474847469998622
182
  }
183
  }
184
  }
@@ -187,19 +340,19 @@
187
  }
188
  },
189
  "trainer_threads": {
190
- "total": 1.1800000265793642e-06,
191
  "count": 1,
192
- "self": 1.1800000265793642e-06
193
  },
194
  "TrainerController._save_models": {
195
- "total": 0.0004909540000426205,
196
  "count": 1,
197
- "self": 2.207500006079499e-05,
198
  "children": {
199
  "RLTrainer._checkpoint": {
200
- "total": 0.00046887899998182547,
201
  "count": 1,
202
- "self": 0.00046887899998182547
203
  }
204
  }
205
  }
 
1
  {
2
  "name": "root",
3
+ "gauges": {
4
+ "Huggy.Policy.Entropy.mean": {
5
+ "value": 1.4285579919815063,
6
+ "min": 1.4195828437805176,
7
+ "max": 1.4285579919815063,
8
+ "count": 5
9
+ },
10
+ "Huggy.Policy.Entropy.sum": {
11
+ "value": 68270.7890625,
12
+ "min": 68270.7890625,
13
+ "max": 77347.390625,
14
+ "count": 5
15
+ },
16
+ "Huggy.Environment.EpisodeLength.mean": {
17
+ "value": 190.31800766283524,
18
+ "min": 190.31800766283524,
19
+ "max": 392.1015625,
20
+ "count": 5
21
+ },
22
+ "Huggy.Environment.EpisodeLength.sum": {
23
+ "value": 49673.0,
24
+ "min": 49553.0,
25
+ "max": 50189.0,
26
+ "count": 5
27
+ },
28
+ "Huggy.Step.mean": {
29
+ "value": 249836.0,
30
+ "min": 49660.0,
31
+ "max": 249836.0,
32
+ "count": 5
33
+ },
34
+ "Huggy.Step.sum": {
35
+ "value": 249836.0,
36
+ "min": 49660.0,
37
+ "max": 249836.0,
38
+ "count": 5
39
+ },
40
+ "Huggy.Policy.ExtrinsicValueEstimate.mean": {
41
+ "value": 1.2006275653839111,
42
+ "min": 0.14006608724594116,
43
+ "max": 1.2006275653839111,
44
+ "count": 5
45
+ },
46
+ "Huggy.Policy.ExtrinsicValueEstimate.sum": {
47
+ "value": 313.3638000488281,
48
+ "min": 17.788393020629883,
49
+ "max": 313.3638000488281,
50
+ "count": 5
51
+ },
52
+ "Huggy.Environment.CumulativeReward.mean": {
53
+ "value": 3.4439491732367156,
54
+ "min": 1.7494514952963731,
55
+ "max": 3.4439491732367156,
56
+ "count": 5
57
+ },
58
+ "Huggy.Environment.CumulativeReward.sum": {
59
+ "value": 898.8707342147827,
60
+ "min": 222.1803399026394,
61
+ "max": 898.8707342147827,
62
+ "count": 5
63
+ },
64
+ "Huggy.Policy.ExtrinsicReward.mean": {
65
+ "value": 3.4439491732367156,
66
+ "min": 1.7494514952963731,
67
+ "max": 3.4439491732367156,
68
+ "count": 5
69
+ },
70
+ "Huggy.Policy.ExtrinsicReward.sum": {
71
+ "value": 898.8707342147827,
72
+ "min": 222.1803399026394,
73
+ "max": 898.8707342147827,
74
+ "count": 5
75
+ },
76
+ "Huggy.Losses.PolicyLoss.mean": {
77
+ "value": 0.019505533616757022,
78
+ "min": 0.01520226820236227,
79
+ "max": 0.019505533616757022,
80
+ "count": 5
81
+ },
82
+ "Huggy.Losses.PolicyLoss.sum": {
83
+ "value": 0.058516600850271064,
84
+ "min": 0.03040453640472454,
85
+ "max": 0.058516600850271064,
86
+ "count": 5
87
+ },
88
+ "Huggy.Losses.ValueLoss.mean": {
89
+ "value": 0.027091392709149256,
90
+ "min": 0.022221150963256754,
91
+ "max": 0.03003601251790921,
92
+ "count": 5
93
+ },
94
+ "Huggy.Losses.ValueLoss.sum": {
95
+ "value": 0.08127417812744776,
96
+ "min": 0.04444230192651351,
97
+ "max": 0.08127417812744776,
98
+ "count": 5
99
+ },
100
+ "Huggy.Policy.LearningRate.mean": {
101
+ "value": 0.00026578251140583326,
102
+ "min": 0.00026578251140583326,
103
+ "max": 0.000295290976569675,
104
+ "count": 5
105
+ },
106
+ "Huggy.Policy.LearningRate.sum": {
107
+ "value": 0.0007973475342174998,
108
+ "min": 0.0005470279676573497,
109
+ "max": 0.0008437899187367,
110
+ "count": 5
111
+ },
112
+ "Huggy.Policy.Epsilon.mean": {
113
+ "value": 0.1885941666666667,
114
+ "min": 0.1885941666666667,
115
+ "max": 0.198430325,
116
+ "count": 5
117
+ },
118
+ "Huggy.Policy.Epsilon.sum": {
119
+ "value": 0.5657825000000001,
120
+ "min": 0.38234265,
121
+ "max": 0.5812633000000001,
122
+ "count": 5
123
+ },
124
+ "Huggy.Policy.Beta.mean": {
125
+ "value": 0.0044308489166666664,
126
+ "min": 0.0044308489166666664,
127
+ "max": 0.004921673217500001,
128
+ "count": 5
129
+ },
130
+ "Huggy.Policy.Beta.sum": {
131
+ "value": 0.013292546749999998,
132
+ "min": 0.009118898234999999,
133
+ "max": 0.014065038670000002,
134
+ "count": 5
135
+ },
136
+ "Huggy.IsTraining.mean": {
137
+ "value": 1.0,
138
+ "min": 1.0,
139
+ "max": 1.0,
140
+ "count": 5
141
+ },
142
+ "Huggy.IsTraining.sum": {
143
+ "value": 1.0,
144
+ "min": 1.0,
145
+ "max": 1.0,
146
+ "count": 5
147
+ }
148
+ },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1759017591",
152
  "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
153
+ "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics --force",
154
  "mlagents_version": "1.2.0.dev0",
155
  "mlagents_envs_version": "1.2.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.8.0+cu128",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1759017927"
160
  },
161
+ "total": 335.82432345200004,
162
  "count": 1,
163
+ "self": 0.25046890199996596,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.022188910000068063,
167
  "count": 1,
168
+ "self": 0.022188910000068063
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 335.55166564,
172
  "count": 1,
173
+ "self": 0.54147499097121,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 1.8028769180000381,
177
  "count": 1,
178
+ "self": 1.8028769180000381
179
  },
180
  "TrainerController.advance": {
181
+ "total": 333.0276004070288,
182
+ "count": 31900,
183
+ "self": 0.5482180550031899,
184
  "children": {
185
  "env_step": {
186
+ "total": 274.55972813401354,
187
+ "count": 31900,
188
+ "self": 219.86683344504445,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 54.349848729992345,
192
+ "count": 31900,
193
+ "self": 2.0505458109987558,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 52.29930291899359,
197
+ "count": 31405,
198
+ "self": 52.29930291899359
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.34304595897674517,
204
+ "count": 31900,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 333.8305134630134,
209
+ "count": 31900,
210
  "is_parallel": true,
211
+ "self": 155.44515551301993,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.0007772960000238527,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.00023474900012843136,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0005425469998954213,
227
  "count": 2,
228
  "is_parallel": true,
229
+ "self": 0.0005425469998954213
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.02926061500011201,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0002725100000589009,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.00021994200005792663,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.00021994200005792663
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.028066018000117765,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.028066018000117765
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0007021449998774187,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.00019123699985357234,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0005109080000238464,
259
  "count": 2,
260
  "is_parallel": true,
261
+ "self": 0.0005109080000238464
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 178.38535794999348,
271
+ "count": 31899,
272
  "is_parallel": true,
273
+ "self": 5.002250489953667,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 11.323774480025122,
277
+ "count": 31899,
278
  "is_parallel": true,
279
+ "self": 11.323774480025122
280
  },
281
  "communicator.exchange": {
282
+ "total": 150.08501977700257,
283
+ "count": 31899,
284
  "is_parallel": true,
285
+ "self": 150.08501977700257
286
  },
287
  "steps_from_proto": {
288
+ "total": 11.974313203012116,
289
+ "count": 31899,
290
  "is_parallel": true,
291
+ "self": 4.249789113014003,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 7.724524089998113,
295
+ "count": 63798,
296
  "is_parallel": true,
297
+ "self": 7.724524089998113
298
  }
299
  }
300
  }
 
307
  }
308
  },
309
  "trainer_advance": {
310
+ "total": 57.919654218012056,
311
+ "count": 31900,
312
+ "self": 0.8376185510117011,
313
  "children": {
314
  "process_trajectory": {
315
+ "total": 15.558618091999733,
316
+ "count": 31900,
317
+ "self": 15.40938006999977,
318
+ "children": {
319
+ "RLTrainer._checkpoint": {
320
+ "total": 0.14923802199996317,
321
+ "count": 1,
322
+ "self": 0.14923802199996317
323
+ }
324
+ }
325
  },
326
  "_update_policy": {
327
+ "total": 41.52341757500062,
328
+ "count": 13,
329
+ "self": 33.15757473300073,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
+ "total": 8.365842841999893,
333
+ "count": 390,
334
+ "self": 8.365842841999893
335
  }
336
  }
337
  }
 
340
  }
341
  },
342
  "trainer_threads": {
343
+ "total": 1.244000031874748e-06,
344
  "count": 1,
345
+ "self": 1.244000031874748e-06
346
  },
347
  "TrainerController._save_models": {
348
+ "total": 0.17971207999994476,
349
  "count": 1,
350
+ "self": 0.0037936119999812945,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
+ "total": 0.17591846799996347,
354
  "count": 1,
355
+ "self": 0.17591846799996347
356
  }
357
  }
358
  }
run_logs/training_status.json CHANGED
@@ -1,4 +1,35 @@
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "metadata": {
3
  "stats_format_version": "0.3.0",
4
  "mlagents_version": "1.2.0.dev0",
 
1
  {
2
+ "Huggy": {
3
+ "checkpoints": [
4
+ {
5
+ "steps": 199765,
6
+ "file_path": "results/Huggy2/Huggy/Huggy-199765.onnx",
7
+ "reward": 3.23468936877004,
8
+ "creation_time": 1759017831.4023836,
9
+ "auxillary_file_paths": [
10
+ "results/Huggy2/Huggy/Huggy-199765.pt"
11
+ ]
12
+ },
13
+ {
14
+ "steps": 280924,
15
+ "file_path": "results/Huggy2/Huggy/Huggy-280924.onnx",
16
+ "reward": 3.771424354825701,
17
+ "creation_time": 1759017927.3021183,
18
+ "auxillary_file_paths": [
19
+ "results/Huggy2/Huggy/Huggy-280924.pt"
20
+ ]
21
+ }
22
+ ],
23
+ "final_checkpoint": {
24
+ "steps": 280924,
25
+ "file_path": "results/Huggy2/Huggy.onnx",
26
+ "reward": 3.771424354825701,
27
+ "creation_time": 1759017927.3021183,
28
+ "auxillary_file_paths": [
29
+ "results/Huggy2/Huggy/Huggy-280924.pt"
30
+ ]
31
+ }
32
+ },
33
  "metadata": {
34
  "stats_format_version": "0.3.0",
35
  "mlagents_version": "1.2.0.dev0",