Hugging Face's logo

mehmetyigitrl
/
ppo-SnowballTarget1

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files Metrics Community
mehmetyigitrl commited on
Commit
d948a70
·
1 Parent(s): 6cc37ae

Hyperparam Tuning

Browse files
Files changed (28) hide show
  1. SnowballTarget.onnx +1 -1
  2. SnowballTarget/SnowballTarget-149984.onnx +1 -1
  3. SnowballTarget/SnowballTarget-149984.pt +1 -1
  4. SnowballTarget/SnowballTarget-199984.onnx +1 -1
  5. SnowballTarget/SnowballTarget-199984.pt +1 -1
  6. SnowballTarget/SnowballTarget-200112.onnx +1 -1
  7. SnowballTarget/SnowballTarget-200112.pt +1 -1
  8. SnowballTarget/SnowballTarget-249944.onnx +3 -0
  9. SnowballTarget/SnowballTarget-249944.pt +3 -0
  10. SnowballTarget/SnowballTarget-299968.onnx +3 -0
  11. SnowballTarget/SnowballTarget-299968.pt +3 -0
  12. SnowballTarget/SnowballTarget-349992.onnx +3 -0
  13. SnowballTarget/SnowballTarget-349992.pt +3 -0
  14. SnowballTarget/SnowballTarget-399992.onnx +3 -0
  15. SnowballTarget/SnowballTarget-399992.pt +3 -0
  16. SnowballTarget/SnowballTarget-400312.onnx +3 -0
  17. SnowballTarget/SnowballTarget-400312.pt +3 -0
  18. SnowballTarget/SnowballTarget-49936.onnx +1 -1
  19. SnowballTarget/SnowballTarget-49936.pt +1 -1
  20. SnowballTarget/SnowballTarget-99960.onnx +1 -1
  21. SnowballTarget/SnowballTarget-99960.pt +1 -1
  22. SnowballTarget/checkpoint.pt +1 -1
  23. SnowballTarget/{events.out.tfevents.1679312661.0d5781064d81.1586.0 → events.out.tfevents.1679315042.0d5781064d81.11751.0} +2 -2
  24. config.json +1 -1
  25. configuration.yaml +6 -6
  26. run_logs/Player-0.log +15 -18
  27. run_logs/timers.json +167 -167
  28. run_logs/training_status.json +53 -17
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b355168b419be67f239d0bf0e9481972aee1d0e6f9d84ea3005c612727fca1d
3
  size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:457ede677e1b9ae6499e0522b8feee2fca02530723a5f4226421d7279c8a4104
3
  size 646532
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2cc0799b6c130154cd6e927974be4ef02c2a87655a2473e2af73cbcc6e0aa1ba
3
  size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37a7a6558d4a490dc0a776e9b8c9b8ec0dc3359a84086808866c3f02bb467de9
3
  size 646532
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e483b8c2029e2ba246f75b0b5c0f378c8d49c97a611eaeb1423ce8cfc0cda8ea
3
  size 3843968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05726f11b913b4b9ebec79fbce84fb96f40b1d301baaa5fb316e7623a757c99f
3
  size 3843968
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b355168b419be67f239d0bf0e9481972aee1d0e6f9d84ea3005c612727fca1d
3
  size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82bea435c8bb5c37f3eab870d4d456d945fa372dfd0f889cb0c9501f9b7c2fe6
3
  size 646532
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b21f6ae4497694c1670dc47b44fe84f51ea85ade502fe0c6190cae54e7509d4
3
  size 3843968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:996427178093415f4f0b59f1a86507de3b16f2ab3b57481433d54212601dd792
3
  size 3843968
SnowballTarget/SnowballTarget-200112.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b355168b419be67f239d0bf0e9481972aee1d0e6f9d84ea3005c612727fca1d
3
  size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f39cfbd28f11a7eff8e0a534bf18ad397a1880ffed7e43b0ce46c0dfd7b8ed78
3
  size 646532
SnowballTarget/SnowballTarget-200112.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a6bc5b4b875d8cfbb46b819c08cb415b9c397aae054315fe611272c51ab78ab
3
  size 3843968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93453909dd4685fc006991c49ca4da193869bf778e3235c6764f71c98a40b91d
3
  size 3843968
SnowballTarget/SnowballTarget-249944.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd30bb8a2fddc8ad81b0eeafe4247399e5a59d99e4e744de77c3b7b3004070c6
3
+ size 646532
SnowballTarget/SnowballTarget-249944.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5d9458c697f024cbd008b564678a373b1108fe90f896e3a16acf859e50c9a96
3
+ size 3843968
SnowballTarget/SnowballTarget-299968.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f17bd0617d1dbbf2703f52d82973b5b3676d2056f69476568e887d35e3edc6e9
3
+ size 646532
SnowballTarget/SnowballTarget-299968.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e669e7056fb7e27d15e21954985a6b29535a1510d242698583bf50b45476c30
3
+ size 3843968
SnowballTarget/SnowballTarget-349992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ebe9b458108491e12cab35befd3116ce22b856449365b314502f868b069b38b
3
+ size 646532
SnowballTarget/SnowballTarget-349992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76c52f862c18d1590cd48cc706cc64ff78b65c5ef902e2b19922da63b838e53f
3
+ size 3843968
SnowballTarget/SnowballTarget-399992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:457ede677e1b9ae6499e0522b8feee2fca02530723a5f4226421d7279c8a4104
3
+ size 646532
SnowballTarget/SnowballTarget-399992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78ee81a01c078286012989abd54417b2e030de62218e7db3204e899f1a1887cf
3
+ size 3843968
SnowballTarget/SnowballTarget-400312.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:457ede677e1b9ae6499e0522b8feee2fca02530723a5f4226421d7279c8a4104
3
+ size 646532
SnowballTarget/SnowballTarget-400312.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:743ac95bf646508f7fb90d433c61d62fab35bfe45003f207b7274aeaabdd5e65
3
+ size 3843968
SnowballTarget/SnowballTarget-49936.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:321fe1fbbb8b389302b4eb9fe1f6a742fa741fab43e98184d4962063669ac5c0
3
  size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:198cdbb8d778d87b5aeb683a001c374dbe8a8fdfc8462431ed2625477ca52fb7
3
  size 646532
SnowballTarget/SnowballTarget-49936.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:29a6a2fbe3401e9bf4a0c71daa147a71e43e1f97cfb84ec908b206df31fc9e94
3
  size 3843968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15449edb7c8601d55abf7deaca79eac3743adcc9d5c22eae83a219d07257d681
3
  size 3843968
SnowballTarget/SnowballTarget-99960.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fcd267f1092e7cfa840ac43c494dabcf394aa10ef164c0f2d9b125881d399b49
3
  size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1866a5dd9e54ccc08d825e618e52e228523d4b216837d5da313e36cc04bcaef7
3
  size 646532
SnowballTarget/SnowballTarget-99960.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ac3018963e3b7bfe485104cfc20867beddaea47dc9ad620031e426f12dfe248
3
  size 3843968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ef0657a84df8af8e63abc4620cbad7eab21979de5660a643c33ae2611c08a7b
3
  size 3843968
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a6bc5b4b875d8cfbb46b819c08cb415b9c397aae054315fe611272c51ab78ab
3
  size 3843968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:743ac95bf646508f7fb90d433c61d62fab35bfe45003f207b7274aeaabdd5e65
3
  size 3843968
SnowballTarget/{events.out.tfevents.1679312661.0d5781064d81.1586.0 → events.out.tfevents.1679315042.0d5781064d81.11751.0} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8690ac667c8c36f79b44cfec60d4cab7cee4d90cb95874afd251befb42c57bf2
3
- size 23569
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34cd62f1dad655d2139502fd4fcbe2ce73afc6b08d6dd50fb4f44d5b9d922b76
3
+ size 50638
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 64, "buffer_size": 2048, "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": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "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": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "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": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 64, "buffer_size": 4096, "learning_rate": 0.0002, "beta": 0.005, "epsilon": 0.15, "lambd": 0.94, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "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": 10, "even_checkpoints": false, "max_steps": 400000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "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
@@ -4,11 +4,11 @@ behaviors:
4
  trainer_type: ppo
5
  hyperparameters:
6
  batch_size: 64
7
- buffer_size: 2048
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
@@ -38,7 +38,7 @@ behaviors:
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
- max_steps: 200000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: true
@@ -68,7 +68,7 @@ checkpoint_settings:
68
  initialize_from: null
69
  load_model: false
70
  resume: false
71
- force: false
72
  train_model: false
73
  inference: false
74
  results_dir: results
 
4
  trainer_type: ppo
5
  hyperparameters:
6
  batch_size: 64
7
+ buffer_size: 4096
8
+ learning_rate: 0.0002
9
  beta: 0.005
10
+ epsilon: 0.15
11
+ lambd: 0.94
12
  num_epoch: 3
13
  shared_critic: false
14
  learning_rate_schedule: linear
 
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
+ max_steps: 400000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: true
 
68
  initialize_from: null
69
  load_model: false
70
  resume: false
71
+ force: true
72
  train_model: false
73
  inference: false
74
  results_dir: results
run_logs/Player-0.log CHANGED
@@ -2,9 +2,6 @@ Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarge
2
  Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_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/SnowballTarget
7
- Unable to load player prefs
8
  Initialize engine version: 2021.3.14f1 (eee1884e7226)
9
  [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
10
  Forcing GfxDevice: Null
@@ -34,7 +31,7 @@ ALSA lib pcm.c:2642:(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 0.122 seconds
38
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
39
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
40
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -45,7 +42,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
45
  WARNING: Shader Unsupported: 'Standard' - 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
- UnloadTime: 0.857879 ms
49
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
50
  requesting resize 84 x 84
51
  Setting up 1 worker threads for Enlighten.
@@ -53,7 +50,7 @@ Memory Statistics:
53
  [ALLOC_TEMP_TLS] TLS Allocator
54
  StackAllocators :
55
  [ALLOC_TEMP_MAIN]
56
- Peak usage frame count: [8.0 KB-16.0 KB]: 5370 frames, [16.0 KB-32.0 KB]: 91 frames, [2.0 MB-4.0 MB]: 1 frames
57
  Initial Block Size 4.0 MB
58
  Current Block Size 4.0 MB
59
  Peak Allocated Bytes 2.0 MB
@@ -169,22 +166,22 @@ Memory Statistics:
169
  Peak Allocated Bytes 0 B
170
  Overflow Count 0
171
  [ALLOC_DEFAULT] Dual Thread Allocator
172
- Peak main deferred allocation count 44
173
  [ALLOC_BUCKET]
174
  Large Block size 4.0 MB
175
  Used Block count 1
176
  Peak Allocated bytes 1.0 MB
177
  [ALLOC_DEFAULT_MAIN]
178
- Peak usage frame count: [4.0 MB-8.0 MB]: 5462 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
- Peak Allocated memory 6.6 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
- Peak usage frame count: [16.0 MB-32.0 MB]: 5462 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
- Peak Allocated memory 17.8 MB
188
  Peak Large allocation bytes 16.0 MB
189
  [ALLOC_TEMP_JOB_1_FRAME]
190
  Initial Block Size 2.0 MB
@@ -213,13 +210,13 @@ Memory Statistics:
213
  Used Block count 1
214
  Peak Allocated bytes 1.0 MB
215
  [ALLOC_GFX_MAIN]
216
- Peak usage frame count: [32.0 KB-64.0 KB]: 4822 frames, [64.0 KB-128.0 KB]: 640 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
- Peak Allocated memory 67.3 KB
220
  Peak Large allocation bytes 0 B
221
  [ALLOC_GFX_THREAD]
222
- Peak usage frame count: [32.0 KB-64.0 KB]: 5462 frames
223
  Requested Block Size 16.0 MB
224
  Peak Block count 1
225
  Peak Allocated memory 39.6 KB
@@ -231,13 +228,13 @@ Memory Statistics:
231
  Used Block count 1
232
  Peak Allocated bytes 1.0 MB
233
  [ALLOC_CACHEOBJECTS_MAIN]
234
- Peak usage frame count: [0.5 MB-1.0 MB]: 5462 frames
235
  Requested Block Size 4.0 MB
236
  Peak Block count 1
237
  Peak Allocated memory 0.6 MB
238
  Peak Large allocation bytes 0 B
239
  [ALLOC_CACHEOBJECTS_THREAD]
240
- Peak usage frame count: [0.5 MB-1.0 MB]: 5461 frames, [2.0 MB-4.0 MB]: 1 frames
241
  Requested Block Size 4.0 MB
242
  Peak Block count 1
243
  Peak Allocated memory 2.2 MB
@@ -249,13 +246,13 @@ Memory Statistics:
249
  Used Block count 1
250
  Peak Allocated bytes 1.0 MB
251
  [ALLOC_TYPETREE_MAIN]
252
- Peak usage frame count: [0-1.0 KB]: 5462 frames
253
  Requested Block Size 2.0 MB
254
  Peak Block count 1
255
  Peak Allocated memory 1.0 KB
256
  Peak Large allocation bytes 0 B
257
  [ALLOC_TYPETREE_THREAD]
258
- Peak usage frame count: [1.0 KB-2.0 KB]: 5462 frames
259
  Requested Block Size 2.0 MB
260
  Peak Block count 1
261
  Peak Allocated memory 1.7 KB
 
2
  Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_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/training-envs-executables/linux/SnowballTarget/SnowballTarget_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 0.078 seconds
35
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
36
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
37
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 
42
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
43
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
44
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
45
+ UnloadTime: 0.693089 ms
46
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
47
  requesting resize 84 x 84
48
  Setting up 1 worker threads for Enlighten.
 
50
  [ALLOC_TEMP_TLS] TLS Allocator
51
  StackAllocators :
52
  [ALLOC_TEMP_MAIN]
53
+ Peak usage frame count: [8.0 KB-16.0 KB]: 10739 frames, [16.0 KB-32.0 KB]: 182 frames, [2.0 MB-4.0 MB]: 1 frames
54
  Initial Block Size 4.0 MB
55
  Current Block Size 4.0 MB
56
  Peak Allocated Bytes 2.0 MB
 
166
  Peak Allocated Bytes 0 B
167
  Overflow Count 0
168
  [ALLOC_DEFAULT] Dual Thread Allocator
169
+ Peak main deferred allocation count 40
170
  [ALLOC_BUCKET]
171
  Large Block size 4.0 MB
172
  Used Block count 1
173
  Peak Allocated bytes 1.0 MB
174
  [ALLOC_DEFAULT_MAIN]
175
+ Peak usage frame count: [4.0 MB-8.0 MB]: 10916 frames, [8.0 MB-16.0 MB]: 6 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
+ Peak Allocated memory 9.1 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 10922 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
+ Peak Allocated memory 17.4 MB
185
  Peak Large allocation bytes 16.0 MB
186
  [ALLOC_TEMP_JOB_1_FRAME]
187
  Initial Block Size 2.0 MB
 
210
  Used Block count 1
211
  Peak Allocated bytes 1.0 MB
212
  [ALLOC_GFX_MAIN]
213
+ Peak usage frame count: [32.0 KB-64.0 KB]: 9906 frames, [64.0 KB-128.0 KB]: 1016 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
+ Peak Allocated memory 66.8 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
+ Peak usage frame count: [32.0 KB-64.0 KB]: 10922 frames
220
  Requested Block Size 16.0 MB
221
  Peak Block count 1
222
  Peak Allocated memory 39.6 KB
 
228
  Used Block count 1
229
  Peak Allocated bytes 1.0 MB
230
  [ALLOC_CACHEOBJECTS_MAIN]
231
+ Peak usage frame count: [0.5 MB-1.0 MB]: 10922 frames
232
  Requested Block Size 4.0 MB
233
  Peak Block count 1
234
  Peak Allocated memory 0.6 MB
235
  Peak Large allocation bytes 0 B
236
  [ALLOC_CACHEOBJECTS_THREAD]
237
+ Peak usage frame count: [0.5 MB-1.0 MB]: 10921 frames, [2.0 MB-4.0 MB]: 1 frames
238
  Requested Block Size 4.0 MB
239
  Peak Block count 1
240
  Peak Allocated memory 2.2 MB
 
246
  Used Block count 1
247
  Peak Allocated bytes 1.0 MB
248
  [ALLOC_TYPETREE_MAIN]
249
+ Peak usage frame count: [0-1.0 KB]: 10922 frames
250
  Requested Block Size 2.0 MB
251
  Peak Block count 1
252
  Peak Allocated memory 1.0 KB
253
  Peak Large allocation bytes 0 B
254
  [ALLOC_TYPETREE_THREAD]
255
+ Peak usage frame count: [1.0 KB-2.0 KB]: 10922 frames
256
  Requested Block Size 2.0 MB
257
  Peak Block count 1
258
  Peak Allocated memory 1.7 KB
run_logs/timers.json CHANGED
@@ -2,213 +2,213 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 0.9254744648933411,
6
- "min": 0.9210100769996643,
7
- "max": 2.8715083599090576,
8
- "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 8846.6103515625,
12
- "min": 8846.6103515625,
13
- "max": 29407.1171875,
14
- "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
17
- "value": 199984.0,
18
  "min": 9952.0,
19
- "max": 199984.0,
20
- "count": 20
21
  },
22
  "SnowballTarget.Step.sum": {
23
- "value": 199984.0,
24
  "min": 9952.0,
25
- "max": 199984.0,
26
- "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 13.158662796020508,
30
- "min": 0.30112528800964355,
31
- "max": 13.158662796020508,
32
- "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2565.939208984375,
36
- "min": 58.418304443359375,
37
- "max": 2656.4404296875,
38
- "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
- "count": 20
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
  "value": 8756.0,
48
  "min": 8756.0,
49
  "max": 10945.0,
50
- "count": 20
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
- "value": 0.09493090531891628,
54
- "min": 0.0917303287011805,
55
- "max": 0.10496558996123449,
56
- "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.3797236212756651,
60
- "min": 0.366921314804722,
61
- "max": 0.5159168399294882,
62
- "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.1769379121707935,
66
- "min": 0.11821952156971008,
67
- "max": 0.25664832625611156,
68
- "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.707751648683174,
72
- "min": 0.4728780862788403,
73
- "max": 1.256713553386576,
74
- "count": 20
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
- "value": 8.082097306000007e-06,
78
- "min": 8.082097306000007e-06,
79
- "max": 0.000291882002706,
80
- "count": 20
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
- "value": 3.232838922400003e-05,
84
- "min": 3.232838922400003e-05,
85
- "max": 0.00138516003828,
86
- "count": 20
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
- "value": 0.10269399999999997,
90
- "min": 0.10269399999999997,
91
- "max": 0.19729400000000002,
92
- "count": 20
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
- "value": 0.41077599999999986,
96
- "min": 0.41077599999999986,
97
- "max": 0.9617200000000001,
98
- "count": 20
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
- "value": 0.0001444306000000001,
102
- "min": 0.0001444306000000001,
103
- "max": 0.004864970599999999,
104
- "count": 20
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
107
- "value": 0.0005777224000000004,
108
- "min": 0.0005777224000000004,
109
- "max": 0.023089828000000003,
110
- "count": 20
111
- },
112
- "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 25.59090909090909,
114
- "min": 3.4545454545454546,
115
- "max": 25.90909090909091,
116
- "count": 20
117
- },
118
- "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1126.0,
120
- "min": 152.0,
121
- "max": 1425.0,
122
- "count": 20
123
- },
124
- "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 25.59090909090909,
126
- "min": 3.4545454545454546,
127
- "max": 25.90909090909091,
128
- "count": 20
129
- },
130
- "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1126.0,
132
- "min": 152.0,
133
- "max": 1425.0,
134
- "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
- "count": 20
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
- "count": 20
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1679312655",
152
  "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]",
153
- "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
154
  "mlagents_version": "0.31.0.dev0",
155
  "mlagents_envs_version": "0.31.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "1.11.0+cu102",
158
  "numpy_version": "1.21.2",
159
- "end_time_seconds": "1679313208"
160
  },
161
- "total": 553.800294531,
162
  "count": 1,
163
- "self": 0.37963741499993375,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.20251715799997783,
167
  "count": 1,
168
- "self": 0.20251715799997783
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 553.218139958,
172
  "count": 1,
173
- "self": 0.6084390209985031,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 9.38211925600001,
177
  "count": 1,
178
- "self": 9.38211925600001
179
  },
180
  "TrainerController.advance": {
181
- "total": 543.0945007440015,
182
- "count": 18204,
183
- "self": 0.32827639499896577,
184
  "children": {
185
  "env_step": {
186
- "total": 542.7662243490025,
187
- "count": 18204,
188
- "self": 409.56404554399217,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 132.88152099300703,
192
- "count": 18204,
193
- "self": 2.119319946997507,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 130.76220104600952,
197
- "count": 18204,
198
- "self": 130.76220104600952
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.32065781200333277,
204
- "count": 18204,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 551.5385710599917,
209
- "count": 18204,
210
  "is_parallel": true,
211
- "self": 283.90119897999205,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
@@ -217,48 +217,48 @@
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
- "total": 0.006117361000008259,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.004510919999972884,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0016064410000353746,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0016064410000353746
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.03934601000003113,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.00042673000001514083,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.00031293799997911265,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.00031293799997911265
244
  },
245
  "communicator.exchange": {
246
- "total": 0.03647594800003162,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.03647594800003162
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0021303940000052535,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.0004666250000582295,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.001663768999947024,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.001663768999947024
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 267.63737207999964,
271
- "count": 18203,
272
  "is_parallel": true,
273
- "self": 10.329086845980157,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 5.903030901998989,
277
- "count": 18203,
278
  "is_parallel": true,
279
- "self": 5.903030901998989
280
  },
281
  "communicator.exchange": {
282
- "total": 215.8796595980154,
283
- "count": 18203,
284
  "is_parallel": true,
285
- "self": 215.8796595980154
286
  },
287
  "steps_from_proto": {
288
- "total": 35.5255947340051,
289
- "count": 18203,
290
  "is_parallel": true,
291
- "self": 7.40056853698303,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 28.125026197022066,
295
- "count": 182030,
296
  "is_parallel": true,
297
- "self": 28.125026197022066
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 0.00011835600002996216,
313
  "count": 1,
314
- "self": 0.00011835600002996216,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,36 +320,36 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 538.8789372869855,
324
- "count": 454351,
325
  "is_parallel": true,
326
- "self": 11.78341512097461,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 278.90736762301094,
330
- "count": 454351,
331
  "is_parallel": true,
332
- "self": 277.654547325011,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
- "total": 1.2528202979999605,
336
- "count": 4,
337
  "is_parallel": true,
338
- "self": 1.2528202979999605
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
- "total": 248.188154543,
344
  "count": 90,
345
  "is_parallel": true,
346
- "self": 68.89862918799355,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
- "total": 179.28952535500645,
350
- "count": 9177,
351
  "is_parallel": true,
352
- "self": 179.28952535500645
353
  }
354
  }
355
  }
@@ -360,14 +360,14 @@
360
  }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.13296258100001523,
364
  "count": 1,
365
- "self": 0.0008671670000239828,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.13209541399999125,
369
  "count": 1,
370
- "self": 0.13209541399999125
371
  }
372
  }
373
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 1.0179998874664307,
6
+ "min": 1.0179998874664307,
7
+ "max": 2.8816232681274414,
8
+ "count": 40
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 10402.94140625,
12
+ "min": 9812.6806640625,
13
+ "max": 29669.193359375,
14
+ "count": 40
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 399992.0,
18
  "min": 9952.0,
19
+ "max": 399992.0,
20
+ "count": 40
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 399992.0,
24
  "min": 9952.0,
25
+ "max": 399992.0,
26
+ "count": 40
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 13.216809272766113,
30
+ "min": 0.1776331067085266,
31
+ "max": 13.216809272766113,
32
+ "count": 40
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2577.27783203125,
36
+ "min": 34.46082305908203,
37
+ "max": 2697.09765625,
38
+ "count": 40
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
+ "count": 40
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
  "value": 8756.0,
48
  "min": 8756.0,
49
  "max": 10945.0,
50
+ "count": 40
51
+ },
52
+ "SnowballTarget.Environment.CumulativeReward.mean": {
53
+ "value": 26.454545454545453,
54
+ "min": 2.659090909090909,
55
+ "max": 26.454545454545453,
56
+ "count": 40
57
+ },
58
+ "SnowballTarget.Environment.CumulativeReward.sum": {
59
+ "value": 1164.0,
60
+ "min": 117.0,
61
+ "max": 1447.0,
62
+ "count": 40
63
+ },
64
+ "SnowballTarget.Policy.ExtrinsicReward.mean": {
65
+ "value": 26.454545454545453,
66
+ "min": 2.659090909090909,
67
+ "max": 26.454545454545453,
68
+ "count": 40
69
+ },
70
+ "SnowballTarget.Policy.ExtrinsicReward.sum": {
71
+ "value": 1164.0,
72
+ "min": 117.0,
73
+ "max": 1447.0,
74
+ "count": 40
75
  },
76
  "SnowballTarget.Losses.PolicyLoss.mean": {
77
+ "value": 0.10018987917040553,
78
+ "min": 0.08981524619529783,
79
+ "max": 0.10747867187741328,
80
+ "count": 40
81
  },
82
  "SnowballTarget.Losses.PolicyLoss.sum": {
83
+ "value": 0.20037975834081106,
84
+ "min": 0.17963049239059567,
85
+ "max": 0.31710270352892156,
86
+ "count": 40
87
  },
88
  "SnowballTarget.Losses.ValueLoss.mean": {
89
+ "value": 0.1706300188111616,
90
+ "min": 0.07835130111641696,
91
+ "max": 0.2309948849716997,
92
+ "count": 40
93
  },
94
  "SnowballTarget.Losses.ValueLoss.sum": {
95
+ "value": 0.3412600376223232,
96
+ "min": 0.15670260223283392,
97
+ "max": 0.6929846549150991,
98
+ "count": 40
99
  },
100
  "SnowballTarget.Policy.LearningRate.mean": {
101
+ "value": 3.1440984280000024e-06,
102
+ "min": 3.1440984280000024e-06,
103
+ "max": 0.00019674400162800003,
104
+ "count": 40
105
  },
106
  "SnowballTarget.Policy.LearningRate.sum": {
107
+ "value": 6.288196856000005e-06,
108
+ "min": 6.288196856000005e-06,
109
+ "max": 0.0005473320263340001,
110
+ "count": 40
111
  },
112
  "SnowballTarget.Policy.Epsilon.mean": {
113
+ "value": 0.10078600000000001,
114
+ "min": 0.10078600000000001,
115
+ "max": 0.14918600000000004,
116
+ "count": 40
117
  },
118
  "SnowballTarget.Policy.Epsilon.sum": {
119
+ "value": 0.20157200000000003,
120
+ "min": 0.20157200000000003,
121
+ "max": 0.4368329999999999,
122
+ "count": 40
123
  },
124
  "SnowballTarget.Policy.Beta.mean": {
125
+ "value": 8.844280000000007e-05,
126
+ "min": 8.844280000000007e-05,
127
+ "max": 0.0049187627999999995,
128
+ "count": 40
129
  },
130
  "SnowballTarget.Policy.Beta.sum": {
131
+ "value": 0.00017688560000000015,
132
+ "min": 0.00017688560000000015,
133
+ "max": 0.0136859334,
134
+ "count": 40
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
+ "count": 40
141
  },
142
  "SnowballTarget.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": "1679315038",
152
  "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]",
153
+ "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force",
154
  "mlagents_version": "0.31.0.dev0",
155
  "mlagents_envs_version": "0.31.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "1.11.0+cu102",
158
  "numpy_version": "1.21.2",
159
+ "end_time_seconds": "1679316065"
160
  },
161
+ "total": 1026.9627269110001,
162
  "count": 1,
163
+ "self": 0.42386767400012104,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.1020579760001965,
167
  "count": 1,
168
+ "self": 0.1020579760001965
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 1026.4368012609998,
172
  "count": 1,
173
+ "self": 1.0849357309398329,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 6.8931366229999185,
177
  "count": 1,
178
+ "self": 6.8931366229999185
179
  },
180
  "TrainerController.advance": {
181
+ "total": 1018.32177950206,
182
+ "count": 36406,
183
+ "self": 0.5312980311036881,
184
  "children": {
185
  "env_step": {
186
+ "total": 1017.7904814709564,
187
+ "count": 36406,
188
+ "self": 783.8077283260764,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 233.44474938392204,
192
+ "count": 36406,
193
+ "self": 4.75262694893172,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 228.69212243499032,
197
+ "count": 36406,
198
+ "self": 228.69212243499032
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.5380037609579631,
204
+ "count": 36406,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 1023.3385514439997,
209
+ "count": 36406,
210
  "is_parallel": true,
211
+ "self": 539.2328077109983,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.002272190999974555,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0007691100008742069,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.001503080999100348,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.001503080999100348
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.03662252900039675,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0005368560005081235,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0004355089999990014,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0004355089999990014
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.033707068000239815,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.033707068000239815
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0019430959996498132,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0003960139997616352,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.001547081999888178,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.001547081999888178
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 484.1057437330014,
271
+ "count": 36405,
272
  "is_parallel": true,
273
+ "self": 19.045695103150592,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 10.679216891955548,
277
+ "count": 36405,
278
  "is_parallel": true,
279
+ "self": 10.679216891955548
280
  },
281
  "communicator.exchange": {
282
+ "total": 390.0623916369723,
283
+ "count": 36405,
284
  "is_parallel": true,
285
+ "self": 390.0623916369723
286
  },
287
  "steps_from_proto": {
288
+ "total": 64.318440100923,
289
+ "count": 36405,
290
  "is_parallel": true,
291
+ "self": 12.715820958037057,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 51.60261914288594,
295
+ "count": 364050,
296
  "is_parallel": true,
297
+ "self": 51.60261914288594
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 0.00020376600014060386,
313
  "count": 1,
314
+ "self": 0.00020376600014060386,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 1009.1185825531134,
324
+ "count": 1037330,
325
  "is_parallel": true,
326
+ "self": 26.12768551106683,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 620.3641213020469,
330
+ "count": 1037330,
331
  "is_parallel": true,
332
+ "self": 618.4720522820467,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
+ "total": 1.8920690200002355,
336
+ "count": 8,
337
  "is_parallel": true,
338
+ "self": 1.8920690200002355
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
+ "total": 362.62677573999963,
344
  "count": 90,
345
  "is_parallel": true,
346
+ "self": 121.65017745000205,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 240.97659828999758,
350
+ "count": 18357,
351
  "is_parallel": true,
352
+ "self": 240.97659828999758
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.13674563899985515,
364
  "count": 1,
365
+ "self": 0.0011115379998045682,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.13563410100005058,
369
  "count": 1,
370
+ "self": 0.13563410100005058
371
  }
372
  }
373
  }
run_logs/training_status.json CHANGED
@@ -4,8 +4,8 @@
4
  {
5
  "steps": 49936,
6
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 14.909090909090908,
8
- "creation_time": 1679312818.2941186,
9
  "auxillary_file_paths": [
10
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
11
  ]
@@ -13,8 +13,8 @@
13
  {
14
  "steps": 99960,
15
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
16
- "reward": 23.454545454545453,
17
- "creation_time": 1679312948.348997,
18
  "auxillary_file_paths": [
19
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
@@ -22,8 +22,8 @@
22
  {
23
  "steps": 149984,
24
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
25
- "reward": 25.181818181818183,
26
- "creation_time": 1679313079.8504438,
27
  "auxillary_file_paths": [
28
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
@@ -31,29 +31,65 @@
31
  {
32
  "steps": 199984,
33
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
34
- "reward": 25.90909090909091,
35
- "creation_time": 1679313208.3765485,
36
  "auxillary_file_paths": [
37
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
39
  },
40
  {
41
- "steps": 200112,
42
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
43
- "reward": 25.90909090909091,
44
- "creation_time": 1679313208.5402513,
45
  "auxillary_file_paths": [
46
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  ]
48
  }
49
  ],
50
  "final_checkpoint": {
51
- "steps": 200112,
52
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
53
- "reward": 25.90909090909091,
54
- "creation_time": 1679313208.5402513,
55
  "auxillary_file_paths": [
56
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },
 
4
  {
5
  "steps": 49936,
6
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
+ "reward": 9.818181818181818,
8
+ "creation_time": 1679315173.4299634,
9
  "auxillary_file_paths": [
10
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
11
  ]
 
13
  {
14
  "steps": 99960,
15
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
16
+ "reward": 16.0,
17
+ "creation_time": 1679315300.5009642,
18
  "auxillary_file_paths": [
19
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
 
22
  {
23
  "steps": 149984,
24
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
25
+ "reward": 21.727272727272727,
26
+ "creation_time": 1679315429.6126037,
27
  "auxillary_file_paths": [
28
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
 
31
  {
32
  "steps": 199984,
33
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
34
+ "reward": 23.181818181818183,
35
+ "creation_time": 1679315556.4432847,
36
  "auxillary_file_paths": [
37
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
39
  },
40
  {
41
+ "steps": 249944,
42
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-249944.onnx",
43
+ "reward": 24.136363636363637,
44
+ "creation_time": 1679315682.3036969,
45
  "auxillary_file_paths": [
46
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-249944.pt"
47
+ ]
48
+ },
49
+ {
50
+ "steps": 299968,
51
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.onnx",
52
+ "reward": 25.636363636363637,
53
+ "creation_time": 1679315813.0081344,
54
+ "auxillary_file_paths": [
55
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.pt"
56
+ ]
57
+ },
58
+ {
59
+ "steps": 349992,
60
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-349992.onnx",
61
+ "reward": 26.636363636363637,
62
+ "creation_time": 1679315938.5921464,
63
+ "auxillary_file_paths": [
64
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-349992.pt"
65
+ ]
66
+ },
67
+ {
68
+ "steps": 399992,
69
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-399992.onnx",
70
+ "reward": 26.5,
71
+ "creation_time": 1679316065.2986662,
72
+ "auxillary_file_paths": [
73
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-399992.pt"
74
+ ]
75
+ },
76
+ {
77
+ "steps": 400312,
78
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-400312.onnx",
79
+ "reward": 26.5,
80
+ "creation_time": 1679316065.4850662,
81
+ "auxillary_file_paths": [
82
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-400312.pt"
83
  ]
84
  }
85
  ],
86
  "final_checkpoint": {
87
+ "steps": 400312,
88
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
89
+ "reward": 26.5,
90
+ "creation_time": 1679316065.4850662,
91
  "auxillary_file_paths": [
92
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-400312.pt"
93
  ]
94
  }
95
  },