Hugging Face's logo

PrithviS
/
ppo-SnowballTarget-2

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files Metrics Community
PrithviS commited on
Commit
f82e582
•
1 Parent(s): f1b282e

Second Push

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-249944.onnx +3 -0
  7. SnowballTarget/SnowballTarget-249944.pt +3 -0
  8. SnowballTarget/SnowballTarget-299968.onnx +3 -0
  9. SnowballTarget/SnowballTarget-299968.pt +3 -0
  10. SnowballTarget/SnowballTarget-349992.onnx +3 -0
  11. SnowballTarget/SnowballTarget-349992.pt +3 -0
  12. SnowballTarget/SnowballTarget-399992.onnx +3 -0
  13. SnowballTarget/SnowballTarget-399992.pt +3 -0
  14. SnowballTarget/SnowballTarget-449952.onnx +3 -0
  15. SnowballTarget/SnowballTarget-449952.pt +3 -0
  16. SnowballTarget/SnowballTarget-499976.onnx +3 -0
  17. SnowballTarget/SnowballTarget-499976.pt +3 -0
  18. SnowballTarget/SnowballTarget-500104.onnx +3 -0
  19. SnowballTarget/SnowballTarget-500104.pt +3 -0
  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.1717143341.f9f95176e326.7966.0 +3 -0
  24. config.json +1 -1
  25. configuration.yaml +2 -2
  26. run_logs/Player-0.log +15 -18
  27. run_logs/timers.json +160 -160
  28. run_logs/training_status.json +69 -24
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b6e957b8b9434714f84f7d86a288b140d77f0d8e3660fd3e49a0a035cdfcc859
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9eb23825d72d294c273605d09d6bcc1cea9644df5314628a3d249492fbbf8746
3
  size 650646
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:31897da38507f3795bef71933582246cf0e74fe2405ab31f6e93ae6f52dc2464
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2247f99af563676f89417ddc35b3b9a6cf84e5d4323c758b52fbebb803d75a5
3
  size 650646
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b29bf90ab476aa1beb3ca92a4b225c18ec0361cbf1e34361a066ba58a8965c6
3
  size 3850075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bd6ffbf6afebcea51151baf0aecf26bc654f595a0876df6ab09a7676212c5bd
3
  size 3850075
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b6e957b8b9434714f84f7d86a288b140d77f0d8e3660fd3e49a0a035cdfcc859
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46b300ab515c989b9fa3e728937a13c83c25cee0bd495f588be0deec0321faf1
3
  size 650646
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a2d9a0ae55e9aa5d9578ad12984df41c3def418e7859d185853dccf63b23d69a
3
  size 3850075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd96eacb57d440800e068059208556864c72ce6225f4680f081abf0e00cce290
3
  size 3850075
SnowballTarget/SnowballTarget-249944.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7558db2220852009a13ce1a78071b24ec83d6bd06ab2dbfbdedfa0d2e671e4a0
3
+ size 650646
SnowballTarget/SnowballTarget-249944.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9fe9be640eed24bc078f32107b928878d599e4870a6feb4062b677ac2b08868
3
+ size 3850075
SnowballTarget/SnowballTarget-299968.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0254bf69da0a8bde8f359050beee1144a0f95201a189f22f4961e62692f65169
3
+ size 650646
SnowballTarget/SnowballTarget-299968.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c7bdac4df2218b2c3f08e757ed99f67f9ee11e513c388bd31a1162561b7ec15
3
+ size 3850075
SnowballTarget/SnowballTarget-349992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80e7091db35a94b8cb74a34638f695174e6f2315344126b1acba5364426781ec
3
+ size 650646
SnowballTarget/SnowballTarget-349992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9624450a834c1e7b446dff1e2a5dca86e0d8ad526b9c59aafeb1e148efe617c4
3
+ size 3850075
SnowballTarget/SnowballTarget-399992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd8a134dd9b909abe6175f4db7c64b837841cb8955f96f4c73b68d90e8282cd6
3
+ size 650646
SnowballTarget/SnowballTarget-399992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a6d4c78723cfccbd4cd24f034658503c959f683837e12b70dfcfff13857156e
3
+ size 3850075
SnowballTarget/SnowballTarget-449952.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7aee5397d86d2a8f3b060563999c468448d9c20d50fff8421b74c86d8380ba53
3
+ size 650646
SnowballTarget/SnowballTarget-449952.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca8b5dd7de945c2d974308901dfba909f2e342454bcb33ef7918b7396c92d6b0
3
+ size 3850075
SnowballTarget/SnowballTarget-499976.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9eb23825d72d294c273605d09d6bcc1cea9644df5314628a3d249492fbbf8746
3
+ size 650646
SnowballTarget/SnowballTarget-499976.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f5a2c79a81879a74340b5f859c468f285796b211eb75c02fdb9754a7780a2a4
3
+ size 3850075
SnowballTarget/SnowballTarget-500104.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9eb23825d72d294c273605d09d6bcc1cea9644df5314628a3d249492fbbf8746
3
+ size 650646
SnowballTarget/SnowballTarget-500104.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:289dcabf4c449deee6fc3fe2bc58dd61e20c9801908176e6a877369de2c4d4b4
3
+ size 3850075
SnowballTarget/SnowballTarget-99960.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d98145890172fe2a924f43dac74e43681997c983b8f19d1302ed877d6fa6881a
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:773cb0b89757efbb9ee915ed5233c1d8be7cab8840ba2c572a578bc093a81bc1
3
  size 650646
SnowballTarget/SnowballTarget-99960.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:05542a367259b210669acc2342ea65e0c5259a875597aebfe8e5c16e19a3e91f
3
  size 3850000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb335607c751f322d608b16c0ee7a1d460fbcffc059620cf70aea0f8f95c1dfb
3
  size 3850000
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:35cf6236e83478083bb63e18361e64ccd4611caf7223677bb42062113b513d3f
3
  size 3849250
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a3d5600aa9498b8ed0294e04744de434c1b41b9660c5b790a2e9476c7a1629b
3
  size 3849250
SnowballTarget/events.out.tfevents.1717143341.f9f95176e326.7966.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:660c07a92f5f6d4831db15595b78ed25b0603994c170a6df20ccda1a960b2796
3
+ size 49007
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}}}, "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.x86_64", "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": "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}
 
1
+ {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.00035, "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": 500000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64", "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": "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
@@ -5,7 +5,7 @@ behaviors:
5
  hyperparameters:
6
  batch_size: 128
7
  buffer_size: 2048
8
- learning_rate: 0.0003
9
  beta: 0.005
10
  epsilon: 0.2
11
  lambd: 0.95
@@ -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
 
5
  hyperparameters:
6
  batch_size: 128
7
  buffer_size: 2048
8
+ learning_rate: 0.00035
9
  beta: 0.005
10
  epsilon: 0.2
11
  lambd: 0.95
 
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
+ max_steps: 500000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: true
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:2664:(snd_pcm_open_noupdate) Unknown PCM default
34
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
35
  FMOD initialized on nosound output
36
  Begin MonoManager ReloadAssembly
37
- - Completed reload, in 0.088 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: 0.728566 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]: 5369 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 40
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]: 5461 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]: 5461 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]: 4644 frames, [64.0 KB-128.0 KB]: 817 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
- Peak Allocated memory 66.8 KB
220
  Peak Large allocation bytes 0 B
221
  [ALLOC_GFX_THREAD]
222
- Peak usage frame count: [32.0 KB-64.0 KB]: 5461 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]: 5461 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]: 5460 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]: 5461 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]: 5461 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 0.084 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: 0.639174 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]: 13415 frames, [16.0 KB-32.0 KB]: 227 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 42
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]: 10972 frames, [8.0 MB-16.0 MB]: 2671 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
+ Peak Allocated memory 9.6 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 13643 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]: 13107 frames, [64.0 KB-128.0 KB]: 536 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
+ Peak Allocated memory 66.4 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
+ Peak usage frame count: [32.0 KB-64.0 KB]: 13643 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]: 13643 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]: 13642 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]: 13643 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]: 13643 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
@@ -2,153 +2,153 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 0.9202103614807129,
6
- "min": 0.9202103614807129,
7
- "max": 2.866475820541382,
8
- "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 8796.291015625,
12
- "min": 8796.291015625,
13
- "max": 29387.109375,
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": 12.823229789733887,
30
- "min": 0.5408574342727661,
31
- "max": 12.823229789733887,
32
- "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2500.52978515625,
36
- "min": 104.92634582519531,
37
- "max": 2606.9072265625,
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": 0.06651720818512795,
54
- "min": 0.06235539605704081,
55
- "max": 0.07493936708630702,
56
- "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.2660688327405118,
60
- "min": 0.24942158422816324,
61
- "max": 0.3746968354315351,
62
- "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.21687843080829172,
66
- "min": 0.13089671620971285,
67
- "max": 0.3080260164889635,
68
- "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.8675137232331669,
72
- "min": 0.5235868648388514,
73
- "max": 1.3896103434118572,
74
- "count": 20
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
- "value": 8.082097306000005e-06,
78
- "min": 8.082097306000005e-06,
79
- "max": 0.000291882002706,
80
- "count": 20
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
- "value": 3.232838922400002e-05,
84
- "min": 3.232838922400002e-05,
85
- "max": 0.00138516003828,
86
- "count": 20
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
- "value": 0.10269400000000001,
90
- "min": 0.10269400000000001,
91
- "max": 0.19729400000000002,
92
- "count": 20
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
- "value": 0.41077600000000003,
96
- "min": 0.41077600000000003,
97
- "max": 0.96172,
98
- "count": 20
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
- "value": 0.0001444306000000001,
102
- "min": 0.0001444306000000001,
103
- "max": 0.0048649706,
104
- "count": 20
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
107
- "value": 0.0005777224000000004,
108
- "min": 0.0005777224000000004,
109
- "max": 0.023089828,
110
- "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 25.227272727272727,
114
- "min": 3.5681818181818183,
115
- "max": 25.227272727272727,
116
- "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1110.0,
120
- "min": 157.0,
121
- "max": 1381.0,
122
- "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 25.227272727272727,
126
- "min": 3.5681818181818183,
127
- "max": 25.227272727272727,
128
- "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1110.0,
132
- "min": 157.0,
133
- "max": 1381.0,
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": "1717142260",
152
  "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
153
  "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64 --run-id=SnowballTarget1 --no-graphics --force",
154
  "mlagents_version": "1.1.0.dev0",
@@ -156,59 +156,59 @@
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.3.0+cu121",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1717142712"
160
  },
161
- "total": 452.33572795,
162
  "count": 1,
163
- "self": 0.42445379299999786,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.05142919200000051,
167
  "count": 1,
168
- "self": 0.05142919200000051
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 451.859844965,
172
  "count": 1,
173
- "self": 0.5632135549963095,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 3.541285923000032,
177
  "count": 1,
178
- "self": 3.541285923000032
179
  },
180
  "TrainerController.advance": {
181
- "total": 447.66254705400377,
182
- "count": 18201,
183
- "self": 0.2694613340011074,
184
  "children": {
185
  "env_step": {
186
- "total": 447.39308572000266,
187
- "count": 18201,
188
- "self": 292.10742475000416,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 155.01131487599037,
192
- "count": 18201,
193
- "self": 1.4396459539884745,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 153.5716689220019,
197
- "count": 18201,
198
- "self": 153.5716689220019
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.2743460940081377,
204
- "count": 18201,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 450.55353015698563,
209
- "count": 18201,
210
  "is_parallel": true,
211
- "self": 228.1237831999797,
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": 0.005615585999976247,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.004052488000070298,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0015630979999059491,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0015630979999059491
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.03631462500004545,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0006571010002289768,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.0003906909998931951,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.0003906909998931951
244
  },
245
  "communicator.exchange": {
246
- "total": 0.03335960799995519,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.03335960799995519
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0019072249999680935,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.0003752309997935299,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0015319940001745636,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0015319940001745636
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 222.42974695700593,
271
- "count": 18200,
272
  "is_parallel": true,
273
- "self": 10.178511182994498,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 5.426610273012329,
277
- "count": 18200,
278
  "is_parallel": true,
279
- "self": 5.426610273012329
280
  },
281
  "communicator.exchange": {
282
- "total": 173.12294335198771,
283
- "count": 18200,
284
  "is_parallel": true,
285
- "self": 173.12294335198771
286
  },
287
  "steps_from_proto": {
288
- "total": 33.70168214901139,
289
- "count": 18200,
290
  "is_parallel": true,
291
- "self": 6.416058570024234,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 27.285623578987156,
295
- "count": 182000,
296
  "is_parallel": true,
297
- "self": 27.285623578987156
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 0.00011597200000323937,
313
  "count": 1,
314
- "self": 0.00011597200000323937,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,36 +320,36 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 442.245792257072,
324
- "count": 676345,
325
  "is_parallel": true,
326
- "self": 13.722016242059453,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 244.24036204901256,
330
- "count": 676345,
331
  "is_parallel": true,
332
- "self": 243.60425310201276,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
- "total": 0.6361089469997978,
336
- "count": 4,
337
  "is_parallel": true,
338
- "self": 0.6361089469997978
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
- "total": 184.283413966,
344
- "count": 90,
345
  "is_parallel": true,
346
- "self": 59.40505667300238,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
- "total": 124.87835729299763,
350
- "count": 4587,
351
  "is_parallel": true,
352
- "self": 124.87835729299763
353
  }
354
  }
355
  }
@@ -360,14 +360,14 @@
360
  }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.09268246099986754,
364
  "count": 1,
365
- "self": 0.0009330109999154956,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.09174944999995205,
369
  "count": 1,
370
- "self": 0.09174944999995205
371
  }
372
  }
373
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.8223253488540649,
6
+ "min": 0.799433708190918,
7
+ "max": 2.8630354404449463,
8
+ "count": 50
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 7932.97265625,
12
+ "min": 7606.61181640625,
13
+ "max": 29351.83984375,
14
+ "count": 50
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 499976.0,
18
  "min": 9952.0,
19
+ "max": 499976.0,
20
+ "count": 50
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 499976.0,
24
  "min": 9952.0,
25
+ "max": 499976.0,
26
+ "count": 50
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 13.931161880493164,
30
+ "min": 0.45234382152557373,
31
+ "max": 13.931161880493164,
32
+ "count": 50
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2855.88818359375,
36
+ "min": 87.75469970703125,
37
+ "max": 2855.88818359375,
38
+ "count": 50
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
+ "count": 50
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
+ "value": 10945.0,
48
  "min": 8756.0,
49
  "max": 10945.0,
50
+ "count": 50
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.07091916145747709,
54
+ "min": 0.06246914924715883,
55
+ "max": 0.07817078895439444,
56
+ "count": 50
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.3545958072873855,
60
+ "min": 0.2524322550515553,
61
+ "max": 0.3908539447719722,
62
+ "count": 50
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.17772815060966157,
66
+ "min": 0.11347350857777558,
67
+ "max": 0.2661994262653239,
68
+ "count": 50
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.8886407530483078,
72
+ "min": 0.4538940343111023,
73
+ "max": 1.3309971313266193,
74
+ "count": 50
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
+ "value": 3.5616989824000025e-06,
78
+ "min": 3.5616989824000025e-06,
79
+ "max": 0.0003462116010824,
80
+ "count": 50
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
+ "value": 1.7808494912000013e-05,
84
+ "min": 1.7808494912000013e-05,
85
+ "max": 0.0016964080153120003,
86
+ "count": 50
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
+ "value": 0.10101760000000001,
90
+ "min": 0.10101760000000001,
91
+ "max": 0.19891759999999997,
92
+ "count": 50
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
+ "value": 0.5050880000000001,
96
+ "min": 0.41199040000000003,
97
+ "max": 0.984688,
98
+ "count": 50
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
+ "value": 6.0778240000000044e-05,
102
+ "min": 6.0778240000000044e-05,
103
+ "max": 0.00494598824,
104
+ "count": 50
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
107
+ "value": 0.0003038912000000002,
108
+ "min": 0.0003038912000000002,
109
+ "max": 0.0242359312,
110
+ "count": 50
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 27.181818181818183,
114
+ "min": 3.272727272727273,
115
+ "max": 27.545454545454547,
116
+ "count": 50
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1495.0,
120
+ "min": 144.0,
121
+ "max": 1515.0,
122
+ "count": 50
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 27.181818181818183,
126
+ "min": 3.272727272727273,
127
+ "max": 27.545454545454547,
128
+ "count": 50
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1495.0,
132
+ "min": 144.0,
133
+ "max": 1515.0,
134
+ "count": 50
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
+ "count": 50
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
+ "count": 50
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1717143340",
152
  "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
153
  "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64 --run-id=SnowballTarget1 --no-graphics --force",
154
  "mlagents_version": "1.1.0.dev0",
 
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.3.0+cu121",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1717144426"
160
  },
161
+ "total": 1085.99541931,
162
  "count": 1,
163
+ "self": 0.43473192800001925,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.055542580000064845,
167
  "count": 1,
168
+ "self": 0.055542580000064845
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 1085.505144802,
172
  "count": 1,
173
+ "self": 1.3018926839840788,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 2.052020551999931,
177
  "count": 1,
178
+ "self": 2.052020551999931
179
  },
180
  "TrainerController.advance": {
181
+ "total": 1082.0634089470161,
182
+ "count": 45476,
183
+ "self": 0.6114708699622042,
184
  "children": {
185
  "env_step": {
186
+ "total": 1081.451938077054,
187
+ "count": 45476,
188
+ "self": 700.7580134160967,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 380.047344059956,
192
+ "count": 45476,
193
+ "self": 3.480147482963048,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 376.56719657699296,
197
+ "count": 45476,
198
+ "self": 376.56719657699296
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.6465806010012329,
204
+ "count": 45476,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 1082.516006696951,
209
+ "count": 45476,
210
  "is_parallel": true,
211
+ "self": 547.2498122079307,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.002331701000002795,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0006857359999230539,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.001645965000079741,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.001645965000079741
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.03653775800012227,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.000707356000020809,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0004187240001556347,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0004187240001556347
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.033396798000012495,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.033396798000012495
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0020148799999333278,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.00039830099990467716,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0016165790000286506,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0016165790000286506
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 535.2661944890203,
271
+ "count": 45475,
272
  "is_parallel": true,
273
+ "self": 24.71541623496114,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 12.955120059065848,
277
+ "count": 45475,
278
  "is_parallel": true,
279
+ "self": 12.955120059065848
280
  },
281
  "communicator.exchange": {
282
+ "total": 416.1775510239354,
283
+ "count": 45475,
284
  "is_parallel": true,
285
+ "self": 416.1775510239354
286
  },
287
  "steps_from_proto": {
288
+ "total": 81.41810717105795,
289
+ "count": 45475,
290
  "is_parallel": true,
291
+ "self": 15.309917971942241,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 66.10818919911571,
295
+ "count": 454750,
296
  "is_parallel": true,
297
+ "self": 66.10818919911571
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 0.0001737859997774649,
313
  "count": 1,
314
+ "self": 0.0001737859997774649,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 1068.9248886532941,
324
+ "count": 1648536,
325
  "is_parallel": true,
326
+ "self": 34.946814295369904,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 588.2397075129222,
330
+ "count": 1648536,
331
  "is_parallel": true,
332
+ "self": 586.5158492779219,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
+ "total": 1.723858235000307,
336
+ "count": 10,
337
  "is_parallel": true,
338
+ "self": 1.723858235000307
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
+ "total": 445.738366845002,
344
+ "count": 227,
345
  "is_parallel": true,
346
+ "self": 141.80564636297345,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 303.93272048202857,
350
+ "count": 11571,
351
  "is_parallel": true,
352
+ "self": 303.93272048202857
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.08764883300000292,
364
  "count": 1,
365
+ "self": 0.0012193009997645277,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.0864295320002384,
369
  "count": 1,
370
+ "self": 0.0864295320002384
371
  }
372
  }
373
  }
run_logs/training_status.json CHANGED
@@ -1,20 +1,11 @@
1
  {
2
  "SnowballTarget": {
3
  "checkpoints": [
4
- {
5
- "steps": 49936,
6
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 12.636363636363637,
8
- "creation_time": 1717142375.4266744,
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": 21.272727272727273,
17
- "creation_time": 1717142487.479833,
18
  "auxillary_file_paths": [
19
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
@@ -22,8 +13,8 @@
22
  {
23
  "steps": 149984,
24
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
25
- "reward": 24.181818181818183,
26
- "creation_time": 1717142600.0611389,
27
  "auxillary_file_paths": [
28
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
@@ -31,29 +22,83 @@
31
  {
32
  "steps": 199984,
33
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
34
- "reward": 24.90909090909091,
35
- "creation_time": 1717142711.8859034,
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": 24.90909090909091,
44
- "creation_time": 1717142712.0053854,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 24.90909090909091,
54
- "creation_time": 1717142712.0053854,
55
  "auxillary_file_paths": [
56
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },
 
1
  {
2
  "SnowballTarget": {
3
  "checkpoints": [
 
 
 
 
 
 
 
 
 
4
  {
5
  "steps": 99960,
6
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
7
+ "reward": 22.181818181818183,
8
+ "creation_time": 1717143563.545283,
9
  "auxillary_file_paths": [
10
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
11
  ]
 
13
  {
14
  "steps": 149984,
15
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
16
+ "reward": 25.636363636363637,
17
+ "creation_time": 1717143671.2380314,
18
  "auxillary_file_paths": [
19
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
20
  ]
 
22
  {
23
  "steps": 199984,
24
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
25
+ "reward": 25.727272727272727,
26
+ "creation_time": 1717143778.551279,
27
  "auxillary_file_paths": [
28
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
29
  ]
30
  },
31
  {
32
+ "steps": 249944,
33
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-249944.onnx",
34
+ "reward": 26.727272727272727,
35
+ "creation_time": 1717143886.3553164,
36
+ "auxillary_file_paths": [
37
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-249944.pt"
38
+ ]
39
+ },
40
+ {
41
+ "steps": 299968,
42
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.onnx",
43
+ "reward": 25.727272727272727,
44
+ "creation_time": 1717143994.751618,
45
+ "auxillary_file_paths": [
46
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.pt"
47
+ ]
48
+ },
49
+ {
50
+ "steps": 349992,
51
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-349992.onnx",
52
+ "reward": 26.727272727272727,
53
+ "creation_time": 1717144103.3137527,
54
+ "auxillary_file_paths": [
55
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-349992.pt"
56
+ ]
57
+ },
58
+ {
59
+ "steps": 399992,
60
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-399992.onnx",
61
+ "reward": 26.181818181818183,
62
+ "creation_time": 1717144209.9148397,
63
+ "auxillary_file_paths": [
64
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-399992.pt"
65
+ ]
66
+ },
67
+ {
68
+ "steps": 449952,
69
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-449952.onnx",
70
+ "reward": 26.727272727272727,
71
+ "creation_time": 1717144319.4079397,
72
+ "auxillary_file_paths": [
73
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-449952.pt"
74
+ ]
75
+ },
76
+ {
77
+ "steps": 499976,
78
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-499976.onnx",
79
+ "reward": 26.636363636363637,
80
+ "creation_time": 1717144426.4260418,
81
+ "auxillary_file_paths": [
82
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-499976.pt"
83
+ ]
84
+ },
85
+ {
86
+ "steps": 500104,
87
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-500104.onnx",
88
+ "reward": 26.636363636363637,
89
+ "creation_time": 1717144426.5341268,
90
  "auxillary_file_paths": [
91
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-500104.pt"
92
  ]
93
  }
94
  ],
95
  "final_checkpoint": {
96
+ "steps": 500104,
97
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
98
+ "reward": 26.636363636363637,
99
+ "creation_time": 1717144426.5341268,
100
  "auxillary_file_paths": [
101
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-500104.pt"
102
  ]
103
  }
104
  },