Hugging Face's logo

jakubgajski
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files Metrics Community
jakubgajski commited on
Commit
fd5926e
•
1 Parent(s): 42073b7

First Push

Browse files
Files changed (23) hide show
  1. SnowballTarget.onnx +1 -1
  2. SnowballTarget/{SnowballTarget-149984.onnx → SnowballTarget-249984.onnx} +1 -1
  3. SnowballTarget/{SnowballTarget-99960.pt → SnowballTarget-249984.pt} +1 -1
  4. SnowballTarget/{SnowballTarget-99960.onnx → SnowballTarget-299944.onnx} +1 -1
  5. SnowballTarget/{SnowballTarget-149984.pt → SnowballTarget-299944.pt} +1 -1
  6. SnowballTarget/{SnowballTarget-49936.onnx → SnowballTarget-349968.onnx} +1 -1
  7. SnowballTarget/{SnowballTarget-49936.pt → SnowballTarget-349968.pt} +1 -1
  8. SnowballTarget/SnowballTarget-399968.onnx +3 -0
  9. SnowballTarget/SnowballTarget-399968.pt +3 -0
  10. SnowballTarget/SnowballTarget-449992.onnx +3 -0
  11. SnowballTarget/SnowballTarget-449992.pt +3 -0
  12. SnowballTarget/SnowballTarget-499952.onnx +3 -0
  13. SnowballTarget/SnowballTarget-499952.pt +3 -0
  14. SnowballTarget/SnowballTarget-500016.onnx +3 -0
  15. SnowballTarget/SnowballTarget-500016.pt +3 -0
  16. SnowballTarget/checkpoint.pt +1 -1
  17. SnowballTarget/events.out.tfevents.1683812688.0f179e1dc6c5.12677.0 +3 -0
  18. SnowballTarget/events.out.tfevents.1683812711.0f179e1dc6c5.12828.0 +3 -0
  19. config.json +1 -1
  20. configuration.yaml +2 -2
  21. run_logs/Player-0.log +14 -17
  22. run_logs/timers.json +192 -192
  23. run_logs/training_status.json +74 -29
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2679e4ecf25657b31e5d46670ac96e7fd0b2d1cc193f6db57d0c1d9e328bf891
3
  size 910131
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d13a1d07960c7e2dbf58789ab492a4b2ede5041fab5a706a8bde90e952089876
3
  size 910131
SnowballTarget/{SnowballTarget-149984.onnx → SnowballTarget-249984.onnx} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca7b4b2d1ba94549b6a5e7948936155a72029f64097cf9f903d1d4a66e1dad68
3
  size 910131
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:148c65813e7c9b13d3a72f76ce10ef29ad6345f081dcb9cecc1ed1dbdfdeb7b3
3
  size 910131
SnowballTarget/{SnowballTarget-99960.pt → SnowballTarget-249984.pt} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b3f386f547af3b3bd1d3d0adcd55e82355394036a1397c877b31d305af4aa060
3
  size 5827622
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db713c3ba93b85d15a1bcd3a999e00829e46c85458e7268569ca5dc559834511
3
  size 5827622
SnowballTarget/{SnowballTarget-99960.onnx → SnowballTarget-299944.onnx} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a105b1aac6a8fe3242f4c4b956fb5a34881afbea91a461b2a900e68b0d61f89c
3
  size 910131
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:571c2d2ec0c800cb3a050a82058ad6efa17cdb9812ec49027f1203e45ed3ced7
3
  size 910131
SnowballTarget/{SnowballTarget-149984.pt → SnowballTarget-299944.pt} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:25d69cdf4e496a5e392994db17aa565f2e21a10c0fbff507961eb7e120372b6e
3
  size 5827622
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d08f2a812644adc5839b492f78c9896fca65f04c2d2f6aba40b6a1806953290b
3
  size 5827622
SnowballTarget/{SnowballTarget-49936.onnx → SnowballTarget-349968.onnx} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0917c76b977e4aa9f7be60cbab03ecea2dc00bf35df101dda9e1165da970ec11
3
  size 910131
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9ce5602383755cc7c8c5dd64f147810352983b9a20ef94137b190ae6eaaa6db
3
  size 910131
SnowballTarget/{SnowballTarget-49936.pt → SnowballTarget-349968.pt} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ebc9a913bd3ab6ddf0e5c63ab22affff34535785d93bd812b508dea5f5ed85d5
3
  size 5827622
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95b2c830ee7a14140b7f84e3669f7c5869f0a5791a78009e73f50de18b303768
3
  size 5827622
SnowballTarget/SnowballTarget-399968.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f5ff4eb2b69b1ebdd653aa0bc9d7ae6e4502d26111a6f65cf43cfa8b5a5914e
3
+ size 910131
SnowballTarget/SnowballTarget-399968.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b41a38f9e55c830b81c6d0301ce20773095125c6c09b5fd0b9b47ddb6210be83
3
+ size 5827622
SnowballTarget/SnowballTarget-449992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ac33c3afaef5938e2042df464a52b170caf555f9b709a9ce41ee12e851ef626
3
+ size 910131
SnowballTarget/SnowballTarget-449992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d72d6fdb204679c3a605146a54d1daa6f3dba29698563c7d78c47045fd2658c6
3
+ size 5827622
SnowballTarget/SnowballTarget-499952.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d13a1d07960c7e2dbf58789ab492a4b2ede5041fab5a706a8bde90e952089876
3
+ size 910131
SnowballTarget/SnowballTarget-499952.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1facb5308cc1617b6e27f1e75b7f37fbb19e1728623c9ed53082b06115e9fcec
3
+ size 5827622
SnowballTarget/SnowballTarget-500016.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d13a1d07960c7e2dbf58789ab492a4b2ede5041fab5a706a8bde90e952089876
3
+ size 910131
SnowballTarget/SnowballTarget-500016.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa12f2b7eb5f844a652f473c752065577fa6d9b132c66de2eac873cf86a460fd
3
+ size 5827622
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ad0703609ab5a669b2f33261545589b3cefc8732656bdf27ca525331eda35b3f
3
  size 5827622
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa12f2b7eb5f844a652f473c752065577fa6d9b132c66de2eac873cf86a460fd
3
  size 5827622
SnowballTarget/events.out.tfevents.1683812688.0f179e1dc6c5.12677.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6da926a93bb8c73f0f81cb0192411694b7f0d1f8be67fac4618e8bb74609c0dd
3
+ size 1426
SnowballTarget/events.out.tfevents.1683812711.0f179e1dc6c5.12828.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe0786488ed303da17282fe2a8701dbb4b5530794a85f51c6fafbfd1a2404603
3
+ size 29980
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 32, "buffer_size": 16384, "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": 3, "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}}, "curiosity": {"gamma": 0.99, "strength": 0.1, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "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": 32, "buffer_size": 16384, "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": 3, "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}}, "curiosity": {"gamma": 0.99, "strength": 0.1, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "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", "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
@@ -51,7 +51,7 @@ behaviors:
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 +80,7 @@ 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
 
51
  init_path: null
52
  keep_checkpoints: 10
53
  even_checkpoints: false
54
+ max_steps: 500000
55
  time_horizon: 64
56
  summary_freq: 10000
57
  threaded: true
 
80
  run_id: SnowballTarget1
81
  initialize_from: null
82
  load_model: false
83
+ resume: true
84
  force: false
85
  train_model: false
86
  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 0.087 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: 0.827891 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
@@ -169,19 +166,19 @@ Memory Statistics:
169
  Peak Allocated Bytes 0 B
170
  Overflow Count 0
171
  [ALLOC_DEFAULT] Dual Thread Allocator
172
- Peak main deferred allocation count 45
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 6.7 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
@@ -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]: 4581 frames, [64.0 KB-128.0 KB]: 882 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
- Peak Allocated memory 66.4 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 0.081 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: 0.910023 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]: 8050 frames, [16.0 KB-32.0 KB]: 136 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 37
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]: 8187 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
+ Peak Allocated memory 7.3 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 8187 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
  Peak Allocated memory 17.8 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]: 7569 frames, [64.0 KB-128.0 KB]: 618 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]: 8187 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]: 8187 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]: 8186 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]: 8187 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]: 8187 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
@@ -2,261 +2,261 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 2.385432004928589,
6
- "min": 2.385432004928589,
7
- "max": 2.8903470039367676,
8
- "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 22907.3046875,
12
- "min": 22907.3046875,
13
- "max": 29695.42578125,
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": 4.15912389755249,
30
- "min": 0.013997421599924564,
31
- "max": 4.15912389755249,
32
- "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 811.0291748046875,
36
- "min": 2.7154998779296875,
37
- "max": 811.0291748046875,
38
- "count": 20
39
  },
40
  "SnowballTarget.Policy.CuriosityValueEstimate.mean": {
41
- "value": 0.33712518215179443,
42
- "min": 0.0004443278885446489,
43
- "max": 0.33712518215179443,
44
- "count": 20
45
  },
46
  "SnowballTarget.Policy.CuriosityValueEstimate.sum": {
47
- "value": 65.73941040039062,
48
- "min": 0.08619961142539978,
49
- "max": 67.01959228515625,
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.Environment.CumulativeReward.mean": {
65
- "value": 14.818181818181818,
66
- "min": 3.090909090909091,
67
- "max": 14.818181818181818,
68
- "count": 20
69
  },
70
  "SnowballTarget.Environment.CumulativeReward.sum": {
71
- "value": 652.0,
72
- "min": 136.0,
73
- "max": 786.0,
74
- "count": 20
75
  },
76
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
77
- "value": 14.818181818181818,
78
- "min": 3.090909090909091,
79
- "max": 14.818181818181818,
80
- "count": 20
81
  },
82
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
83
- "value": 652.0,
84
- "min": 136.0,
85
- "max": 786.0,
86
- "count": 20
87
  },
88
  "SnowballTarget.Policy.CuriosityReward.mean": {
89
- "value": 0.9024262693922289,
90
  "min": 0.0,
91
- "max": 1.07683557609993,
92
- "count": 20
93
  },
94
  "SnowballTarget.Policy.CuriosityReward.sum": {
95
- "value": 39.70675585325807,
96
  "min": 0.0,
97
- "max": 58.14912110939622,
98
- "count": 20
99
  },
100
  "SnowballTarget.IsTraining.mean": {
101
  "value": 1.0,
102
  "min": 1.0,
103
  "max": 1.0,
104
- "count": 20
105
  },
106
  "SnowballTarget.IsTraining.sum": {
107
  "value": 1.0,
108
  "min": 1.0,
109
  "max": 1.0,
110
- "count": 20
111
  },
112
  "SnowballTarget.Losses.PolicyLoss.mean": {
113
- "value": 0.14216311709067075,
114
- "min": 0.13723099632516236,
115
- "max": 0.14307166072689548,
116
- "count": 11
117
  },
118
  "SnowballTarget.Losses.PolicyLoss.sum": {
119
- "value": 0.14216311709067075,
120
- "min": 0.13723099632516236,
121
- "max": 0.14307166072689548,
122
- "count": 11
123
  },
124
  "SnowballTarget.Losses.ValueLoss.mean": {
125
- "value": 0.14027505533482704,
126
- "min": 0.045727412595990155,
127
- "max": 0.14027505533482704,
128
- "count": 11
129
  },
130
  "SnowballTarget.Losses.ValueLoss.sum": {
131
- "value": 0.14027505533482704,
132
- "min": 0.045727412595990155,
133
- "max": 0.14027505533482704,
134
- "count": 11
135
  },
136
  "SnowballTarget.Policy.LearningRate.mean": {
137
- "value": 2.2932092355999987e-05,
138
- "min": 2.2932092355999987e-05,
139
- "max": 0.000274788008404,
140
- "count": 11
141
  },
142
  "SnowballTarget.Policy.LearningRate.sum": {
143
- "value": 2.2932092355999987e-05,
144
- "min": 2.2932092355999987e-05,
145
- "max": 0.000274788008404,
146
- "count": 11
147
  },
148
  "SnowballTarget.Policy.Epsilon.mean": {
149
- "value": 0.107644,
150
- "min": 0.107644,
151
- "max": 0.19159600000000004,
152
- "count": 11
153
  },
154
  "SnowballTarget.Policy.Epsilon.sum": {
155
- "value": 0.107644,
156
- "min": 0.107644,
157
- "max": 0.19159600000000004,
158
- "count": 11
159
  },
160
  "SnowballTarget.Policy.Beta.mean": {
161
- "value": 0.00039143559999999975,
162
- "min": 0.00039143559999999975,
163
- "max": 0.0045806404000000005,
164
- "count": 11
165
  },
166
  "SnowballTarget.Policy.Beta.sum": {
167
- "value": 0.00039143559999999975,
168
- "min": 0.00039143559999999975,
169
- "max": 0.0045806404000000005,
170
- "count": 11
171
  },
172
  "SnowballTarget.Losses.CuriosityForwardLoss.mean": {
173
- "value": 0.04660418435455637,
174
- "min": 0.03838069728324338,
175
- "max": 0.07110486752575353,
176
- "count": 11
177
  },
178
  "SnowballTarget.Losses.CuriosityForwardLoss.sum": {
179
- "value": 0.04660418435455637,
180
- "min": 0.03838069728324338,
181
- "max": 0.07110486752575353,
182
- "count": 11
183
  },
184
  "SnowballTarget.Losses.CuriosityInverseLoss.mean": {
185
- "value": 2.065821149824205,
186
- "min": 2.065821149824205,
187
- "max": 2.756891046554323,
188
- "count": 11
189
  },
190
  "SnowballTarget.Losses.CuriosityInverseLoss.sum": {
191
- "value": 2.065821149824205,
192
- "min": 2.065821149824205,
193
- "max": 2.756891046554323,
194
- "count": 11
195
  }
196
  },
197
  "metadata": {
198
  "timer_format_version": "0.1.0",
199
- "start_time_seconds": "1683811596",
200
  "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]",
201
- "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
202
  "mlagents_version": "0.31.0.dev0",
203
  "mlagents_envs_version": "0.31.0.dev0",
204
  "communication_protocol_version": "1.5.0",
205
  "pytorch_version": "1.11.0+cu102",
206
  "numpy_version": "1.21.2",
207
- "end_time_seconds": "1683812358"
208
  },
209
- "total": 761.7432244089998,
210
  "count": 1,
211
- "self": 0.43862323299958916,
212
  "children": {
213
  "run_training.setup": {
214
- "total": 0.04238357899998846,
215
  "count": 1,
216
- "self": 0.04238357899998846
217
  },
218
  "TrainerController.start_learning": {
219
- "total": 761.2622175970002,
220
  "count": 1,
221
- "self": 0.5552386300096259,
222
  "children": {
223
  "TrainerController._reset_env": {
224
- "total": 3.8741584639999473,
225
  "count": 1,
226
- "self": 3.8741584639999473
227
  },
228
  "TrainerController.advance": {
229
- "total": 756.681970258991,
230
- "count": 18207,
231
- "self": 0.2753362879659562,
232
  "children": {
233
  "env_step": {
234
- "total": 756.406633971025,
235
- "count": 18207,
236
- "self": 643.0490705560201,
237
  "children": {
238
  "SubprocessEnvManager._take_step": {
239
- "total": 113.09053104500686,
240
- "count": 18207,
241
- "self": 2.0404263569810155,
242
  "children": {
243
  "TorchPolicy.evaluate": {
244
- "total": 111.05010468802584,
245
- "count": 18207,
246
- "self": 111.05010468802584
247
  }
248
  }
249
  },
250
  "workers": {
251
- "total": 0.2670323699981054,
252
- "count": 18207,
253
  "self": 0.0,
254
  "children": {
255
  "worker_root": {
256
- "total": 759.8618616810047,
257
- "count": 18207,
258
  "is_parallel": true,
259
- "self": 514.9759165389949,
260
  "children": {
261
  "run_training.setup": {
262
  "total": 0.0,
@@ -265,48 +265,48 @@
265
  "self": 0.0,
266
  "children": {
267
  "steps_from_proto": {
268
- "total": 0.005080220000081681,
269
  "count": 1,
270
  "is_parallel": true,
271
- "self": 0.00354788400045436,
272
  "children": {
273
  "_process_rank_one_or_two_observation": {
274
- "total": 0.0015323359996273211,
275
  "count": 10,
276
  "is_parallel": true,
277
- "self": 0.0015323359996273211
278
  }
279
  }
280
  },
281
  "UnityEnvironment.step": {
282
- "total": 0.04351448300008087,
283
  "count": 1,
284
  "is_parallel": true,
285
- "self": 0.000659725000105027,
286
  "children": {
287
  "UnityEnvironment._generate_step_input": {
288
- "total": 0.00037621799992848537,
289
  "count": 1,
290
  "is_parallel": true,
291
- "self": 0.00037621799992848537
292
  },
293
  "communicator.exchange": {
294
- "total": 0.04028667900001892,
295
  "count": 1,
296
  "is_parallel": true,
297
- "self": 0.04028667900001892
298
  },
299
  "steps_from_proto": {
300
- "total": 0.002191861000028439,
301
  "count": 1,
302
  "is_parallel": true,
303
- "self": 0.00043742000002566783,
304
  "children": {
305
  "_process_rank_one_or_two_observation": {
306
- "total": 0.001754441000002771,
307
  "count": 10,
308
  "is_parallel": true,
309
- "self": 0.001754441000002771
310
  }
311
  }
312
  }
@@ -315,34 +315,34 @@
315
  }
316
  },
317
  "UnityEnvironment.step": {
318
- "total": 244.88594514200986,
319
- "count": 18206,
320
  "is_parallel": true,
321
- "self": 10.038581193020491,
322
  "children": {
323
  "UnityEnvironment._generate_step_input": {
324
- "total": 5.299940268000682,
325
- "count": 18206,
326
  "is_parallel": true,
327
- "self": 5.299940268000682
328
  },
329
  "communicator.exchange": {
330
- "total": 196.67254681099803,
331
- "count": 18206,
332
  "is_parallel": true,
333
- "self": 196.67254681099803
334
  },
335
  "steps_from_proto": {
336
- "total": 32.87487686999066,
337
- "count": 18206,
338
  "is_parallel": true,
339
- "self": 6.261275034059963,
340
  "children": {
341
  "_process_rank_one_or_two_observation": {
342
- "total": 26.613601835930695,
343
- "count": 182060,
344
  "is_parallel": true,
345
- "self": 26.613601835930695
346
  }
347
  }
348
  }
@@ -357,9 +357,9 @@
357
  }
358
  },
359
  "trainer_threads": {
360
- "total": 0.00014040799987924402,
361
  "count": 1,
362
- "self": 0.00014040799987924402,
363
  "children": {
364
  "thread_root": {
365
  "total": 0.0,
@@ -368,36 +368,36 @@
368
  "self": 0.0,
369
  "children": {
370
  "trainer_advance": {
371
- "total": 751.8785557158856,
372
- "count": 543778,
373
  "is_parallel": true,
374
- "self": 13.25509078697769,
375
  "children": {
376
  "process_trajectory": {
377
- "total": 354.3881192759077,
378
- "count": 543778,
379
  "is_parallel": true,
380
- "self": 353.0601057139072,
381
  "children": {
382
  "RLTrainer._checkpoint": {
383
- "total": 1.3280135620004785,
384
- "count": 4,
385
  "is_parallel": true,
386
- "self": 1.3280135620004785
387
  }
388
  }
389
  },
390
  "_update_policy": {
391
- "total": 384.2353456530002,
392
- "count": 11,
393
  "is_parallel": true,
394
- "self": 200.98167754598535,
395
  "children": {
396
  "TorchPPOOptimizer.update": {
397
- "total": 183.25366810701485,
398
- "count": 17313,
399
  "is_parallel": true,
400
- "self": 183.25366810701485
401
  }
402
  }
403
  }
@@ -408,14 +408,14 @@
408
  }
409
  },
410
  "TrainerController._save_models": {
411
- "total": 0.15070983599980536,
412
  "count": 1,
413
- "self": 0.0010795619996315509,
414
  "children": {
415
  "RLTrainer._checkpoint": {
416
- "total": 0.1496302740001738,
417
  "count": 1,
418
- "self": 0.1496302740001738
419
  }
420
  }
421
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 1.6185333728790283,
6
+ "min": 1.6185333728790283,
7
+ "max": 2.3890488147735596,
8
+ "count": 30
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 15685.20703125,
12
+ "min": 15685.20703125,
13
+ "max": 24492.52734375,
14
+ "count": 30
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 499952.0,
18
+ "min": 209936.0,
19
+ "max": 499952.0,
20
+ "count": 30
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 499952.0,
24
+ "min": 209936.0,
25
+ "max": 499952.0,
26
+ "count": 30
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 10.35067081451416,
30
+ "min": 4.125368118286133,
31
+ "max": 10.35067081451416,
32
+ "count": 30
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2111.536865234375,
36
+ "min": 792.0706787109375,
37
+ "max": 2111.536865234375,
38
+ "count": 30
39
  },
40
  "SnowballTarget.Policy.CuriosityValueEstimate.mean": {
41
+ "value": 0.41174212098121643,
42
+ "min": 0.29970523715019226,
43
+ "max": 0.41174212098121643,
44
+ "count": 30
45
  },
46
  "SnowballTarget.Policy.CuriosityValueEstimate.sum": {
47
+ "value": 83.99539184570312,
48
+ "min": 58.44252014160156,
49
+ "max": 83.99539184570312,
50
+ "count": 30
51
  },
52
  "SnowballTarget.Environment.EpisodeLength.mean": {
53
  "value": 199.0,
54
  "min": 199.0,
55
  "max": 199.0,
56
+ "count": 30
57
  },
58
  "SnowballTarget.Environment.EpisodeLength.sum": {
59
  "value": 10945.0,
60
  "min": 8756.0,
61
  "max": 10945.0,
62
+ "count": 30
63
  },
64
  "SnowballTarget.Environment.CumulativeReward.mean": {
65
+ "value": 24.2,
66
+ "min": 15.0,
67
+ "max": 24.2,
68
+ "count": 30
69
  },
70
  "SnowballTarget.Environment.CumulativeReward.sum": {
71
+ "value": 1331.0,
72
+ "min": 683.0,
73
+ "max": 1331.0,
74
+ "count": 30
75
  },
76
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
77
+ "value": 24.2,
78
+ "min": 15.0,
79
+ "max": 24.2,
80
+ "count": 30
81
  },
82
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
83
+ "value": 1331.0,
84
+ "min": 683.0,
85
+ "max": 1331.0,
86
+ "count": 30
87
  },
88
  "SnowballTarget.Policy.CuriosityReward.mean": {
89
+ "value": 0.9702810207551176,
90
  "min": 0.0,
91
+ "max": 0.9702810207551176,
92
+ "count": 30
93
  },
94
  "SnowballTarget.Policy.CuriosityReward.sum": {
95
+ "value": 53.36545614153147,
96
  "min": 0.0,
97
+ "max": 53.36545614153147,
98
+ "count": 30
99
  },
100
  "SnowballTarget.IsTraining.mean": {
101
  "value": 1.0,
102
  "min": 1.0,
103
  "max": 1.0,
104
+ "count": 30
105
  },
106
  "SnowballTarget.IsTraining.sum": {
107
  "value": 1.0,
108
  "min": 1.0,
109
  "max": 1.0,
110
+ "count": 30
111
  },
112
  "SnowballTarget.Losses.PolicyLoss.mean": {
113
+ "value": 0.14052760786062757,
114
+ "min": 0.13743979886894153,
115
+ "max": 0.14526880568945744,
116
+ "count": 17
117
  },
118
  "SnowballTarget.Losses.PolicyLoss.sum": {
119
+ "value": 0.14052760786062757,
120
+ "min": 0.13743979886894153,
121
+ "max": 0.14526880568945744,
122
+ "count": 17
123
  },
124
  "SnowballTarget.Losses.ValueLoss.mean": {
125
+ "value": 0.11250105779085841,
126
+ "min": 0.1080041357898523,
127
+ "max": 0.1483479710065183,
128
+ "count": 17
129
  },
130
  "SnowballTarget.Losses.ValueLoss.sum": {
131
+ "value": 0.11250105779085841,
132
+ "min": 0.1080041357898523,
133
+ "max": 0.1483479710065183,
134
+ "count": 17
135
  },
136
  "SnowballTarget.Policy.LearningRate.mean": {
137
+ "value": 8.385697204799993e-06,
138
+ "min": 8.385697204799993e-06,
139
+ "max": 0.00016984804338399998,
140
+ "count": 17
141
  },
142
  "SnowballTarget.Policy.LearningRate.sum": {
143
+ "value": 8.385697204799993e-06,
144
+ "min": 8.385697204799993e-06,
145
+ "max": 0.00016984804338399998,
146
+ "count": 17
147
  },
148
  "SnowballTarget.Policy.Epsilon.mean": {
149
+ "value": 0.1027952,
150
+ "min": 0.1027952,
151
+ "max": 0.15661600000000006,
152
+ "count": 17
153
  },
154
  "SnowballTarget.Policy.Epsilon.sum": {
155
+ "value": 0.1027952,
156
+ "min": 0.1027952,
157
+ "max": 0.15661600000000006,
158
+ "count": 17
159
  },
160
  "SnowballTarget.Policy.Beta.mean": {
161
+ "value": 0.00014948047999999988,
162
+ "min": 0.00014948047999999988,
163
+ "max": 0.0028351384000000006,
164
+ "count": 17
165
  },
166
  "SnowballTarget.Policy.Beta.sum": {
167
+ "value": 0.00014948047999999988,
168
+ "min": 0.00014948047999999988,
169
+ "max": 0.0028351384000000006,
170
+ "count": 17
171
  },
172
  "SnowballTarget.Losses.CuriosityForwardLoss.mean": {
173
+ "value": 0.04631114746370013,
174
+ "min": 0.03979384261582579,
175
+ "max": 0.05177491479153472,
176
+ "count": 17
177
  },
178
  "SnowballTarget.Losses.CuriosityForwardLoss.sum": {
179
+ "value": 0.04631114746370013,
180
+ "min": 0.03979384261582579,
181
+ "max": 0.05177491479153472,
182
+ "count": 17
183
  },
184
  "SnowballTarget.Losses.CuriosityInverseLoss.mean": {
185
+ "value": 1.4249065720845782,
186
+ "min": 1.4249065720845782,
187
+ "max": 2.0070621078733413,
188
+ "count": 17
189
  },
190
  "SnowballTarget.Losses.CuriosityInverseLoss.sum": {
191
+ "value": 1.4249065720845782,
192
+ "min": 1.4249065720845782,
193
+ "max": 2.0070621078733413,
194
+ "count": 17
195
  }
196
  },
197
  "metadata": {
198
  "timer_format_version": "0.1.0",
199
+ "start_time_seconds": "1683812710",
200
  "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]",
201
+ "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",
202
  "mlagents_version": "0.31.0.dev0",
203
  "mlagents_envs_version": "0.31.0.dev0",
204
  "communication_protocol_version": "1.5.0",
205
  "pytorch_version": "1.11.0+cu102",
206
  "numpy_version": "1.21.2",
207
+ "end_time_seconds": "1683813838"
208
  },
209
+ "total": 1127.5446133629998,
210
  "count": 1,
211
+ "self": 0.7297791769997275,
212
  "children": {
213
  "run_training.setup": {
214
+ "total": 0.039653480000197305,
215
  "count": 1,
216
+ "self": 0.039653480000197305
217
  },
218
  "TrainerController.start_learning": {
219
+ "total": 1126.775180706,
220
  "count": 1,
221
+ "self": 0.7847868159728932,
222
  "children": {
223
  "TrainerController._reset_env": {
224
+ "total": 3.5591430199997376,
225
  "count": 1,
226
+ "self": 3.5591430199997376
227
  },
228
  "TrainerController.advance": {
229
+ "total": 1122.160470015027,
230
+ "count": 27287,
231
+ "self": 0.37183532803874186,
232
  "children": {
233
  "env_step": {
234
+ "total": 1121.7886346869882,
235
+ "count": 27287,
236
+ "self": 957.4939411440519,
237
  "children": {
238
  "SubprocessEnvManager._take_step": {
239
+ "total": 163.90950036098184,
240
+ "count": 27287,
241
+ "self": 2.7304017519550143,
242
  "children": {
243
  "TorchPolicy.evaluate": {
244
+ "total": 161.17909860902682,
245
+ "count": 27287,
246
+ "self": 161.17909860902682
247
  }
248
  }
249
  },
250
  "workers": {
251
+ "total": 0.3851931819544916,
252
+ "count": 27287,
253
  "self": 0.0,
254
  "children": {
255
  "worker_root": {
256
+ "total": 1124.6364629710201,
257
+ "count": 27287,
258
  "is_parallel": true,
259
+ "self": 766.363746886037,
260
  "children": {
261
  "run_training.setup": {
262
  "total": 0.0,
 
265
  "self": 0.0,
266
  "children": {
267
  "steps_from_proto": {
268
+ "total": 0.0019262570003775181,
269
  "count": 1,
270
  "is_parallel": true,
271
+ "self": 0.0006033180002305016,
272
  "children": {
273
  "_process_rank_one_or_two_observation": {
274
+ "total": 0.0013229390001470165,
275
  "count": 10,
276
  "is_parallel": true,
277
+ "self": 0.0013229390001470165
278
  }
279
  }
280
  },
281
  "UnityEnvironment.step": {
282
+ "total": 0.03693232599971452,
283
  "count": 1,
284
  "is_parallel": true,
285
+ "self": 0.000581247999889456,
286
  "children": {
287
  "UnityEnvironment._generate_step_input": {
288
+ "total": 0.000326738999774534,
289
  "count": 1,
290
  "is_parallel": true,
291
+ "self": 0.000326738999774534
292
  },
293
  "communicator.exchange": {
294
+ "total": 0.033779210000375315,
295
  "count": 1,
296
  "is_parallel": true,
297
+ "self": 0.033779210000375315
298
  },
299
  "steps_from_proto": {
300
+ "total": 0.0022451289996752166,
301
  "count": 1,
302
  "is_parallel": true,
303
+ "self": 0.0005249089990684297,
304
  "children": {
305
  "_process_rank_one_or_two_observation": {
306
+ "total": 0.001720220000606787,
307
  "count": 10,
308
  "is_parallel": true,
309
+ "self": 0.001720220000606787
310
  }
311
  }
312
  }
 
315
  }
316
  },
317
  "UnityEnvironment.step": {
318
+ "total": 358.27271608498313,
319
+ "count": 27286,
320
  "is_parallel": true,
321
+ "self": 14.223715283988895,
322
  "children": {
323
  "UnityEnvironment._generate_step_input": {
324
+ "total": 7.861399810001785,
325
+ "count": 27286,
326
  "is_parallel": true,
327
+ "self": 7.861399810001785
328
  },
329
  "communicator.exchange": {
330
+ "total": 287.70915352500015,
331
+ "count": 27286,
332
  "is_parallel": true,
333
+ "self": 287.70915352500015
334
  },
335
  "steps_from_proto": {
336
+ "total": 48.4784474659923,
337
+ "count": 27286,
338
  "is_parallel": true,
339
+ "self": 9.105429239834848,
340
  "children": {
341
  "_process_rank_one_or_two_observation": {
342
+ "total": 39.373018226157456,
343
+ "count": 272860,
344
  "is_parallel": true,
345
+ "self": 39.373018226157456
346
  }
347
  }
348
  }
 
357
  }
358
  },
359
  "trainer_threads": {
360
+ "total": 4.6364000354515156e-05,
361
  "count": 1,
362
+ "self": 4.6364000354515156e-05,
363
  "children": {
364
  "thread_root": {
365
  "total": 0.0,
 
368
  "self": 0.0,
369
  "children": {
370
  "trainer_advance": {
371
+ "total": 1115.195070694926,
372
+ "count": 794249,
373
  "is_parallel": true,
374
+ "self": 18.099510688789906,
375
  "children": {
376
  "process_trajectory": {
377
+ "total": 515.2461097201353,
378
+ "count": 794249,
379
  "is_parallel": true,
380
+ "self": 512.6004755141348,
381
  "children": {
382
  "RLTrainer._checkpoint": {
383
+ "total": 2.6456342060005227,
384
+ "count": 6,
385
  "is_parallel": true,
386
+ "self": 2.6456342060005227
387
  }
388
  }
389
  },
390
  "_update_policy": {
391
+ "total": 581.8494502860008,
392
+ "count": 17,
393
  "is_parallel": true,
394
+ "self": 303.6705323810138,
395
  "children": {
396
  "TorchPPOOptimizer.update": {
397
+ "total": 278.178917904987,
398
+ "count": 26799,
399
  "is_parallel": true,
400
+ "self": 278.178917904987
401
  }
402
  }
403
  }
 
408
  }
409
  },
410
  "TrainerController._save_models": {
411
+ "total": 0.2707344909999847,
412
  "count": 1,
413
+ "self": 0.0018728250001913693,
414
  "children": {
415
  "RLTrainer._checkpoint": {
416
+ "total": 0.26886166599979333,
417
  "count": 1,
418
+ "self": 0.26886166599979333
419
  }
420
  }
421
  }
run_logs/training_status.json CHANGED
@@ -2,58 +2,103 @@
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
- "steps": 49936,
6
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 5.454545454545454,
8
- "creation_time": 1683811774.2959902,
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": 9.12987012987013,
17
- "creation_time": 1683811970.7363544,
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",
25
- "reward": 11.857142857142858,
26
- "creation_time": 1683812165.6711266,
27
  "auxillary_file_paths": [
28
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
30
  },
31
  {
32
- "steps": 199984,
33
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
34
- "reward": 14.61038961038961,
35
- "creation_time": 1683812357.8780396,
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": 14.61038961038961,
44
- "creation_time": 1683812358.059873,
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": 14.61038961038961,
54
- "creation_time": 1683812358.059873,
55
  "auxillary_file_paths": [
56
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },
 
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
+ "steps": 199984,
6
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
7
+ "reward": 14.61038961038961,
8
+ "creation_time": 1683812357.8780396,
9
  "auxillary_file_paths": [
10
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
11
  ]
12
  },
13
  {
14
+ "steps": 200112,
15
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
16
+ "reward": 14.61038961038961,
17
+ "creation_time": 1683812358.059873,
18
  "auxillary_file_paths": [
19
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
20
  ]
21
  },
22
  {
23
+ "steps": 200112,
24
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
25
+ "reward": null,
26
+ "creation_time": 1683812692.0511055,
27
  "auxillary_file_paths": [
28
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
29
  ]
30
  },
31
  {
32
+ "steps": 249984,
33
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-249984.onnx",
34
+ "reward": 16.376623376623378,
35
+ "creation_time": 1683812876.309644,
36
  "auxillary_file_paths": [
37
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-249984.pt"
38
  ]
39
  },
40
  {
41
+ "steps": 299944,
42
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-299944.onnx",
43
+ "reward": 18.792207792207794,
44
+ "creation_time": 1683813067.8789525,
45
  "auxillary_file_paths": [
46
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-299944.pt"
47
+ ]
48
+ },
49
+ {
50
+ "steps": 349968,
51
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-349968.onnx",
52
+ "reward": 20.147727272727273,
53
+ "creation_time": 1683813258.7650945,
54
+ "auxillary_file_paths": [
55
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-349968.pt"
56
+ ]
57
+ },
58
+ {
59
+ "steps": 399968,
60
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-399968.onnx",
61
+ "reward": 21.61038961038961,
62
+ "creation_time": 1683813452.530951,
63
+ "auxillary_file_paths": [
64
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-399968.pt"
65
+ ]
66
+ },
67
+ {
68
+ "steps": 449992,
69
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-449992.onnx",
70
+ "reward": 23.155844155844157,
71
+ "creation_time": 1683813644.694016,
72
+ "auxillary_file_paths": [
73
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-449992.pt"
74
+ ]
75
+ },
76
+ {
77
+ "steps": 499952,
78
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-499952.onnx",
79
+ "reward": 24.07792207792208,
80
+ "creation_time": 1683813837.019088,
81
+ "auxillary_file_paths": [
82
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-499952.pt"
83
+ ]
84
+ },
85
+ {
86
+ "steps": 500016,
87
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-500016.onnx",
88
+ "reward": 24.07792207792208,
89
+ "creation_time": 1683813837.330003,
90
+ "auxillary_file_paths": [
91
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-500016.pt"
92
  ]
93
  }
94
  ],
95
  "final_checkpoint": {
96
+ "steps": 500016,
97
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
98
+ "reward": 24.07792207792208,
99
+ "creation_time": 1683813837.330003,
100
  "auxillary_file_paths": [
101
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-500016.pt"
102
  ]
103
  }
104
  },