Hugging Face's logo

s94lopez
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
s94lopez commited on
Commit
daa7a12
·
verified ·
1 Parent(s): df83d7b

Second Push

Browse files
Files changed (28) hide show
  1. SnowballTarget.onnx +2 -2
  2. SnowballTarget/SnowballTarget-149984.onnx +2 -2
  3. SnowballTarget/SnowballTarget-149984.pt +2 -2
  4. SnowballTarget/SnowballTarget-199984.onnx +2 -2
  5. SnowballTarget/SnowballTarget-199984.pt +2 -2
  6. SnowballTarget/SnowballTarget-249880.onnx +3 -0
  7. SnowballTarget/SnowballTarget-249880.pt +3 -0
  8. SnowballTarget/SnowballTarget-299968.onnx +3 -0
  9. SnowballTarget/SnowballTarget-299968.pt +3 -0
  10. SnowballTarget/SnowballTarget-349928.onnx +3 -0
  11. SnowballTarget/SnowballTarget-349928.pt +3 -0
  12. SnowballTarget/SnowballTarget-399968.onnx +3 -0
  13. SnowballTarget/SnowballTarget-399968.pt +3 -0
  14. SnowballTarget/SnowballTarget-449952.onnx +3 -0
  15. SnowballTarget/SnowballTarget-449952.pt +3 -0
  16. SnowballTarget/SnowballTarget-499912.onnx +3 -0
  17. SnowballTarget/SnowballTarget-499912.pt +3 -0
  18. SnowballTarget/SnowballTarget-500808.onnx +3 -0
  19. SnowballTarget/SnowballTarget-500808.pt +3 -0
  20. SnowballTarget/SnowballTarget-99896.onnx +3 -0
  21. SnowballTarget/SnowballTarget-99896.pt +3 -0
  22. SnowballTarget/checkpoint.pt +2 -2
  23. SnowballTarget/events.out.tfevents.1745188861.3e769864649d.3063.0 +3 -0
  24. config.json +1 -1
  25. configuration.yaml +11 -11
  26. run_logs/Player-0.log +15 -15
  27. run_logs/timers.json +177 -177
  28. run_logs/training_status.json +72 -27
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:39d9b21a460f98fd4b86f6dfc7bc7f128fbd71e998bc52531401d0e2454a7bf9
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f1b067903f7344100f7d5f5a1a4d190c443f5503993146effa44205ea091f2f
3
+ size 1823189
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a8b841c99e29bbf9879b04d442439eb7be7b22188c7221cdc0bc7ad20017e997
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6194e579e67679fb6a5fcf025cb6616e616915c63b1295764559442fdc2a160c
3
+ size 1823189
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c6e38fe5ce778a98740971ff3a92a1056b5d99395640b52ae2f12ce655d53b8a
3
- size 3850075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b91df028bce4b3aa0188bc282b939eed4467a09e460dba691cd2daf45da4258
3
+ size 10842534
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:39d9b21a460f98fd4b86f6dfc7bc7f128fbd71e998bc52531401d0e2454a7bf9
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:631c91c63e949049a26f522d3c117c95fa0a2aab0a8358408fdfb833ee3e801d
3
+ size 1823189
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d28c3951743517d03545f2f910b83d877cd0cf020f073003852d31fa2ab1b4f
3
- size 3850075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b62174e029b811a769614003b2cf4a56bc370d9fd5408f817e3c5293b695cac0
3
+ size 10842534
SnowballTarget/SnowballTarget-249880.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ade2dfe8857aa1dfd0b1754f4eae0c5cf61211791a9d42476cd8119c8f9553c5
3
+ size 1823189
SnowballTarget/SnowballTarget-249880.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a0502e9326224bdd5606628830290fcbc9e5001f44055da1d3b5221372ee006
3
+ size 10842534
SnowballTarget/SnowballTarget-299968.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a44a87ad60bb54bf21961f16676eb159043c8476ae49c4ee4f04fa3bd09a0305
3
+ size 1823189
SnowballTarget/SnowballTarget-299968.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c163e9b7e22e3b3b5d1efcdb3ac1c0c56a647257e21b93461875a8db4c4d5da
3
+ size 10842534
SnowballTarget/SnowballTarget-349928.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8aac68dce3cacd0bf0719088d57ca7af548839deeca2e5e7bb5eadb38b9089a9
3
+ size 1823189
SnowballTarget/SnowballTarget-349928.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:441146362e8eea6482ea5732acc0e95b01fec734610c86f086742ee4c3460b2e
3
+ size 10842534
SnowballTarget/SnowballTarget-399968.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a5c46592998148a659c865fe1f76b955e1612acee7275f930297c8381041362
3
+ size 1823189
SnowballTarget/SnowballTarget-399968.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5344bdfd9cb5e1874bd0a99c5253c83685c8f564c65ac74ea7bafd64953ce975
3
+ size 10842534
SnowballTarget/SnowballTarget-449952.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de3cdcc72af2c0e288c7d670afc881ed79a2cc543ca4d8551295ebc50388e7d1
3
+ size 1823189
SnowballTarget/SnowballTarget-449952.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36e0ccca1afd449c7dd7509ed788ca24001db56abcc25874cde986f3c2b69e28
3
+ size 10842534
SnowballTarget/SnowballTarget-499912.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24cd05b6a4d75dc637d1a69c3d39303dc3207df2b0fe9ae9e6bba26e3b83c978
3
+ size 1823189
SnowballTarget/SnowballTarget-499912.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9daf4204d977e858c148949ae69699592323a848ad0f4b9f4ef047bddaf5d184
3
+ size 10842534
SnowballTarget/SnowballTarget-500808.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f1b067903f7344100f7d5f5a1a4d190c443f5503993146effa44205ea091f2f
3
+ size 1823189
SnowballTarget/SnowballTarget-500808.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58340d15ac5124ada4b9dd59256ad2bcaaf10123c4f52ffbb0b1cc506701aec3
3
+ size 10842534
SnowballTarget/SnowballTarget-99896.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4d8108683ef3ea6eb0b110eb8357fb4b7b9ee1bedf8a5f1f227e7c7509aba2d
3
+ size 1823189
SnowballTarget/SnowballTarget-99896.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da91e165dfa032a6facb57b947c9dd230e35a87d53400d02bf9fe7a7f8779e90
3
+ size 10842429
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:92e573d225cf289f2807a8fdd71a32a7c0a60154a421eb66da972ac91dfc7c25
3
- size 3849250
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2271bf483832ffab8f231b0a94c6b5838a94b52e188b564310a42f6f50efacb
3
+ size 10841379
SnowballTarget/events.out.tfevents.1745188861.3e769864649d.3063.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9aea539a55458df69de5516f0c62ac67a4de869b0355ed018dfa72d4ece65bef
3
+ size 57510
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": false, "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, "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": 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": 256, "buffer_size": 4096, "learning_rate": 0.00025, "beta": 0.001, "epsilon": 0.2, "lambd": 0.97, "num_epoch": 5, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": true, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.995, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 500000, "time_horizon": 128, "summary_freq": 10000, "threaded": false, "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, "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": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -3,21 +3,21 @@ behaviors:
3
  SnowballTarget:
4
  trainer_type: ppo
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
12
- num_epoch: 3
13
  shared_critic: false
14
  learning_rate_schedule: linear
15
  beta_schedule: linear
16
  epsilon_schedule: linear
17
  checkpoint_interval: 50000
18
  network_settings:
19
- normalize: false
20
- hidden_units: 256
21
  num_layers: 2
22
  vis_encode_type: simple
23
  memory: null
@@ -25,7 +25,7 @@ behaviors:
25
  deterministic: false
26
  reward_signals:
27
  extrinsic:
28
- gamma: 0.99
29
  strength: 1.0
30
  network_settings:
31
  normalize: false
@@ -38,8 +38,8 @@ 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: false
45
  self_play: null
 
3
  SnowballTarget:
4
  trainer_type: ppo
5
  hyperparameters:
6
+ batch_size: 256
7
+ buffer_size: 4096
8
+ learning_rate: 0.00025
9
+ beta: 0.001
10
  epsilon: 0.2
11
+ lambd: 0.97
12
+ num_epoch: 5
13
  shared_critic: false
14
  learning_rate_schedule: linear
15
  beta_schedule: linear
16
  epsilon_schedule: linear
17
  checkpoint_interval: 50000
18
  network_settings:
19
+ normalize: true
20
+ hidden_units: 512
21
  num_layers: 2
22
  vis_encode_type: simple
23
  memory: null
 
25
  deterministic: false
26
  reward_signals:
27
  extrinsic:
28
+ gamma: 0.995
29
  strength: 1.0
30
  network_settings:
31
  normalize: false
 
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
+ max_steps: 500000
42
+ time_horizon: 128
43
  summary_freq: 10000
44
  threaded: false
45
  self_play: null
run_logs/Player-0.log CHANGED
@@ -34,7 +34,7 @@ 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 0.096 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 +45,7 @@ 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: 0.742326 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 +53,7 @@ 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]: 5367 frames, [16.0 KB-32.0 KB]: 90 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 +169,22 @@ Memory Statistics:
169
  Peak Allocated Bytes 0 B
170
  Overflow Count 0
171
  [ALLOC_DEFAULT] Dual Thread Allocator
172
- Peak main deferred allocation count 41
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]: 5458 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]: 5458 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
- Peak Allocated memory 17.7 MB
188
  Peak Large allocation bytes 16.0 MB
189
  [ALLOC_TEMP_JOB_1_FRAME]
190
  Initial Block Size 2.0 MB
@@ -213,13 +213,13 @@ 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]: 5022 frames, [64.0 KB-128.0 KB]: 436 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
- Peak Allocated memory 66.7 KB
220
  Peak Large allocation bytes 0 B
221
  [ALLOC_GFX_THREAD]
222
- Peak usage frame count: [32.0 KB-64.0 KB]: 5458 frames
223
  Requested Block Size 16.0 MB
224
  Peak Block count 1
225
  Peak Allocated memory 39.6 KB
@@ -231,13 +231,13 @@ 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]: 5458 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]: 5457 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 +249,13 @@ 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]: 5458 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]: 5458 frames
259
  Requested Block Size 2.0 MB
260
  Peak Block count 1
261
  Peak Allocated memory 1.7 KB
 
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 0.086 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
  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: 0.708488 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
  [ALLOC_TEMP_TLS] TLS Allocator
54
  StackAllocators :
55
  [ALLOC_TEMP_MAIN]
56
+ Peak usage frame count: [8.0 KB-16.0 KB]: 13431 frames, [16.0 KB-32.0 KB]: 227 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
  Peak Allocated Bytes 0 B
170
  Overflow Count 0
171
  [ALLOC_DEFAULT] Dual Thread Allocator
172
+ Peak main deferred allocation count 44
173
  [ALLOC_BUCKET]
174
  Large Block size 4.0 MB
175
  Used Block count 1
176
  Peak Allocated bytes 1.0 MB
177
  [ALLOC_DEFAULT_MAIN]
178
+ Peak usage frame count: [4.0 MB-8.0 MB]: 11610 frames, [8.0 MB-16.0 MB]: 2049 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
+ Peak Allocated memory 9.5 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
+ Peak usage frame count: [16.0 MB-32.0 MB]: 13659 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
  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]: 13176 frames, [64.0 KB-128.0 KB]: 483 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]: 13659 frames
223
  Requested Block Size 16.0 MB
224
  Peak Block count 1
225
  Peak Allocated memory 39.6 KB
 
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]: 13659 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]: 13658 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
  Used Block count 1
250
  Peak Allocated bytes 1.0 MB
251
  [ALLOC_TYPETREE_MAIN]
252
+ Peak usage frame count: [0-1.0 KB]: 13659 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]: 13659 frames
259
  Requested Block Size 2.0 MB
260
  Peak Block count 1
261
  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": 0.8698084950447083,
6
- "min": 0.8531681299209595,
7
- "max": 2.860461473464966,
8
- "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 8266.66015625,
12
- "min": 8183.5888671875,
13
- "max": 29199.591796875,
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": 12.964693069458008,
30
- "min": 0.36069631576538086,
31
- "max": 12.964693069458008,
32
- "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2528.115234375,
36
- "min": 69.97508239746094,
37
- "max": 2618.98095703125,
38
- "count": 20
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
- "value": 0.06554111967881338,
42
- "min": 0.06520679867917709,
43
- "max": 0.07539658877980329,
44
- "count": 20
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
- "value": 0.2621644787152535,
48
- "min": 0.26082719471670834,
49
- "max": 0.37058092398322456,
50
- "count": 20
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
- "value": 0.19473029516052967,
54
- "min": 0.12073119277677809,
55
- "max": 0.2837352125083699,
56
- "count": 20
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
- "value": 0.7789211806421187,
60
- "min": 0.48292477110711235,
61
- "max": 1.4186760625418495,
62
- "count": 20
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
65
- "value": 8.082097306000005e-06,
66
- "min": 8.082097306000005e-06,
67
- "max": 0.000291882002706,
68
- "count": 20
69
  },
70
  "SnowballTarget.Policy.LearningRate.sum": {
71
- "value": 3.232838922400002e-05,
72
- "min": 3.232838922400002e-05,
73
- "max": 0.00138516003828,
74
- "count": 20
75
  },
76
  "SnowballTarget.Policy.Epsilon.mean": {
77
- "value": 0.10269400000000001,
78
- "min": 0.10269400000000001,
79
- "max": 0.19729400000000002,
80
- "count": 20
81
  },
82
  "SnowballTarget.Policy.Epsilon.sum": {
83
- "value": 0.41077600000000003,
84
- "min": 0.41077600000000003,
85
- "max": 0.96172,
86
- "count": 20
87
  },
88
  "SnowballTarget.Policy.Beta.mean": {
89
- "value": 0.0001444306000000001,
90
- "min": 0.0001444306000000001,
91
- "max": 0.0048649706,
92
- "count": 20
93
  },
94
  "SnowballTarget.Policy.Beta.sum": {
95
- "value": 0.0005777224000000004,
96
- "min": 0.0005777224000000004,
97
- "max": 0.023089828,
98
- "count": 20
99
- },
100
- "SnowballTarget.Environment.EpisodeLength.mean": {
101
- "value": 199.0,
102
- "min": 199.0,
103
- "max": 199.0,
104
- "count": 20
105
- },
106
- "SnowballTarget.Environment.EpisodeLength.sum": {
107
- "value": 8756.0,
108
- "min": 8756.0,
109
- "max": 10945.0,
110
- "count": 20
111
- },
112
- "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 25.522727272727273,
114
- "min": 3.659090909090909,
115
- "max": 25.672727272727272,
116
- "count": 20
117
- },
118
- "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1123.0,
120
- "min": 161.0,
121
- "max": 1412.0,
122
- "count": 20
123
- },
124
- "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 25.522727272727273,
126
- "min": 3.659090909090909,
127
- "max": 25.672727272727272,
128
- "count": 20
129
- },
130
- "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1123.0,
132
- "min": 161.0,
133
- "max": 1412.0,
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": "1744947247",
152
  "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
153
  "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
154
  "mlagents_version": "1.2.0.dev0",
@@ -156,59 +156,59 @@
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.6.0+cu124",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1744947722"
160
  },
161
- "total": 474.741439455,
162
  "count": 1,
163
- "self": 0.4378416889998107,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.023436419000063324,
167
  "count": 1,
168
- "self": 0.023436419000063324
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 474.2801613470001,
172
  "count": 1,
173
- "self": 0.4186222830015822,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 3.3185108769999943,
177
  "count": 1,
178
- "self": 3.3185108769999943
179
  },
180
  "TrainerController.advance": {
181
- "total": 470.4409619869987,
182
- "count": 18192,
183
- "self": 0.427614562005715,
184
  "children": {
185
  "env_step": {
186
- "total": 336.0650025990009,
187
- "count": 18192,
188
- "self": 254.97174688799748,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 80.85299135499599,
192
- "count": 18192,
193
- "self": 1.412971331992594,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 79.4400200230034,
197
- "count": 18192,
198
- "self": 79.4400200230034
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.24026435600740115,
204
- "count": 18192,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 472.79424330599136,
209
- "count": 18192,
210
  "is_parallel": true,
211
- "self": 249.47584784199762,
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": 0.005052288000001681,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.0034757560000571175,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0015765319999445637,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0015765319999445637
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.07891404899999088,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0006865159999733805,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.0003746690000525632,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.0003746690000525632
244
  },
245
  "communicator.exchange": {
246
- "total": 0.07567667900002562,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.07567667900002562
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0021761849999393235,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.0003986140000051819,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0017775709999341416,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0017775709999341416
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 223.31839546399374,
271
- "count": 18191,
272
  "is_parallel": true,
273
- "self": 10.618433171005108,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 6.025178782995795,
277
- "count": 18191,
278
  "is_parallel": true,
279
- "self": 6.025178782995795
280
  },
281
  "communicator.exchange": {
282
- "total": 171.13239334699892,
283
- "count": 18191,
284
  "is_parallel": true,
285
- "self": 171.13239334699892
286
  },
287
  "steps_from_proto": {
288
- "total": 35.54239016299391,
289
- "count": 18191,
290
  "is_parallel": true,
291
- "self": 6.5321003960428925,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 29.01028976695102,
295
- "count": 181910,
296
  "is_parallel": true,
297
- "self": 29.01028976695102
298
  }
299
  }
300
  }
@@ -307,31 +307,31 @@
307
  }
308
  },
309
  "trainer_advance": {
310
- "total": 133.94834482599208,
311
- "count": 18192,
312
- "self": 0.5089990580021322,
313
  "children": {
314
  "process_trajectory": {
315
- "total": 29.910590317990454,
316
- "count": 18192,
317
- "self": 29.410250469990388,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
- "total": 0.5003398480000669,
321
- "count": 4,
322
- "self": 0.5003398480000669
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
- "total": 103.5287554499995,
328
- "count": 90,
329
- "self": 41.777088107996974,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
- "total": 61.75166734200252,
333
- "count": 4587,
334
- "self": 61.75166734200252
335
  }
336
  }
337
  }
@@ -340,19 +340,19 @@
340
  }
341
  },
342
  "trainer_threads": {
343
- "total": 1.0339999789721332e-06,
344
  "count": 1,
345
- "self": 1.0339999789721332e-06
346
  },
347
  "TrainerController._save_models": {
348
- "total": 0.10206516599987481,
349
  "count": 1,
350
- "self": 0.000886918999867703,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
- "total": 0.1011782470000071,
354
  "count": 1,
355
- "self": 0.1011782470000071
356
  }
357
  }
358
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.8681857585906982,
6
+ "min": 0.8617246747016907,
7
+ "max": 2.8711941242218018,
8
+ "count": 50
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 8862.4404296875,
12
+ "min": 7700.611328125,
13
+ "max": 30545.3828125,
14
+ "count": 50
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 499912.0,
18
  "min": 9952.0,
19
+ "max": 499912.0,
20
+ "count": 50
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 499912.0,
24
  "min": 9952.0,
25
+ "max": 499912.0,
26
+ "count": 50
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 28.480539321899414,
30
+ "min": 0.06870930641889572,
31
+ "max": 28.496248245239258,
32
+ "count": 50
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2876.534423828125,
36
+ "min": 6.6648030281066895,
37
+ "max": 2927.86083984375,
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": 8756.0,
48
+ "min": 8756.0,
49
+ "max": 10945.0,
50
+ "count": 50
51
+ },
52
+ "SnowballTarget.Environment.CumulativeReward.mean": {
53
+ "value": 27.830188679245282,
54
+ "min": 2.75,
55
+ "max": 28.163636363636364,
56
+ "count": 50
57
+ },
58
+ "SnowballTarget.Environment.CumulativeReward.sum": {
59
+ "value": 1475.0,
60
+ "min": 121.0,
61
+ "max": 1549.0,
62
+ "count": 50
63
+ },
64
+ "SnowballTarget.Policy.ExtrinsicReward.mean": {
65
+ "value": 27.830188679245282,
66
+ "min": 2.75,
67
+ "max": 28.163636363636364,
68
+ "count": 50
69
+ },
70
+ "SnowballTarget.Policy.ExtrinsicReward.sum": {
71
+ "value": 1475.0,
72
+ "min": 121.0,
73
+ "max": 1549.0,
74
+ "count": 50
75
  },
76
  "SnowballTarget.Losses.PolicyLoss.mean": {
77
+ "value": 0.04759585250490893,
78
+ "min": 0.04096470710458508,
79
+ "max": 0.05477973770620712,
80
+ "count": 50
81
  },
82
  "SnowballTarget.Losses.PolicyLoss.sum": {
83
+ "value": 0.09519170500981786,
84
+ "min": 0.08192941420917016,
85
+ "max": 0.1612619695447981,
86
+ "count": 50
87
  },
88
  "SnowballTarget.Losses.ValueLoss.mean": {
89
+ "value": 0.2687982366365545,
90
+ "min": 0.1750995202537845,
91
+ "max": 0.6149530507185881,
92
+ "count": 50
93
  },
94
  "SnowballTarget.Losses.ValueLoss.sum": {
95
+ "value": 0.537596473273109,
96
+ "min": 0.350199040507569,
97
+ "max": 1.8410278215127833,
98
+ "count": 50
99
  },
100
  "SnowballTarget.Policy.LearningRate.mean": {
101
+ "value": 2.500099000000002e-06,
102
+ "min": 2.500099000000002e-06,
103
+ "max": 0.00024670000131999997,
104
+ "count": 50
105
  },
106
  "SnowballTarget.Policy.LearningRate.sum": {
107
+ "value": 5.000198000000004e-06,
108
+ "min": 5.000198000000004e-06,
109
+ "max": 0.0006972000211200003,
110
+ "count": 50
111
  },
112
  "SnowballTarget.Policy.Epsilon.mean": {
113
+ "value": 0.101,
114
+ "min": 0.101,
115
+ "max": 0.19867999999999997,
116
+ "count": 50
117
  },
118
  "SnowballTarget.Policy.Epsilon.sum": {
119
+ "value": 0.202,
120
+ "min": 0.202,
121
+ "max": 0.5788800000000001,
122
+ "count": 50
123
  },
124
  "SnowballTarget.Policy.Beta.mean": {
125
+ "value": 1.990000000000001e-05,
126
+ "min": 1.990000000000001e-05,
127
+ "max": 0.0009869320000000003,
128
+ "count": 50
129
  },
130
  "SnowballTarget.Policy.Beta.sum": {
131
+ "value": 3.980000000000002e-05,
132
+ "min": 3.980000000000002e-05,
133
+ "max": 0.0027909120000000004,
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": "1745188860",
152
  "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
153
  "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
154
  "mlagents_version": "1.2.0.dev0",
 
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.6.0+cu124",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1745190034"
160
  },
161
+ "total": 1173.8106681919999,
162
  "count": 1,
163
+ "self": 0.4365396149996741,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.02320058100008282,
167
  "count": 1,
168
+ "self": 0.02320058100008282
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 1173.350927996,
172
  "count": 1,
173
+ "self": 0.9582707039592151,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 3.020470119000038,
177
  "count": 1,
178
+ "self": 3.020470119000038
179
  },
180
  "TrainerController.advance": {
181
+ "total": 1169.2210458940408,
182
+ "count": 45528,
183
+ "self": 0.9680215890550699,
184
  "children": {
185
  "env_step": {
186
+ "total": 777.1709635440084,
187
+ "count": 45528,
188
+ "self": 573.1229712800598,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 203.48116705397217,
192
+ "count": 45528,
193
+ "self": 3.2984373559432925,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 200.18272969802888,
197
+ "count": 45528,
198
+ "self": 200.18272969802888
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.5668252099764004,
204
+ "count": 45528,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 1169.892334609994,
209
+ "count": 45528,
210
  "is_parallel": true,
211
+ "self": 667.077291025972,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.0054461409999930765,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.004014567000012903,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0014315739999801735,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0014315739999801735
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.033421472999975776,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0005497850000892868,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.00038939499995649385,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.00038939499995649385
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.030676989999960824,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.030676989999960824
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0018053029999691717,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0003579419999368838,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0014473610000322878,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0014473610000322878
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 502.81504358402185,
271
+ "count": 45527,
272
  "is_parallel": true,
273
+ "self": 23.927230637047614,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 13.056193737019157,
277
+ "count": 45527,
278
  "is_parallel": true,
279
+ "self": 13.056193737019157
280
  },
281
  "communicator.exchange": {
282
+ "total": 388.68731416500884,
283
+ "count": 45527,
284
  "is_parallel": true,
285
+ "self": 388.68731416500884
286
  },
287
  "steps_from_proto": {
288
+ "total": 77.14430504494624,
289
+ "count": 45527,
290
  "is_parallel": true,
291
+ "self": 13.787736321055036,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 63.3565687238912,
295
+ "count": 455270,
296
  "is_parallel": true,
297
+ "self": 63.3565687238912
298
  }
299
  }
300
  }
 
307
  }
308
  },
309
  "trainer_advance": {
310
+ "total": 391.08206076097736,
311
+ "count": 45528,
312
+ "self": 1.187493573984625,
313
  "children": {
314
  "process_trajectory": {
315
+ "total": 84.54256373499288,
316
+ "count": 45528,
317
+ "self": 82.82474377999313,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
+ "total": 1.7178199549997544,
321
+ "count": 10,
322
+ "self": 1.7178199549997544
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
+ "total": 305.35200345199985,
328
+ "count": 113,
329
+ "self": 161.62613715300677,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
+ "total": 143.72586629899308,
333
+ "count": 9605,
334
+ "self": 143.72586629899308
335
  }
336
  }
337
  }
 
340
  }
341
  },
342
  "trainer_threads": {
343
+ "total": 8.489998890581774e-07,
344
  "count": 1,
345
+ "self": 8.489998890581774e-07
346
  },
347
  "TrainerController._save_models": {
348
+ "total": 0.15114043000016864,
349
  "count": 1,
350
+ "self": 0.0016895950002435711,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
+ "total": 0.14945083499992506,
354
  "count": 1,
355
+ "self": 0.14945083499992506
356
  }
357
  }
358
  }
run_logs/training_status.json CHANGED
@@ -2,28 +2,19 @@
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
- "steps": 49936,
6
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 14.818181818181818,
8
- "creation_time": 1744947366.0060189,
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": 22.636363636363637,
17
- "creation_time": 1744947486.1652224,
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": 26.0,
26
- "creation_time": 1744947604.6907313,
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": 25.727272727272727,
35
- "creation_time": 1744947721.4837508,
36
  "auxillary_file_paths": [
37
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
39
  },
40
  {
41
- "steps": 200112,
42
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
43
- "reward": 25.727272727272727,
44
- "creation_time": 1744947721.6007376,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
45
  "auxillary_file_paths": [
46
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
47
  ]
48
  }
49
  ],
50
  "final_checkpoint": {
51
- "steps": 200112,
52
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
53
- "reward": 25.727272727272727,
54
- "creation_time": 1744947721.6007376,
55
  "auxillary_file_paths": [
56
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },
 
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
+ "steps": 99896,
6
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99896.onnx",
7
+ "reward": 22.09090909090909,
8
+ "creation_time": 1745189099.9739656,
9
  "auxillary_file_paths": [
10
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-99896.pt"
 
 
 
 
 
 
 
 
 
11
  ]
12
  },
13
  {
14
  "steps": 149984,
15
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
16
+ "reward": null,
17
+ "creation_time": 1745189225.1068332,
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": 25.75,
26
+ "creation_time": 1745189342.5262828,
27
  "auxillary_file_paths": [
28
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
29
  ]
30
  },
31
  {
32
+ "steps": 249880,
33
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-249880.onnx",
34
+ "reward": 25.0,
35
+ "creation_time": 1745189459.6854053,
36
+ "auxillary_file_paths": [
37
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-249880.pt"
38
+ ]
39
+ },
40
+ {
41
+ "steps": 299968,
42
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.onnx",
43
+ "reward": null,
44
+ "creation_time": 1745189578.2964988,
45
+ "auxillary_file_paths": [
46
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.pt"
47
+ ]
48
+ },
49
+ {
50
+ "steps": 349928,
51
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-349928.onnx",
52
+ "reward": 26.181818181818183,
53
+ "creation_time": 1745189696.894822,
54
+ "auxillary_file_paths": [
55
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-349928.pt"
56
+ ]
57
+ },
58
+ {
59
+ "steps": 399968,
60
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-399968.onnx",
61
+ "reward": 27.625,
62
+ "creation_time": 1745189806.5303326,
63
+ "auxillary_file_paths": [
64
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-399968.pt"
65
+ ]
66
+ },
67
+ {
68
+ "steps": 449952,
69
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-449952.onnx",
70
+ "reward": null,
71
+ "creation_time": 1745189919.5262213,
72
+ "auxillary_file_paths": [
73
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-449952.pt"
74
+ ]
75
+ },
76
+ {
77
+ "steps": 499912,
78
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-499912.onnx",
79
+ "reward": 28.0,
80
+ "creation_time": 1745190034.0010014,
81
+ "auxillary_file_paths": [
82
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-499912.pt"
83
+ ]
84
+ },
85
+ {
86
+ "steps": 500808,
87
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-500808.onnx",
88
+ "reward": 28.0,
89
+ "creation_time": 1745190034.2539973,
90
  "auxillary_file_paths": [
91
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-500808.pt"
92
  ]
93
  }
94
  ],
95
  "final_checkpoint": {
96
+ "steps": 500808,
97
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
98
+ "reward": 28.0,
99
+ "creation_time": 1745190034.2539973,
100
  "auxillary_file_paths": [
101
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-500808.pt"
102
  ]
103
  }
104
  },