Hugging Face's logo

tux
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files Metrics Community
tux commited on
Commit
68c582e
·
1 Parent(s): ee7412f

Second Push

Browse files
Files changed (22) hide show
  1. SnowballTarget.onnx +1 -1
  2. SnowballTarget/SnowballTarget-249984.onnx +3 -0
  3. SnowballTarget/SnowballTarget-249984.pt +3 -0
  4. SnowballTarget/SnowballTarget-270424.onnx +3 -0
  5. SnowballTarget/SnowballTarget-270424.pt +3 -0
  6. SnowballTarget/SnowballTarget-299984.onnx +3 -0
  7. SnowballTarget/SnowballTarget-299984.pt +3 -0
  8. SnowballTarget/SnowballTarget-349944.onnx +3 -0
  9. SnowballTarget/SnowballTarget-349944.pt +3 -0
  10. SnowballTarget/SnowballTarget-399944.onnx +3 -0
  11. SnowballTarget/SnowballTarget-399944.pt +3 -0
  12. SnowballTarget/SnowballTarget-400136.onnx +3 -0
  13. SnowballTarget/SnowballTarget-400136.pt +3 -0
  14. SnowballTarget/checkpoint.pt +2 -2
  15. SnowballTarget/events.out.tfevents.1687088968.0fd2ca80588f.15680.0 +3 -0
  16. SnowballTarget/events.out.tfevents.1687089009.0fd2ca80588f.15910.0 +3 -0
  17. SnowballTarget/events.out.tfevents.1687089214.0fd2ca80588f.16826.0 +3 -0
  18. config.json +1 -1
  19. configuration.yaml +2 -15
  20. run_logs/Player-0.log +14 -17
  21. run_logs/timers.json +163 -199
  22. run_logs/training_status.json +67 -22
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:68ac1f76ebb5468be255d6b39ae561558208fb4ea7fbd41015f6fc18ef2281fa
3
  size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0eb32c4466e2e06c75fab8f8173c2785bde57043bd64d122cd82c03cb86b0986
3
  size 646532
SnowballTarget/SnowballTarget-249984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8bcb9d9dd2af3c677d3e189b7057a91f9554db598e29c429f7e137a85ac01e8
3
+ size 646532
SnowballTarget/SnowballTarget-249984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d70e49f2585a3b88a7fa6585c37b670fdbbdc5f7d5388736edd9a1c1273ff60
3
+ size 5119318
SnowballTarget/SnowballTarget-270424.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fef3afeb968695118cec5daed8c53290eacefcd9925eb09c52bdc777b214490
3
+ size 646532
SnowballTarget/SnowballTarget-270424.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f13c6ce49b94ff0f4b36245098fc34f1488f87efeac3c21105509c3e3dfc335
3
+ size 5119318
SnowballTarget/SnowballTarget-299984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b945a299d61e3b88e0eee4edd6648dd2c6e5c145cefbecb6458d4f2d27515d3
3
+ size 646532
SnowballTarget/SnowballTarget-299984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b21d1aa93d751595b62e6ac3e981efab6ac427da96ce6c09ba05be653b14a66
3
+ size 3843968
SnowballTarget/SnowballTarget-349944.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44a42f4520cd487abb584938358183eda3fbf4d633789f728bc477d3f3f00a94
3
+ size 646532
SnowballTarget/SnowballTarget-349944.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6d23b91bdd5138b851b2b2d778c23e54c7679ffb56c1b5dc12b4a9b15f02be3
3
+ size 3843968
SnowballTarget/SnowballTarget-399944.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0eb32c4466e2e06c75fab8f8173c2785bde57043bd64d122cd82c03cb86b0986
3
+ size 646532
SnowballTarget/SnowballTarget-399944.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74dfe5ac4424f5c01efe4bca96bd4ae15bb2f5766fabc510d0387a8b145a3831
3
+ size 3843968
SnowballTarget/SnowballTarget-400136.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0eb32c4466e2e06c75fab8f8173c2785bde57043bd64d122cd82c03cb86b0986
3
+ size 646532
SnowballTarget/SnowballTarget-400136.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52958a0b24c1b0b79a881d37d9c3e1978bf5c97e621918b046d3c3c05d355177
3
+ size 3843968
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c992b5de834fe7f857ef719ce9a24ebaae5f81004b362f029602bdf2d6dbc986
3
- size 5119318
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52958a0b24c1b0b79a881d37d9c3e1978bf5c97e621918b046d3c3c05d355177
3
+ size 3843968
SnowballTarget/events.out.tfevents.1687088968.0fd2ca80588f.15680.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29fd721797ab83047eb8661289c6eed4891a80800698a49e9356755b57cedad5
3
+ size 1421
SnowballTarget/events.out.tfevents.1687089009.0fd2ca80588f.15910.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25a29002962dd1892da66094e33f513585d85467702a4ce0dff461a9b7b15b12
3
+ size 8558
SnowballTarget/events.out.tfevents.1687089214.0fd2ca80588f.16826.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a80e3f3a2b5a8b313d0b0b4ec8db18c377536895b1213dec0d61536948bdcba8
3
+ size 11816
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "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}}, "rnd": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0003, "encoding_size": null}}, "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": 128, "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": 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": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -35,23 +35,10 @@ behaviors:
35
  memory: null
36
  goal_conditioning_type: hyper
37
  deterministic: false
38
- rnd:
39
- gamma: 0.99
40
- strength: 1.0
41
- network_settings:
42
- normalize: false
43
- hidden_units: 256
44
- num_layers: 2
45
- vis_encode_type: simple
46
- memory: null
47
- goal_conditioning_type: hyper
48
- deterministic: false
49
- learning_rate: 0.0003
50
- encoding_size: null
51
  init_path: null
52
  keep_checkpoints: 10
53
  even_checkpoints: false
54
- max_steps: 200000
55
  time_horizon: 64
56
  summary_freq: 10000
57
  threaded: true
@@ -80,7 +67,7 @@ checkpoint_settings:
80
  run_id: SnowballTarget1
81
  initialize_from: null
82
  load_model: false
83
- resume: false
84
  force: false
85
  train_model: false
86
  inference: false
 
35
  memory: null
36
  goal_conditioning_type: hyper
37
  deterministic: false
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
67
  run_id: SnowballTarget1
68
  initialize_from: null
69
  load_model: false
70
+ resume: true
71
  force: false
72
  train_model: false
73
  inference: false
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 0.085 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: 0.821510 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]: 5371 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 36
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]: 5463 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]: 5463 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]: 5218 frames, [64.0 KB-128.0 KB]: 245 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
  Peak Allocated memory 66.0 KB
220
  Peak Large allocation bytes 0 B
221
  [ALLOC_GFX_THREAD]
222
- Peak usage frame count: [32.0 KB-64.0 KB]: 5463 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]: 5463 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]: 5462 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]: 5463 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]: 5463 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 0.127 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: 0.837779 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]: 3487 frames, [16.0 KB-32.0 KB]: 59 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 34
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]: 3547 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
+ Peak Allocated memory 6.1 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 3547 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
+ Peak Allocated memory 17.7 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]: 3441 frames, [64.0 KB-128.0 KB]: 106 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
  Peak Allocated memory 66.0 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
+ Peak usage frame count: [32.0 KB-64.0 KB]: 3547 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]: 3547 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]: 3546 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]: 3547 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]: 3547 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
@@ -2,249 +2,213 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 1.081656575202942,
6
- "min": 1.081656575202942,
7
- "max": 2.871687650680542,
8
- "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 10410.9443359375,
12
- "min": 10410.9443359375,
13
- "max": 29535.30859375,
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": 11.892847061157227,
30
- "min": 0.38023102283477783,
31
- "max": 11.892847061157227,
32
- "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2319.105224609375,
36
- "min": 73.76481628417969,
37
- "max": 2421.75390625,
38
- "count": 20
39
- },
40
- "SnowballTarget.Policy.RndValueEstimate.mean": {
41
- "value": 0.3695298731327057,
42
- "min": 0.3695298731327057,
43
- "max": 20.148469924926758,
44
- "count": 20
45
- },
46
- "SnowballTarget.Policy.RndValueEstimate.sum": {
47
- "value": 72.0583267211914,
48
- "min": 72.0583267211914,
49
- "max": 4130.4365234375,
50
- "count": 20
51
  },
52
  "SnowballTarget.Environment.EpisodeLength.mean": {
53
  "value": 199.0,
54
  "min": 199.0,
55
  "max": 199.0,
56
- "count": 20
57
  },
58
  "SnowballTarget.Environment.EpisodeLength.sum": {
59
- "value": 10945.0,
60
  "min": 8756.0,
61
  "max": 10945.0,
62
- "count": 20
63
  },
64
  "SnowballTarget.Losses.PolicyLoss.mean": {
65
- "value": 0.06167541818542625,
66
- "min": 0.06167541818542625,
67
- "max": 0.07331990349213775,
68
- "count": 20
69
  },
70
  "SnowballTarget.Losses.PolicyLoss.sum": {
71
- "value": 0.246701672741705,
72
- "min": 0.246701672741705,
73
- "max": 0.36659951746068875,
74
- "count": 20
75
  },
76
  "SnowballTarget.Losses.ValueLoss.mean": {
77
- "value": 0.1400872111758765,
78
- "min": 0.1294612772324506,
79
- "max": 125.28937412944495,
80
- "count": 20
81
  },
82
  "SnowballTarget.Losses.ValueLoss.sum": {
83
- "value": 0.560348844703506,
84
- "min": 0.560348844703506,
85
- "max": 501.1574965177798,
86
- "count": 20
87
  },
88
  "SnowballTarget.Policy.LearningRate.mean": {
89
- "value": 8.082097306000005e-06,
90
- "min": 8.082097306000005e-06,
91
- "max": 0.000291882002706,
92
- "count": 20
93
  },
94
  "SnowballTarget.Policy.LearningRate.sum": {
95
- "value": 3.232838922400002e-05,
96
- "min": 3.232838922400002e-05,
97
- "max": 0.00138516003828,
98
- "count": 20
99
  },
100
  "SnowballTarget.Policy.Epsilon.mean": {
101
- "value": 0.10269400000000001,
102
- "min": 0.10269400000000001,
103
- "max": 0.19729400000000002,
104
- "count": 20
105
  },
106
  "SnowballTarget.Policy.Epsilon.sum": {
107
- "value": 0.41077600000000003,
108
- "min": 0.41077600000000003,
109
- "max": 0.96172,
110
- "count": 20
111
  },
112
  "SnowballTarget.Policy.Beta.mean": {
113
- "value": 0.0001444306000000001,
114
- "min": 0.0001444306000000001,
115
- "max": 0.0048649706,
116
- "count": 20
117
  },
118
  "SnowballTarget.Policy.Beta.sum": {
119
- "value": 0.0005777224000000004,
120
- "min": 0.0005777224000000004,
121
- "max": 0.023089828,
122
- "count": 20
123
- },
124
- "SnowballTarget.Losses.RNDLoss.mean": {
125
- "value": 0.0034183606039732695,
126
- "min": 0.0034183606039732695,
127
- "max": 0.3998382091522217,
128
- "count": 20
129
- },
130
- "SnowballTarget.Losses.RNDLoss.sum": {
131
- "value": 0.013673442415893078,
132
- "min": 0.013673442415893078,
133
- "max": 1.5993528366088867,
134
- "count": 20
135
  },
136
  "SnowballTarget.Environment.CumulativeReward.mean": {
137
- "value": 23.681818181818183,
138
- "min": 2.8636363636363638,
139
- "max": 24.072727272727274,
140
- "count": 20
141
  },
142
  "SnowballTarget.Environment.CumulativeReward.sum": {
143
- "value": 1042.0,
144
- "min": 126.0,
145
- "max": 1324.0,
146
- "count": 20
147
  },
148
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
149
- "value": 23.681818181818183,
150
- "min": 2.8636363636363638,
151
- "max": 24.072727272727274,
152
- "count": 20
153
  },
154
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
155
- "value": 1042.0,
156
- "min": 126.0,
157
- "max": 1324.0,
158
- "count": 20
159
- },
160
- "SnowballTarget.Policy.RndReward.mean": {
161
- "value": 0.7163594745692204,
162
- "min": 0.7163594745692204,
163
- "max": 178.4163769077171,
164
- "count": 20
165
- },
166
- "SnowballTarget.Policy.RndReward.sum": {
167
- "value": 31.5198168810457,
168
- "min": 31.5198168810457,
169
- "max": 7850.320583939552,
170
- "count": 20
171
  },
172
  "SnowballTarget.IsTraining.mean": {
173
  "value": 1.0,
174
  "min": 1.0,
175
  "max": 1.0,
176
- "count": 20
177
  },
178
  "SnowballTarget.IsTraining.sum": {
179
  "value": 1.0,
180
  "min": 1.0,
181
  "max": 1.0,
182
- "count": 20
183
  }
184
  },
185
  "metadata": {
186
  "timer_format_version": "0.1.0",
187
- "start_time_seconds": "1687085599",
188
  "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]",
189
- "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
190
  "mlagents_version": "0.31.0.dev0",
191
  "mlagents_envs_version": "0.31.0.dev0",
192
  "communication_protocol_version": "1.5.0",
193
  "pytorch_version": "1.11.0+cu102",
194
  "numpy_version": "1.21.2",
195
- "end_time_seconds": "1687086101"
196
  },
197
- "total": 502.82307906499994,
198
  "count": 1,
199
- "self": 0.43293366199992533,
200
  "children": {
201
  "run_training.setup": {
202
- "total": 0.04406309000000874,
203
  "count": 1,
204
- "self": 0.04406309000000874
205
  },
206
  "TrainerController.start_learning": {
207
- "total": 502.346082313,
208
  "count": 1,
209
- "self": 0.5690054680054573,
210
  "children": {
211
  "TrainerController._reset_env": {
212
- "total": 4.140457286000014,
213
  "count": 1,
214
- "self": 4.140457286000014
215
  },
216
  "TrainerController.advance": {
217
- "total": 497.48666733499454,
218
- "count": 18209,
219
- "self": 0.2642808819992979,
220
  "children": {
221
  "env_step": {
222
- "total": 497.22238645299524,
223
- "count": 18209,
224
- "self": 373.7566097889891,
225
  "children": {
226
  "SubprocessEnvManager._take_step": {
227
- "total": 123.19183615299409,
228
- "count": 18209,
229
- "self": 1.796826380996606,
230
  "children": {
231
  "TorchPolicy.evaluate": {
232
- "total": 121.39500977199748,
233
- "count": 18209,
234
- "self": 121.39500977199748
235
  }
236
  }
237
  },
238
  "workers": {
239
- "total": 0.27394051101202876,
240
- "count": 18209,
241
  "self": 0.0,
242
  "children": {
243
  "worker_root": {
244
- "total": 500.7638370499975,
245
- "count": 18209,
246
  "is_parallel": true,
247
- "self": 253.1233061049906,
248
  "children": {
249
  "run_training.setup": {
250
  "total": 0.0,
@@ -253,48 +217,48 @@
253
  "self": 0.0,
254
  "children": {
255
  "steps_from_proto": {
256
- "total": 0.005230067000013605,
257
  "count": 1,
258
  "is_parallel": true,
259
- "self": 0.003548437999882026,
260
  "children": {
261
  "_process_rank_one_or_two_observation": {
262
- "total": 0.0016816290001315792,
263
  "count": 10,
264
  "is_parallel": true,
265
- "self": 0.0016816290001315792
266
  }
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 0.05466635499999484,
271
  "count": 1,
272
  "is_parallel": true,
273
- "self": 0.0006263249999847176,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 0.0004094450000025063,
277
  "count": 1,
278
  "is_parallel": true,
279
- "self": 0.0004094450000025063
280
  },
281
  "communicator.exchange": {
282
- "total": 0.051609476999999515,
283
  "count": 1,
284
  "is_parallel": true,
285
- "self": 0.051609476999999515
286
  },
287
  "steps_from_proto": {
288
- "total": 0.0020211080000080983,
289
  "count": 1,
290
  "is_parallel": true,
291
- "self": 0.00034206799995217807,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 0.0016790400000559202,
295
  "count": 10,
296
  "is_parallel": true,
297
- "self": 0.0016790400000559202
298
  }
299
  }
300
  }
@@ -303,34 +267,34 @@
303
  }
304
  },
305
  "UnityEnvironment.step": {
306
- "total": 247.6405309450069,
307
- "count": 18208,
308
  "is_parallel": true,
309
- "self": 10.540071582000621,
310
  "children": {
311
  "UnityEnvironment._generate_step_input": {
312
- "total": 5.376574129001085,
313
- "count": 18208,
314
  "is_parallel": true,
315
- "self": 5.376574129001085
316
  },
317
  "communicator.exchange": {
318
- "total": 196.64055253599895,
319
- "count": 18208,
320
  "is_parallel": true,
321
- "self": 196.64055253599895
322
  },
323
  "steps_from_proto": {
324
- "total": 35.083332698006245,
325
- "count": 18208,
326
  "is_parallel": true,
327
- "self": 6.293852239987132,
328
  "children": {
329
  "_process_rank_one_or_two_observation": {
330
- "total": 28.789480458019113,
331
- "count": 182080,
332
  "is_parallel": true,
333
- "self": 28.789480458019113
334
  }
335
  }
336
  }
@@ -345,9 +309,9 @@
345
  }
346
  },
347
  "trainer_threads": {
348
- "total": 0.00015815200003999053,
349
  "count": 1,
350
- "self": 0.00015815200003999053,
351
  "children": {
352
  "thread_root": {
353
  "total": 0.0,
@@ -356,36 +320,36 @@
356
  "self": 0.0,
357
  "children": {
358
  "trainer_advance": {
359
- "total": 494.38502684100905,
360
- "count": 399747,
361
  "is_parallel": true,
362
- "self": 8.654125904049579,
363
  "children": {
364
  "process_trajectory": {
365
- "total": 266.78117643595914,
366
- "count": 399747,
367
  "is_parallel": true,
368
- "self": 265.5369639209592,
369
  "children": {
370
  "RLTrainer._checkpoint": {
371
- "total": 1.2442125149999583,
372
- "count": 4,
373
  "is_parallel": true,
374
- "self": 1.2442125149999583
375
  }
376
  }
377
  },
378
  "_update_policy": {
379
- "total": 218.94972450100033,
380
- "count": 90,
381
  "is_parallel": true,
382
- "self": 115.2116738200026,
383
  "children": {
384
  "TorchPPOOptimizer.update": {
385
- "total": 103.73805068099773,
386
- "count": 4584,
387
  "is_parallel": true,
388
- "self": 103.73805068099773
389
  }
390
  }
391
  }
@@ -396,14 +360,14 @@
396
  }
397
  },
398
  "TrainerController._save_models": {
399
- "total": 0.1497940719999633,
400
  "count": 1,
401
- "self": 0.0009099930000502354,
402
  "children": {
403
  "RLTrainer._checkpoint": {
404
- "total": 0.14888407899991307,
405
  "count": 1,
406
- "self": 0.14888407899991307
407
  }
408
  }
409
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.6749759912490845,
6
+ "min": 0.6749759912490845,
7
+ "max": 0.8381103873252869,
8
+ "count": 13
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 6459.5205078125,
12
+ "min": 6459.5205078125,
13
+ "max": 8555.4306640625,
14
+ "count": 13
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 399944.0,
18
+ "min": 279992.0,
19
+ "max": 399944.0,
20
+ "count": 13
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 399944.0,
24
+ "min": 279992.0,
25
+ "max": 399944.0,
26
+ "count": 13
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 12.998022079467773,
30
+ "min": 12.612207412719727,
31
+ "max": 13.121735572814941,
32
+ "count": 13
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2521.6162109375,
36
+ "min": 2397.19091796875,
37
+ "max": 2676.833984375,
38
+ "count": 13
 
 
 
 
 
 
 
 
 
 
 
 
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
+ "count": 13
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
+ "value": 8756.0,
48
  "min": 8756.0,
49
  "max": 10945.0,
50
+ "count": 13
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.06842379256248059,
54
+ "min": 0.06274938085330445,
55
+ "max": 0.07379341599087497,
56
+ "count": 13
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.27369517024992235,
60
+ "min": 0.2530691640870417,
61
+ "max": 0.36896707995437483,
62
+ "count": 13
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.19016173211675066,
66
+ "min": 0.18351931782329783,
67
+ "max": 0.2117971901800118,
68
+ "count": 13
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.7606469284670027,
72
+ "min": 0.7515429112256742,
73
+ "max": 1.058985950900059,
74
+ "count": 13
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
+ "value": 4.0230986590000025e-06,
78
+ "min": 4.0230986590000025e-06,
79
+ "max": 9.312306895899999e-05,
80
+ "count": 13
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
+ "value": 1.609239463600001e-05,
84
+ "min": 1.609239463600001e-05,
85
+ "max": 0.0003954903681699999,
86
+ "count": 13
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
+ "value": 0.10134100000000001,
90
+ "min": 0.10134100000000001,
91
+ "max": 0.13104100000000002,
92
+ "count": 13
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
+ "value": 0.40536400000000006,
96
+ "min": 0.40536400000000006,
97
+ "max": 0.63183,
98
+ "count": 13
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
+ "value": 7.691590000000003e-05,
102
+ "min": 7.691590000000003e-05,
103
+ "max": 0.0015589459000000005,
104
+ "count": 13
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
107
+ "value": 0.0003076636000000001,
108
+ "min": 0.0003076636000000001,
109
+ "max": 0.006628317,
110
+ "count": 13
 
 
 
 
 
 
 
 
 
 
 
 
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 25.681818181818183,
114
+ "min": 24.454545454545453,
115
+ "max": 26.022727272727273,
116
+ "count": 13
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1130.0,
120
+ "min": 1076.0,
121
+ "max": 1423.0,
122
+ "count": 13
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 25.681818181818183,
126
+ "min": 24.454545454545453,
127
+ "max": 26.022727272727273,
128
+ "count": 13
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1130.0,
132
+ "min": 1076.0,
133
+ "max": 1423.0,
134
+ "count": 13
 
 
 
 
 
 
 
 
 
 
 
 
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
+ "count": 13
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
+ "count": 13
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1687089213",
152
  "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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 --resume",
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": "1687089515"
160
  },
161
+ "total": 302.4342371169996,
162
  "count": 1,
163
+ "self": 0.8387473499997213,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.06620121099967946,
167
  "count": 1,
168
+ "self": 0.06620121099967946
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 301.5292885560002,
172
  "count": 1,
173
+ "self": 0.3744299729842169,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 4.302400324000246,
177
  "count": 1,
178
+ "self": 4.302400324000246
179
  },
180
  "TrainerController.advance": {
181
+ "total": 296.62832749101517,
182
+ "count": 11821,
183
+ "self": 0.16391955803783276,
184
  "children": {
185
  "env_step": {
186
+ "total": 296.46440793297734,
187
+ "count": 11821,
188
+ "self": 218.3596087559531,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 77.9404431580283,
192
+ "count": 11821,
193
+ "self": 1.2103973100033727,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 76.73004584802493,
197
+ "count": 11821,
198
+ "self": 76.73004584802493
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.16435601899593166,
204
+ "count": 11821,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 300.37892925197,
209
+ "count": 11821,
210
  "is_parallel": true,
211
+ "self": 142.82830187891295,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.003400146999865683,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0007431369999721937,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0026570099998934893,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0026570099998934893
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.04434941599993181,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0005497960000866442,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.00032860099963727407,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.00032860099963727407
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.041253743000197574,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.041253743000197574
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0022172760000103153,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0004083720004928182,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0018089039995174971,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0018089039995174971
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 157.55062737305707,
271
+ "count": 11820,
272
  "is_parallel": true,
273
+ "self": 6.540792842022256,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 3.3528731100345794,
277
+ "count": 11820,
278
  "is_parallel": true,
279
+ "self": 3.3528731100345794
280
  },
281
  "communicator.exchange": {
282
+ "total": 125.86504411401711,
283
+ "count": 11820,
284
  "is_parallel": true,
285
+ "self": 125.86504411401711
286
  },
287
  "steps_from_proto": {
288
+ "total": 21.791917306983123,
289
+ "count": 11820,
290
  "is_parallel": true,
291
+ "self": 3.9140963719200954,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 17.877820935063028,
295
+ "count": 118200,
296
  "is_parallel": true,
297
+ "self": 17.877820935063028
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 0.00018013600038102595,
313
  "count": 1,
314
+ "self": 0.00018013600038102595,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 294.4034886741424,
324
+ "count": 275822,
325
  "is_parallel": true,
326
+ "self": 6.150136907125216,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 160.87285804101384,
330
+ "count": 275822,
331
  "is_parallel": true,
332
+ "self": 159.30715024501342,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
+ "total": 1.5657077960004244,
336
+ "count": 3,
337
  "is_parallel": true,
338
+ "self": 1.5657077960004244
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
+ "total": 127.38049372600335,
344
+ "count": 58,
345
  "is_parallel": true,
346
+ "self": 49.78196640102624,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 77.59852732497711,
350
+ "count": 2955,
351
  "is_parallel": true,
352
+ "self": 77.59852732497711
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.2239506320001965,
364
  "count": 1,
365
+ "self": 0.0018281009997735964,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.2221225310004229,
369
  "count": 1,
370
+ "self": 0.2221225310004229
371
  }
372
  }
373
  }
run_logs/training_status.json CHANGED
@@ -1,24 +1,6 @@
1
  {
2
  "SnowballTarget": {
3
  "checkpoints": [
4
- {
5
- "steps": 49936,
6
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 7.0,
8
- "creation_time": 1687085730.2541745,
9
- "auxillary_file_paths": [
10
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
11
- ]
12
- },
13
- {
14
- "steps": 99960,
15
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
16
- "reward": 14.454545454545455,
17
- "creation_time": 1687085855.340704,
18
- "auxillary_file_paths": [
19
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
20
- ]
21
- },
22
  {
23
  "steps": 149984,
24
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
@@ -45,15 +27,78 @@
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": 24.272727272727273,
54
- "creation_time": 1687086101.5429204,
55
  "auxillary_file_paths": [
56
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },
 
1
  {
2
  "SnowballTarget": {
3
  "checkpoints": [
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  {
5
  "steps": 149984,
6
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
 
27
  "auxillary_file_paths": [
28
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
29
  ]
30
+ },
31
+ {
32
+ "steps": 200112,
33
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
34
+ "reward": null,
35
+ "creation_time": 1687088971.5190713,
36
+ "auxillary_file_paths": [
37
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
38
+ ]
39
+ },
40
+ {
41
+ "steps": 249984,
42
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-249984.onnx",
43
+ "reward": 23.636363636363637,
44
+ "creation_time": 1687089134.6237562,
45
+ "auxillary_file_paths": [
46
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-249984.pt"
47
+ ]
48
+ },
49
+ {
50
+ "steps": 270424,
51
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-270424.onnx",
52
+ "reward": null,
53
+ "creation_time": 1687089187.0483046,
54
+ "auxillary_file_paths": [
55
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-270424.pt"
56
+ ]
57
+ },
58
+ {
59
+ "steps": 299984,
60
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-299984.onnx",
61
+ "reward": 24.90909090909091,
62
+ "creation_time": 1687089286.8308792,
63
+ "auxillary_file_paths": [
64
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-299984.pt"
65
+ ]
66
+ },
67
+ {
68
+ "steps": 349944,
69
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-349944.onnx",
70
+ "reward": 26.454545454545453,
71
+ "creation_time": 1687089401.55398,
72
+ "auxillary_file_paths": [
73
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-349944.pt"
74
+ ]
75
+ },
76
+ {
77
+ "steps": 399944,
78
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-399944.onnx",
79
+ "reward": 25.545454545454547,
80
+ "creation_time": 1687089514.595855,
81
+ "auxillary_file_paths": [
82
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-399944.pt"
83
+ ]
84
+ },
85
+ {
86
+ "steps": 400136,
87
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-400136.onnx",
88
+ "reward": 25.545454545454547,
89
+ "creation_time": 1687089514.8510673,
90
+ "auxillary_file_paths": [
91
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-400136.pt"
92
+ ]
93
  }
94
  ],
95
  "final_checkpoint": {
96
+ "steps": 400136,
97
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
98
+ "reward": 25.545454545454547,
99
+ "creation_time": 1687089514.8510673,
100
  "auxillary_file_paths": [
101
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-400136.pt"
102
  ]
103
  }
104
  },