Hugging Face's logo

pomeloD
/
ppo-Huggy

Reinforcement Learning
ml-agents
TensorBoard
ONNX
Huggy
deep-reinforcement-learning
ML-Agents-Huggy
Model card Files
xet
 Metrics Community
pomeloD commited on
Commit
fa0459d
·
verified ·
1 Parent(s): a9859d6

Huggy

Browse files
Files changed (14) hide show
  1. Huggy.onnx +2 -2
  2. Huggy/Huggy-199914.onnx +3 -0
  3. Huggy/Huggy-199914.pt +3 -0
  4. Huggy/Huggy-399953.onnx +3 -0
  5. Huggy/Huggy-399953.pt +3 -0
  6. Huggy/Huggy-511223.onnx +3 -0
  7. Huggy/Huggy-511223.pt +3 -0
  8. Huggy/checkpoint.pt +2 -2
  9. Huggy/events.out.tfevents.1736928462.0779b60c6c76.9374.0 +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 +234 -69
  14. run_logs/training_status.json +31 -4
Huggy.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:923a4ee55be83dc7b2cb0ceeb8ec8fd6ce03e3d3dac8051f247ca85a84958028
3
- size 2270042
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2af87a3f671e0c19be46be589f58234c929930cb15cb4ba44f413ea3c9c2399c
3
+ size 2274020
Huggy/Huggy-199914.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f828d69965c0f28ed9581a9e9fc22c31762f57c0ab4eea72154d01e0a9e160d
3
+ size 2274020
Huggy/Huggy-199914.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:353263abd72fa7089614fd50f4963189b8e5d450154f6a426b0ad936c170d154
3
+ size 13509388
Huggy/Huggy-399953.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:081fe0e65a6996683cea00c5fc4c3916437e4f8ff06045af0d5ac9260e4f15c8
3
+ size 2274020
Huggy/Huggy-399953.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20af35a0abafec3696e0789a6f7609b8852c99893dd309cb766c851ef98ad059
3
+ size 13509388
Huggy/Huggy-511223.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2af87a3f671e0c19be46be589f58234c929930cb15cb4ba44f413ea3c9c2399c
3
+ size 2274020
Huggy/Huggy-511223.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:211ecb6ac3a94c95df3c42b44f7f4c2bf87e0fdb8e988b9de6c4ef41399aa591
3
+ size 13509388
Huggy/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:481db42246ca9476931ff257e8b23c9a498d5f2e100464f2455b440a99caa225
3
- size 4507874
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61f62b7c87aa6ed65ac8065190e4c0cccddda0c1d4edce7a8ad12b0fc3d2e3c1
3
+ size 13509218
Huggy/events.out.tfevents.1736928462.0779b60c6c76.9374.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1725c0db2f84cf63eed1db71df475ca67e586ce1a315e13e7f8faf7d7b627e90
3
+ size 60129
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"Huggy": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0004, "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": 0.0004, "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": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -69,7 +69,7 @@ checkpoint_settings:
69
  run_id: Huggy2
70
  initialize_from: null
71
  load_model: false
72
- resume: false
73
  force: false
74
  train_model: false
75
  inference: false
 
69
  run_id: Huggy2
70
  initialize_from: null
71
  load_model: false
72
+ resume: true
73
  force: false
74
  train_model: false
75
  inference: false
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
@@ -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: 0.964667 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]: 225 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 184 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 190
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]: 226 frames
211
  Requested Block Size 16.0 MB
212
  Peak Block count 1
213
- Peak Allocated memory 21.9 MB
214
  Peak Large allocation bytes 16.0 MB
215
  [ALLOC_DEFAULT_THREAD]
216
- Peak usage frame count: [2.0 MB-4.0 MB]: 226 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
- Peak Allocated memory 2.4 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]: 225 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]: 226 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]: 225 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]: 225 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]: 226 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]: 226 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
 
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: 0.830478 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]: 6719 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 136 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 115
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]: 6720 frames
208
  Requested Block Size 16.0 MB
209
  Peak Block count 1
210
+ Peak Allocated memory 22.0 MB
211
  Peak Large allocation bytes 16.0 MB
212
  [ALLOC_DEFAULT_THREAD]
213
+ Peak usage frame count: [2.0 MB-4.0 MB]: 6720 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
+ Peak Allocated memory 2.5 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]: 6719 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]: 6720 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]: 6719 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]: 6719 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]: 6720 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]: 6720 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": "1736928117",
6
  "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]",
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": "2.5.1+cu121",
12
  "numpy_version": "1.23.5",
13
- "end_time_seconds": "1736928143"
14
  },
15
- "total": 26.00519273100008,
16
  "count": 1,
17
- "self": 0.23372510300009708,
18
  "children": {
19
  "run_training.setup": {
20
- "total": 0.06391543700010516,
21
  "count": 1,
22
- "self": 0.06391543700010516
23
  },
24
  "TrainerController.start_learning": {
25
- "total": 25.707552190999877,
26
  "count": 1,
27
- "self": 0.04058519800673821,
28
  "children": {
29
  "TrainerController._reset_env": {
30
- "total": 5.362256291999984,
31
  "count": 1,
32
- "self": 5.362256291999984
33
  },
34
  "TrainerController.advance": {
35
- "total": 19.799804655993285,
36
- "count": 1894,
37
- "self": 0.041890538989264314,
38
  "children": {
39
  "env_step": {
40
- "total": 18.830560933995457,
41
- "count": 1894,
42
- "self": 14.490684486004284,
43
  "children": {
44
  "SubprocessEnvManager._take_step": {
45
- "total": 4.313145188991484,
46
- "count": 1894,
47
- "self": 0.14550498698986303,
48
  "children": {
49
  "TorchPolicy.evaluate": {
50
- "total": 4.167640202001621,
51
- "count": 1880,
52
- "self": 4.167640202001621
53
  }
54
  }
55
  },
56
  "workers": {
57
- "total": 0.02673125899968909,
58
- "count": 1893,
59
  "self": 0.0,
60
  "children": {
61
  "worker_root": {
62
- "total": 25.17333861599127,
63
- "count": 1893,
64
  "is_parallel": true,
65
- "self": 13.425136868988602,
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": 0.0009161190000668284,
75
  "count": 1,
76
  "is_parallel": true,
77
- "self": 0.0002806480001709133,
78
  "children": {
79
  "_process_rank_one_or_two_observation": {
80
- "total": 0.0006354709998959152,
81
  "count": 2,
82
  "is_parallel": true,
83
- "self": 0.0006354709998959152
84
  }
85
  }
86
  },
87
  "UnityEnvironment.step": {
88
- "total": 0.03593273000001318,
89
  "count": 1,
90
  "is_parallel": true,
91
- "self": 0.0004089830001703376,
92
  "children": {
93
  "UnityEnvironment._generate_step_input": {
94
- "total": 0.0002385599998433463,
95
  "count": 1,
96
  "is_parallel": true,
97
- "self": 0.0002385599998433463
98
  },
99
  "communicator.exchange": {
100
- "total": 0.03452021099997182,
101
  "count": 1,
102
  "is_parallel": true,
103
- "self": 0.03452021099997182
104
  },
105
  "steps_from_proto": {
106
- "total": 0.0007649760000276729,
107
  "count": 1,
108
  "is_parallel": true,
109
- "self": 0.000212540000120498,
110
  "children": {
111
  "_process_rank_one_or_two_observation": {
112
- "total": 0.0005524359999071748,
113
  "count": 2,
114
  "is_parallel": true,
115
- "self": 0.0005524359999071748
116
  }
117
  }
118
  }
@@ -121,34 +267,34 @@
121
  }
122
  },
123
  "UnityEnvironment.step": {
124
- "total": 11.748201747002668,
125
- "count": 1892,
126
  "is_parallel": true,
127
- "self": 0.3382018729985248,
128
  "children": {
129
  "UnityEnvironment._generate_step_input": {
130
- "total": 0.7872003349989427,
131
- "count": 1892,
132
  "is_parallel": true,
133
- "self": 0.7872003349989427
134
  },
135
  "communicator.exchange": {
136
- "total": 9.79712245199812,
137
- "count": 1892,
138
  "is_parallel": true,
139
- "self": 9.79712245199812
140
  },
141
  "steps_from_proto": {
142
- "total": 0.8256770870070795,
143
- "count": 1892,
144
  "is_parallel": true,
145
- "self": 0.3130288480024319,
146
  "children": {
147
  "_process_rank_one_or_two_observation": {
148
- "total": 0.5126482390046476,
149
- "count": 3784,
150
  "is_parallel": true,
151
- "self": 0.5126482390046476
152
  }
153
  }
154
  }
@@ -161,33 +307,52 @@
161
  }
162
  },
163
  "trainer_advance": {
164
- "total": 0.9273531830085631,
165
- "count": 1893,
166
- "self": 0.05093279800780692,
167
  "children": {
168
  "process_trajectory": {
169
- "total": 0.8764203850007561,
170
- "count": 1893,
171
- "self": 0.8764203850007561
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
172
  }
173
  }
174
  }
175
  }
176
  },
177
  "trainer_threads": {
178
- "total": 1.7509998997411458e-06,
179
  "count": 1,
180
- "self": 1.7509998997411458e-06
181
  },
182
  "TrainerController._save_models": {
183
- "total": 0.5049042939999708,
184
  "count": 1,
185
- "self": 0.005456499999809239,
186
  "children": {
187
  "RLTrainer._checkpoint": {
188
- "total": 0.4994477940001616,
189
  "count": 1,
190
- "self": 0.4994477940001616
191
  }
192
  }
193
  }
 
1
  {
2
  "name": "root",
3
+ "gauges": {
4
+ "Huggy.Policy.Entropy.mean": {
5
+ "value": 1.4190422296524048,
6
+ "min": 1.4190422296524048,
7
+ "max": 1.4250876903533936,
8
+ "count": 10
9
+ },
10
+ "Huggy.Policy.Entropy.sum": {
11
+ "value": 70891.09375,
12
+ "min": 63498.87109375,
13
+ "max": 72457.15625,
14
+ "count": 10
15
+ },
16
+ "Huggy.Environment.EpisodeLength.mean": {
17
+ "value": 113.47368421052632,
18
+ "min": 113.47368421052632,
19
+ "max": 389.59615384615387,
20
+ "count": 10
21
+ },
22
+ "Huggy.Environment.EpisodeLength.sum": {
23
+ "value": 49588.0,
24
+ "min": 40518.0,
25
+ "max": 50288.0,
26
+ "count": 10
27
+ },
28
+ "Huggy.Step.mean": {
29
+ "value": 499913.0,
30
+ "min": 49297.0,
31
+ "max": 499913.0,
32
+ "count": 10
33
+ },
34
+ "Huggy.Step.sum": {
35
+ "value": 499913.0,
36
+ "min": 49297.0,
37
+ "max": 499913.0,
38
+ "count": 10
39
+ },
40
+ "Huggy.Policy.ExtrinsicValueEstimate.mean": {
41
+ "value": 2.1788582801818848,
42
+ "min": 0.04198251664638519,
43
+ "max": 2.1788582801818848,
44
+ "count": 10
45
+ },
46
+ "Huggy.Policy.ExtrinsicValueEstimate.sum": {
47
+ "value": 952.1610717773438,
48
+ "min": 4.324199199676514,
49
+ "max": 952.1610717773438,
50
+ "count": 10
51
+ },
52
+ "Huggy.Environment.CumulativeReward.mean": {
53
+ "value": 3.830079616821058,
54
+ "min": 1.7462001202754605,
55
+ "max": 4.031612083813831,
56
+ "count": 10
57
+ },
58
+ "Huggy.Environment.CumulativeReward.sum": {
59
+ "value": 1673.7447925508022,
60
+ "min": 179.85861238837242,
61
+ "max": 1673.7447925508022,
62
+ "count": 10
63
+ },
64
+ "Huggy.Policy.ExtrinsicReward.mean": {
65
+ "value": 3.830079616821058,
66
+ "min": 1.7462001202754605,
67
+ "max": 4.031612083813831,
68
+ "count": 10
69
+ },
70
+ "Huggy.Policy.ExtrinsicReward.sum": {
71
+ "value": 1673.7447925508022,
72
+ "min": 179.85861238837242,
73
+ "max": 1673.7447925508022,
74
+ "count": 10
75
+ },
76
+ "Huggy.Losses.PolicyLoss.mean": {
77
+ "value": 0.017336433089803906,
78
+ "min": 0.014320030546009041,
79
+ "max": 0.020833562784052143,
80
+ "count": 10
81
+ },
82
+ "Huggy.Losses.PolicyLoss.sum": {
83
+ "value": 0.03467286617960781,
84
+ "min": 0.020833562784052143,
85
+ "max": 0.052766499834615385,
86
+ "count": 10
87
+ },
88
+ "Huggy.Losses.ValueLoss.mean": {
89
+ "value": 0.03799693329880635,
90
+ "min": 0.022262288505832353,
91
+ "max": 0.04358985579262177,
92
+ "count": 10
93
+ },
94
+ "Huggy.Losses.ValueLoss.sum": {
95
+ "value": 0.0759938665976127,
96
+ "min": 0.04358985579262177,
97
+ "max": 0.11701987441629172,
98
+ "count": 10
99
+ },
100
+ "Huggy.Policy.LearningRate.mean": {
101
+ "value": 0.000305149723712575,
102
+ "min": 0.000305149723712575,
103
+ "max": 0.00039399960150010013,
104
+ "count": 10
105
+ },
106
+ "Huggy.Policy.LearningRate.sum": {
107
+ "value": 0.00061029944742515,
108
+ "min": 0.00039399960150010013,
109
+ "max": 0.0011568816107796003,
110
+ "count": 10
111
+ },
112
+ "Huggy.Policy.Epsilon.mean": {
113
+ "value": 0.176287425,
114
+ "min": 0.176287425,
115
+ "max": 0.19849989999999995,
116
+ "count": 10
117
+ },
118
+ "Huggy.Policy.Epsilon.sum": {
119
+ "value": 0.35257485,
120
+ "min": 0.19849989999999995,
121
+ "max": 0.5892204000000001,
122
+ "count": 10
123
+ },
124
+ "Huggy.Policy.Beta.mean": {
125
+ "value": 0.003816742507500002,
126
+ "min": 0.003816742507500002,
127
+ "max": 0.004925145009999998,
128
+ "count": 10
129
+ },
130
+ "Huggy.Policy.Beta.sum": {
131
+ "value": 0.007633485015000004,
132
+ "min": 0.004925145009999998,
133
+ "max": 0.014462097960000002,
134
+ "count": 10
135
+ },
136
+ "Huggy.IsTraining.mean": {
137
+ "value": 1.0,
138
+ "min": 1.0,
139
+ "max": 1.0,
140
+ "count": 10
141
+ },
142
+ "Huggy.IsTraining.sum": {
143
+ "value": 1.0,
144
+ "min": 1.0,
145
+ "max": 1.0,
146
+ "count": 10
147
+ }
148
+ },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1736928461",
152
  "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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=Huggy2 --no-graphics --resume",
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": "2.5.1+cu121",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1736929151"
160
  },
161
+ "total": 690.1705263700001,
162
  "count": 1,
163
+ "self": 0.26756672200008325,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.060188609000306315,
167
  "count": 1,
168
+ "self": 0.060188609000306315
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 689.8427710389997,
172
  "count": 1,
173
+ "self": 1.2803969640613104,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 2.1697141549998378,
177
  "count": 1,
178
+ "self": 2.1697141549998378
179
  },
180
  "TrainerController.advance": {
181
+ "total": 686.1896143319382,
182
+ "count": 57447,
183
+ "self": 1.314082940940807,
184
  "children": {
185
  "env_step": {
186
+ "total": 556.8092361580402,
187
+ "count": 57447,
188
+ "self": 437.53755228413775,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 118.45669438204504,
192
+ "count": 57447,
193
+ "self": 4.305640458034759,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 114.15105392401028,
197
+ "count": 55994,
198
+ "self": 114.15105392401028
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.8149894918574319,
204
+ "count": 57446,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 687.6982669689774,
209
+ "count": 57446,
210
  "is_parallel": true,
211
+ "self": 331.744342757941,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.0010421269998914795,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.00030624500004705624,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0007358819998444233,
227
  "count": 2,
228
  "is_parallel": true,
229
+ "self": 0.0007358819998444233
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.030213659999844822,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.000411865999467409,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.00025261800010412117,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.00025261800010412117
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.02877581700022347,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.02877581700022347
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0007733590000498225,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.00021840700037500937,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0005549519996748131,
259
  "count": 2,
260
  "is_parallel": true,
261
+ "self": 0.0005549519996748131
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 355.95392421103634,
271
+ "count": 57445,
272
  "is_parallel": true,
273
+ "self": 10.389698987031807,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 23.767190306059092,
277
+ "count": 57445,
278
  "is_parallel": true,
279
+ "self": 23.767190306059092
280
  },
281
  "communicator.exchange": {
282
+ "total": 296.7199569759473,
283
+ "count": 57445,
284
  "is_parallel": true,
285
+ "self": 296.7199569759473
286
  },
287
  "steps_from_proto": {
288
+ "total": 25.07707794199814,
289
+ "count": 57445,
290
  "is_parallel": true,
291
+ "self": 9.550197338021462,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 15.526880603976679,
295
+ "count": 114890,
296
  "is_parallel": true,
297
+ "self": 15.526880603976679
298
  }
299
  }
300
  }
 
307
  }
308
  },
309
  "trainer_advance": {
310
+ "total": 128.06629523295715,
311
+ "count": 57446,
312
+ "self": 1.8541531419550665,
313
  "children": {
314
  "process_trajectory": {
315
+ "total": 38.21958914600373,
316
+ "count": 57446,
317
+ "self": 37.92409228000406,
318
+ "children": {
319
+ "RLTrainer._checkpoint": {
320
+ "total": 0.2954968659996666,
321
+ "count": 2,
322
+ "self": 0.2954968659996666
323
+ }
324
+ }
325
+ },
326
+ "_update_policy": {
327
+ "total": 87.99255294499835,
328
+ "count": 24,
329
+ "self": 70.93867519599189,
330
+ "children": {
331
+ "TorchPPOOptimizer.update": {
332
+ "total": 17.05387774900646,
333
+ "count": 720,
334
+ "self": 17.05387774900646
335
+ }
336
+ }
337
  }
338
  }
339
  }
340
  }
341
  },
342
  "trainer_threads": {
343
+ "total": 1.5650002751499414e-06,
344
  "count": 1,
345
+ "self": 1.5650002751499414e-06
346
  },
347
  "TrainerController._save_models": {
348
+ "total": 0.20304402300007496,
349
  "count": 1,
350
+ "self": 0.006738720999692305,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
+ "total": 0.19630530200038265,
354
  "count": 1,
355
+ "self": 0.19630530200038265
356
  }
357
  }
358
  }
run_logs/training_status.json CHANGED
@@ -9,15 +9,42 @@
9
  "auxillary_file_paths": [
10
  "results/Huggy2/Huggy/Huggy-9425.pt"
11
  ]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
12
  }
13
  ],
14
  "final_checkpoint": {
15
- "steps": 9425,
16
  "file_path": "results/Huggy2/Huggy.onnx",
17
- "reward": 1.6226544082164764,
18
- "creation_time": 1736928143.0003135,
19
  "auxillary_file_paths": [
20
- "results/Huggy2/Huggy/Huggy-9425.pt"
21
  ]
22
  }
23
  },
 
9
  "auxillary_file_paths": [
10
  "results/Huggy2/Huggy/Huggy-9425.pt"
11
  ]
12
+ },
13
+ {
14
+ "steps": 199914,
15
+ "file_path": "results/Huggy2/Huggy/Huggy-199914.onnx",
16
+ "reward": 3.5835559517145157,
17
+ "creation_time": 1736928723.2081444,
18
+ "auxillary_file_paths": [
19
+ "results/Huggy2/Huggy/Huggy-199914.pt"
20
+ ]
21
+ },
22
+ {
23
+ "steps": 399953,
24
+ "file_path": "results/Huggy2/Huggy/Huggy-399953.onnx",
25
+ "reward": 3.8444520432344627,
26
+ "creation_time": 1736928995.6214097,
27
+ "auxillary_file_paths": [
28
+ "results/Huggy2/Huggy/Huggy-399953.pt"
29
+ ]
30
+ },
31
+ {
32
+ "steps": 511223,
33
+ "file_path": "results/Huggy2/Huggy/Huggy-511223.onnx",
34
+ "reward": 3.6433242857456207,
35
+ "creation_time": 1736929151.431713,
36
+ "auxillary_file_paths": [
37
+ "results/Huggy2/Huggy/Huggy-511223.pt"
38
+ ]
39
  }
40
  ],
41
  "final_checkpoint": {
42
+ "steps": 511223,
43
  "file_path": "results/Huggy2/Huggy.onnx",
44
+ "reward": 3.6433242857456207,
45
+ "creation_time": 1736929151.431713,
46
  "auxillary_file_paths": [
47
+ "results/Huggy2/Huggy/Huggy-511223.pt"
48
  ]
49
  }
50
  },