Hugging Face's logo

MysteryManav
/
q-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
MysteryManav commited on
Commit
e20ec12
·
verified ·
1 Parent(s): 13a56eb

SnowballTarget

Browse files
Files changed (28) hide show
  1. SnowballTarget.onnx +2 -2
  2. SnowballTarget/SnowballTarget-1000208.onnx +3 -0
  3. SnowballTarget/SnowballTarget-1000208.pt +3 -0
  4. SnowballTarget/SnowballTarget-199984.onnx +2 -2
  5. SnowballTarget/SnowballTarget-199984.pt +2 -2
  6. SnowballTarget/SnowballTarget-299968.onnx +3 -0
  7. SnowballTarget/SnowballTarget-299968.pt +3 -0
  8. SnowballTarget/SnowballTarget-399992.onnx +3 -0
  9. SnowballTarget/SnowballTarget-399992.pt +3 -0
  10. SnowballTarget/SnowballTarget-499976.onnx +3 -0
  11. SnowballTarget/SnowballTarget-499976.pt +3 -0
  12. SnowballTarget/SnowballTarget-599936.onnx +3 -0
  13. SnowballTarget/SnowballTarget-599936.pt +3 -0
  14. SnowballTarget/SnowballTarget-699984.onnx +3 -0
  15. SnowballTarget/SnowballTarget-699984.pt +3 -0
  16. SnowballTarget/SnowballTarget-799944.onnx +3 -0
  17. SnowballTarget/SnowballTarget-799944.pt +3 -0
  18. SnowballTarget/SnowballTarget-899992.onnx +3 -0
  19. SnowballTarget/SnowballTarget-899992.pt +3 -0
  20. SnowballTarget/SnowballTarget-999952.onnx +3 -0
  21. SnowballTarget/SnowballTarget-999952.pt +3 -0
  22. SnowballTarget/checkpoint.pt +2 -2
  23. SnowballTarget/events.out.tfevents.1748872477.manav.19269.0 +3 -0
  24. config.json +1 -1
  25. configuration.yaml +6 -6
  26. run_logs/Player-0.log +16 -16
  27. run_logs/timers.json +165 -165
  28. run_logs/training_status.json +75 -30
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:42b38029d8fd02acafa581fc4127fd83f53910e0cb7b406b51d295c640651c90
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba6525cdbb5a6a85e764d2f8ff3cd872431bea41f543c1b0260ddf317f5adc00
3
+ size 3919089
SnowballTarget/SnowballTarget-1000208.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba6525cdbb5a6a85e764d2f8ff3cd872431bea41f543c1b0260ddf317f5adc00
3
+ size 3919089
SnowballTarget/SnowballTarget-1000208.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1bb93d3402fea3c3e61464566d2c57adb810733d915945cec5ae9ab01a5319d
3
+ size 23439124
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:42b38029d8fd02acafa581fc4127fd83f53910e0cb7b406b51d295c640651c90
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08205b2f0fdab9958df4693efbaceee33b1a72900f0d08c622540e20edb19bae
3
+ size 3919089
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4942612f1f1a9cedeb25b585186ab5a37f03638cf982157c6313d721639a1865
3
- size 3850564
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3dafd364048208f28122f3c7e47f5c80c946b283b8afb344411a9438760e98d0
3
+ size 23438951
SnowballTarget/SnowballTarget-299968.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b175b8420c3e791bad3c6eb3d6d47019566cd82fc563f829d7ca41d6dec770cf
3
+ size 3919089
SnowballTarget/SnowballTarget-299968.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c1d4d946521481696f16fef3cf2a3c4a12d8662a89e1e5b86e3dfac63557f97
3
+ size 23438951
SnowballTarget/SnowballTarget-399992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a017d88cb621f77032cc87fa88a3359f06af8574977a2f73ee9179f40167c203
3
+ size 3919089
SnowballTarget/SnowballTarget-399992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbc10f6ff691661fcf73bef15b4d85e36936c32b6c99d9729a965d2b72d3f676
3
+ size 23438951
SnowballTarget/SnowballTarget-499976.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85b12df1381823545aeab01d10b758afa7f2916ca840de622f50a32baeeb08f9
3
+ size 3919089
SnowballTarget/SnowballTarget-499976.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:164aa756c96143cee18ff4c83ea68202c7b6c64ba714d1099023cc715ecaf083
3
+ size 23438951
SnowballTarget/SnowballTarget-599936.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4283818ff75307cab7e6a88d5b404555e0ef13748f40228b0b9d6eeca0ee5036
3
+ size 3919089
SnowballTarget/SnowballTarget-599936.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5e695e6723377c11e2dff9efc3e2bb67e51faf0e44c30fc06d80e76c4878760
3
+ size 23438951
SnowballTarget/SnowballTarget-699984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0135768ceea8a61628d9725fd4e3d5c33f30d8722b56ff0f9a757810b356c2e4
3
+ size 3919089
SnowballTarget/SnowballTarget-699984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbaa0f1f5122f495c2f80466cb7cc58ac4da2ce5d604c5e3cfcf5c48e808199d
3
+ size 23438951
SnowballTarget/SnowballTarget-799944.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf37984a5f9789cf887350f84c3a404ca87de2baba2f23c4b3e86f5d1888acd5
3
+ size 3919089
SnowballTarget/SnowballTarget-799944.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c571d0204ee96f09693aad7e3e353f7e4569721b88b496d0e00a7a772cc0c51f
3
+ size 23438951
SnowballTarget/SnowballTarget-899992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d926b405542906fff70473f8ccf19fba4974e658f235165d3456ebb26f85a8c2
3
+ size 3919089
SnowballTarget/SnowballTarget-899992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3073843f79bc388f8e0faa641f6e3abd0cf59aeb46a7038b59eb419c899cd6f1
3
+ size 23438951
SnowballTarget/SnowballTarget-999952.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba6525cdbb5a6a85e764d2f8ff3cd872431bea41f543c1b0260ddf317f5adc00
3
+ size 3919089
SnowballTarget/SnowballTarget-999952.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b3df9dc54fdbe5f8830264c78383e24c5f052453d7c56c6b19de94ac9604c75
3
+ size 23438951
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f24da4917d6d6275021d466ec41d8e846c78b0a75291ca4bfbd7392e504ea04
3
- size 3849717
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db1cfb05925f6c1ea88a7bdc295be70704364988ca1c7e5a3cb1a93cfc191c1c
3
+ size 23437752
SnowballTarget/events.out.tfevents.1748872477.manav.19269.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39f6b017de8c30ce527b7374a98519c9357a652ba061283017b7589f6b33c8f5
3
+ size 53099
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": 1280, "height": 720, "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": "SnowballTarget-v3", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
 
1
+ {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 100000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 4, "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": 1000000, "time_horizon": 64, "summary_freq": 20000, "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": 1280, "height": 720, "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": "SnowballTarget", "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
@@ -14,11 +14,11 @@ behaviors:
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
24
  goal_conditioning_type: hyper
@@ -38,9 +38,9 @@ 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
46
  behavioral_cloning: null
@@ -66,7 +66,7 @@ engine_settings:
66
  no_graphics_monitor: false
67
  environment_parameters: null
68
  checkpoint_settings:
69
- run_id: SnowballTarget-v3
70
  initialize_from: null
71
  load_model: false
72
  resume: false
 
14
  learning_rate_schedule: linear
15
  beta_schedule: linear
16
  epsilon_schedule: linear
17
+ checkpoint_interval: 100000
18
  network_settings:
19
  normalize: false
20
+ hidden_units: 512
21
+ num_layers: 4
22
  vis_encode_type: simple
23
  memory: null
24
  goal_conditioning_type: hyper
 
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
+ max_steps: 1000000
42
  time_horizon: 64
43
+ summary_freq: 20000
44
  threaded: false
45
  self_play: null
46
  behavioral_cloning: null
 
66
  no_graphics_monitor: false
67
  environment_parameters: null
68
  checkpoint_settings:
69
+ run_id: SnowballTarget
70
  initialize_from: null
71
  load_model: false
72
  resume: false
run_logs/Player-0.log CHANGED
@@ -11,7 +11,7 @@ NullGfxDevice:
11
  Renderer: Null Device
12
  Vendor: Unity Technologies
13
  Begin MonoManager ReloadAssembly
14
- - Completed reload, in 0.063 seconds
15
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
16
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
17
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -22,7 +22,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
22
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
23
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
24
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
25
- UnloadTime: 0.721872 ms
26
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
27
  requesting resize 1280 x 720
28
  Setting up 6 worker threads for Enlighten.
@@ -30,7 +30,7 @@ Memory Statistics:
30
  [ALLOC_TEMP_TLS] TLS Allocator
31
  StackAllocators :
32
  [ALLOC_TEMP_MAIN]
33
- 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
34
  Initial Block Size 4.0 MB
35
  Current Block Size 4.0 MB
36
  Peak Allocated Bytes 2.0 MB
@@ -196,22 +196,22 @@ Memory Statistics:
196
  Peak Allocated Bytes 0 B
197
  Overflow Count 0
198
  [ALLOC_DEFAULT] Dual Thread Allocator
199
- Peak main deferred allocation count 42
200
  [ALLOC_BUCKET]
201
  Large Block size 4.0 MB
202
  Used Block count 1
203
  Peak Allocated bytes 1.0 MB
204
  [ALLOC_DEFAULT_MAIN]
205
- Peak usage frame count: [4.0 MB-8.0 MB]: 5458 frames
206
  Requested Block Size 16.0 MB
207
- Peak Block count 1
208
- Peak Allocated memory 7.0 MB
209
  Peak Large allocation bytes 0 B
210
  [ALLOC_DEFAULT_THREAD]
211
- Peak usage frame count: [16.0 MB-32.0 MB]: 5458 frames
212
  Requested Block Size 16.0 MB
213
  Peak Block count 1
214
- Peak Allocated memory 17.5 MB
215
  Peak Large allocation bytes 16.0 MB
216
  [ALLOC_TEMP_JOB_1_FRAME]
217
  Initial Block Size 2.0 MB
@@ -240,13 +240,13 @@ Memory Statistics:
240
  Used Block count 1
241
  Peak Allocated bytes 1.0 MB
242
  [ALLOC_GFX_MAIN]
243
- Peak usage frame count: [32.0 KB-64.0 KB]: 3790 frames, [64.0 KB-128.0 KB]: 1668 frames
244
  Requested Block Size 16.0 MB
245
  Peak Block count 1
246
- Peak Allocated memory 68.2 KB
247
  Peak Large allocation bytes 0 B
248
  [ALLOC_GFX_THREAD]
249
- Peak usage frame count: [32.0 KB-64.0 KB]: 5458 frames
250
  Requested Block Size 16.0 MB
251
  Peak Block count 1
252
  Peak Allocated memory 39.6 KB
@@ -258,13 +258,13 @@ Memory Statistics:
258
  Used Block count 1
259
  Peak Allocated bytes 1.0 MB
260
  [ALLOC_CACHEOBJECTS_MAIN]
261
- Peak usage frame count: [0.5 MB-1.0 MB]: 5458 frames
262
  Requested Block Size 4.0 MB
263
  Peak Block count 1
264
  Peak Allocated memory 0.6 MB
265
  Peak Large allocation bytes 0 B
266
  [ALLOC_CACHEOBJECTS_THREAD]
267
- Peak usage frame count: [0.5 MB-1.0 MB]: 5457 frames, [2.0 MB-4.0 MB]: 1 frames
268
  Requested Block Size 4.0 MB
269
  Peak Block count 1
270
  Peak Allocated memory 2.2 MB
@@ -276,13 +276,13 @@ Memory Statistics:
276
  Used Block count 1
277
  Peak Allocated bytes 1.0 MB
278
  [ALLOC_TYPETREE_MAIN]
279
- Peak usage frame count: [0-1.0 KB]: 5458 frames
280
  Requested Block Size 2.0 MB
281
  Peak Block count 1
282
  Peak Allocated memory 1.0 KB
283
  Peak Large allocation bytes 0 B
284
  [ALLOC_TYPETREE_THREAD]
285
- Peak usage frame count: [1.0 KB-2.0 KB]: 5458 frames
286
  Requested Block Size 2.0 MB
287
  Peak Block count 1
288
  Peak Allocated memory 1.7 KB
 
11
  Renderer: Null Device
12
  Vendor: Unity Technologies
13
  Begin MonoManager ReloadAssembly
14
+ - Completed reload, in 0.074 seconds
15
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
16
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
17
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 
22
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
23
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
24
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
25
+ UnloadTime: 0.637356 ms
26
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
27
  requesting resize 1280 x 720
28
  Setting up 6 worker threads for Enlighten.
 
30
  [ALLOC_TEMP_TLS] TLS Allocator
31
  StackAllocators :
32
  [ALLOC_TEMP_MAIN]
33
+ Peak usage frame count: [8.0 KB-16.0 KB]: 26824 frames, [16.0 KB-32.0 KB]: 454 frames, [2.0 MB-4.0 MB]: 1 frames
34
  Initial Block Size 4.0 MB
35
  Current Block Size 4.0 MB
36
  Peak Allocated Bytes 2.0 MB
 
196
  Peak Allocated Bytes 0 B
197
  Overflow Count 0
198
  [ALLOC_DEFAULT] Dual Thread Allocator
199
+ Peak main deferred allocation count 41
200
  [ALLOC_BUCKET]
201
  Large Block size 4.0 MB
202
  Used Block count 1
203
  Peak Allocated bytes 1.0 MB
204
  [ALLOC_DEFAULT_MAIN]
205
+ Peak usage frame count: [4.0 MB-8.0 MB]: 10754 frames, [8.0 MB-16.0 MB]: 16525 frames
206
  Requested Block Size 16.0 MB
207
+ Peak Block count 2
208
+ Peak Allocated memory 14.7 MB
209
  Peak Large allocation bytes 0 B
210
  [ALLOC_DEFAULT_THREAD]
211
+ Peak usage frame count: [16.0 MB-32.0 MB]: 27279 frames
212
  Requested Block Size 16.0 MB
213
  Peak Block count 1
214
+ Peak Allocated memory 17.4 MB
215
  Peak Large allocation bytes 16.0 MB
216
  [ALLOC_TEMP_JOB_1_FRAME]
217
  Initial Block Size 2.0 MB
 
240
  Used Block count 1
241
  Peak Allocated bytes 1.0 MB
242
  [ALLOC_GFX_MAIN]
243
+ Peak usage frame count: [32.0 KB-64.0 KB]: 26541 frames, [64.0 KB-128.0 KB]: 738 frames
244
  Requested Block Size 16.0 MB
245
  Peak Block count 1
246
+ Peak Allocated memory 66.0 KB
247
  Peak Large allocation bytes 0 B
248
  [ALLOC_GFX_THREAD]
249
+ Peak usage frame count: [32.0 KB-64.0 KB]: 27279 frames
250
  Requested Block Size 16.0 MB
251
  Peak Block count 1
252
  Peak Allocated memory 39.6 KB
 
258
  Used Block count 1
259
  Peak Allocated bytes 1.0 MB
260
  [ALLOC_CACHEOBJECTS_MAIN]
261
+ Peak usage frame count: [0.5 MB-1.0 MB]: 27279 frames
262
  Requested Block Size 4.0 MB
263
  Peak Block count 1
264
  Peak Allocated memory 0.6 MB
265
  Peak Large allocation bytes 0 B
266
  [ALLOC_CACHEOBJECTS_THREAD]
267
+ Peak usage frame count: [0.5 MB-1.0 MB]: 27278 frames, [2.0 MB-4.0 MB]: 1 frames
268
  Requested Block Size 4.0 MB
269
  Peak Block count 1
270
  Peak Allocated memory 2.2 MB
 
276
  Used Block count 1
277
  Peak Allocated bytes 1.0 MB
278
  [ALLOC_TYPETREE_MAIN]
279
+ Peak usage frame count: [0-1.0 KB]: 27279 frames
280
  Requested Block Size 2.0 MB
281
  Peak Block count 1
282
  Peak Allocated memory 1.0 KB
283
  Peak Large allocation bytes 0 B
284
  [ALLOC_TYPETREE_THREAD]
285
+ Peak usage frame count: [1.0 KB-2.0 KB]: 27279 frames
286
  Requested Block Size 2.0 MB
287
  Peak Block count 1
288
  Peak Allocated memory 1.7 KB
run_logs/timers.json CHANGED
@@ -2,213 +2,213 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 0.679754912853241,
6
- "min": 0.679754912853241,
7
- "max": 2.8512115478515625,
8
- "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 6460.390625,
12
- "min": 6460.390625,
13
- "max": 29105.16796875,
14
- "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
17
- "value": 199984.0,
18
- "min": 9952.0,
19
- "max": 199984.0,
20
- "count": 20
21
  },
22
  "SnowballTarget.Step.sum": {
23
- "value": 199984.0,
24
- "min": 9952.0,
25
- "max": 199984.0,
26
- "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 11.98922061920166,
30
- "min": 0.4224729537963867,
31
- "max": 12.085224151611328,
32
- "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2337.89794921875,
36
- "min": 81.95975494384766,
37
- "max": 2465.3857421875,
38
- "count": 20
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
- "value": 0.07573059144773402,
42
- "min": 0.06207504068916736,
43
- "max": 0.07573059144773402,
44
- "count": 20
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
- "value": 0.30292236579093607,
48
- "min": 0.26853579190997956,
49
- "max": 0.37129102058151703,
50
- "count": 20
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
- "value": 0.18484952344613917,
54
- "min": 0.11586106555563783,
55
- "max": 0.2937942708970285,
56
- "count": 20
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
- "value": 0.7393980937845567,
60
- "min": 0.4634442622225513,
61
- "max": 1.438774553291938,
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": 23.318181818181817,
114
- "min": 3.2045454545454546,
115
- "max": 23.98181818181818,
116
- "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1026.0,
120
- "min": 141.0,
121
- "max": 1319.0,
122
- "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 23.318181818181817,
126
- "min": 3.2045454545454546,
127
- "max": 23.98181818181818,
128
- "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1026.0,
132
- "min": 141.0,
133
- "max": 1319.0,
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": "1748868333",
152
  "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
153
- "command_line_arguments": "/home/manav/Code/AIML/DRL/.conda/bin/mlagents-learn ./ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget-v3 --width=1280 --height=720 --no-graphics",
154
  "mlagents_version": "1.2.0.dev0",
155
  "mlagents_envs_version": "1.2.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.7.0+cu126",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1748868554"
160
  },
161
- "total": 220.57955450999907,
162
  "count": 1,
163
- "self": 0.21852042799946503,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.021993993999785744,
167
  "count": 1,
168
- "self": 0.021993993999785744
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 220.33904008799982,
172
  "count": 1,
173
- "self": 0.27149966993238195,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 1.7454038209998544,
177
  "count": 1,
178
- "self": 1.7454038209998544
179
  },
180
  "TrainerController.advance": {
181
- "total": 218.27687669906845,
182
- "count": 18192,
183
- "self": 0.2434329302977858,
184
  "children": {
185
  "env_step": {
186
- "total": 154.78325090489489,
187
- "count": 18192,
188
- "self": 115.55906575380322,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 39.05045941908065,
192
- "count": 18192,
193
- "self": 0.7475669139657839,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 38.30289250511487,
197
- "count": 18192,
198
- "self": 38.30289250511487
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.1737257320110075,
204
- "count": 18192,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 219.8509752760383,
209
- "count": 18192,
210
  "is_parallel": true,
211
- "self": 120.86191039407458,
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": 0.0017590070001460845,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.000617758001681068,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0011412489984650165,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0011412489984650165
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.02416658199945232,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.00034487599987187423,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.00022378100038622506,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.00022378100038622506
244
  },
245
  "communicator.exchange": {
246
- "total": 0.02272888599873113,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.02272888599873113
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0008690390004630899,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.00019310499919811264,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0006759340012649773,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0006759340012649773
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 98.98906488196371,
271
- "count": 18191,
272
  "is_parallel": true,
273
- "self": 3.7139572482319636,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 2.1861783200547507,
277
- "count": 18191,
278
  "is_parallel": true,
279
- "self": 2.1861783200547507
280
  },
281
  "communicator.exchange": {
282
- "total": 81.69014335991051,
283
- "count": 18191,
284
  "is_parallel": true,
285
- "self": 81.69014335991051
286
  },
287
  "steps_from_proto": {
288
- "total": 11.398785953766492,
289
- "count": 18191,
290
  "is_parallel": true,
291
- "self": 2.4167913150849927,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 8.981994638681499,
295
- "count": 181910,
296
  "is_parallel": true,
297
- "self": 8.981994638681499
298
  }
299
  }
300
  }
@@ -307,31 +307,31 @@
307
  }
308
  },
309
  "trainer_advance": {
310
- "total": 63.25019286387578,
311
- "count": 18192,
312
- "self": 0.3463065538799128,
313
  "children": {
314
  "process_trajectory": {
315
- "total": 14.085360287986987,
316
- "count": 18192,
317
- "self": 13.883280057985758,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
- "total": 0.2020802300012292,
321
- "count": 4,
322
- "self": 0.2020802300012292
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
- "total": 48.81852602200888,
328
- "count": 90,
329
- "self": 20.691032286989866,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
- "total": 28.127493735019016,
333
- "count": 4587,
334
- "self": 28.127493735019016
335
  }
336
  }
337
  }
@@ -340,19 +340,19 @@
340
  }
341
  },
342
  "trainer_threads": {
343
- "total": 7.899998308857903e-07,
344
  "count": 1,
345
- "self": 7.899998308857903e-07
346
  },
347
  "TrainerController._save_models": {
348
- "total": 0.045259107999299886,
349
  "count": 1,
350
- "self": 0.00040428099782729987,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
- "total": 0.044854827001472586,
354
  "count": 1,
355
- "self": 0.044854827001472586
356
  }
357
  }
358
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.7713654041290283,
6
+ "min": 0.7058430314064026,
7
+ "max": 2.7871124744415283,
8
+ "count": 50
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 15273.03515625,
12
+ "min": 13975.6923828125,
13
+ "max": 57146.953125,
14
+ "count": 50
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 999952.0,
18
+ "min": 19992.0,
19
+ "max": 999952.0,
20
+ "count": 50
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 999952.0,
24
+ "min": 19992.0,
25
+ "max": 999952.0,
26
+ "count": 50
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 14.311433792114258,
30
+ "min": 0.9383178353309631,
31
+ "max": 14.37216567993164,
32
+ "count": 50
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 5710.26220703125,
36
+ "min": 374.3888244628906,
37
+ "max": 5781.15771484375,
38
+ "count": 50
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
+ "value": 0.06689777244062493,
42
+ "min": 0.06322509537698322,
43
+ "max": 0.07288012154531474,
44
+ "count": 50
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
+ "value": 0.6020799519656244,
48
+ "min": 0.5690258583928489,
49
+ "max": 0.6990882444612604,
50
+ "count": 50
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
+ "value": 0.1538192628840216,
54
+ "min": 0.1443460942093843,
55
+ "max": 0.28104940910614656,
56
+ "count": 50
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
+ "value": 1.3843733659561943,
60
+ "min": 1.2991148478844587,
61
+ "max": 2.529444681955319,
62
+ "count": 50
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
65
+ "value": 3.0264989911999997e-06,
66
+ "min": 3.0264989911999997e-06,
67
+ "max": 0.00029672640109119994,
68
+ "count": 50
69
  },
70
  "SnowballTarget.Policy.LearningRate.sum": {
71
+ "value": 2.72384909208e-05,
72
+ "min": 2.72384909208e-05,
73
+ "max": 0.0026705376098207995,
74
+ "count": 50
75
  },
76
  "SnowballTarget.Policy.Epsilon.mean": {
77
+ "value": 0.10100880000000001,
78
+ "min": 0.10100880000000001,
79
+ "max": 0.1989088,
80
+ "count": 50
81
  },
82
  "SnowballTarget.Policy.Epsilon.sum": {
83
+ "value": 0.9090792000000001,
84
+ "min": 0.9090792000000001,
85
+ "max": 1.7901791999999999,
86
+ "count": 50
87
  },
88
  "SnowballTarget.Policy.Beta.mean": {
89
+ "value": 6.0339119999999994e-05,
90
+ "min": 6.0339119999999994e-05,
91
+ "max": 0.00494554912,
92
+ "count": 50
93
  },
94
  "SnowballTarget.Policy.Beta.sum": {
95
+ "value": 0.0005430520799999999,
96
+ "min": 0.0005430520799999999,
97
+ "max": 0.04450994208,
98
+ "count": 50
99
  },
100
  "SnowballTarget.Environment.EpisodeLength.mean": {
101
  "value": 199.0,
102
  "min": 199.0,
103
  "max": 199.0,
104
+ "count": 50
105
  },
106
  "SnowballTarget.Environment.EpisodeLength.sum": {
107
+ "value": 19701.0,
108
+ "min": 19701.0,
109
+ "max": 21890.0,
110
+ "count": 50
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 28.303030303030305,
114
+ "min": 5.757575757575758,
115
+ "max": 28.303030303030305,
116
+ "count": 50
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 2802.0,
120
+ "min": 570.0,
121
+ "max": 3037.0,
122
+ "count": 50
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 28.303030303030305,
126
+ "min": 5.757575757575758,
127
+ "max": 28.303030303030305,
128
+ "count": 50
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 2802.0,
132
+ "min": 570.0,
133
+ "max": 3037.0,
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": "1748872476",
152
  "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
153
+ "command_line_arguments": "/home/manav/Code/AIML/DRL/.conda/bin/mlagents-learn ./ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget --width=1280 --height=720 --no-graphics",
154
  "mlagents_version": "1.2.0.dev0",
155
  "mlagents_envs_version": "1.2.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.7.0+cu126",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1748873827"
160
  },
161
+ "total": 1350.9069259240005,
162
  "count": 1,
163
+ "self": 1.0637655530008487,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.020917910000207485,
167
  "count": 1,
168
+ "self": 0.020917910000207485
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 1349.8222424609994,
172
  "count": 1,
173
+ "self": 1.590281933940787,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 1.786696381001093,
177
  "count": 1,
178
+ "self": 1.786696381001093
179
  },
180
  "TrainerController.advance": {
181
+ "total": 1346.2494775780578,
182
+ "count": 90928,
183
+ "self": 1.5996849833336455,
184
  "children": {
185
  "env_step": {
186
+ "total": 929.4366662100292,
187
+ "count": 90928,
188
+ "self": 680.8426842890258,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 247.53564174976054,
192
+ "count": 90928,
193
+ "self": 4.768349892021433,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 242.7672918577391,
197
+ "count": 90928,
198
+ "self": 242.7672918577391
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 1.0583401712428895,
204
+ "count": 90928,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 1347.3265317070145,
209
+ "count": 90928,
210
  "is_parallel": true,
211
+ "self": 772.7373323594602,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.0014423630000237608,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.00040456200440530665,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0010378009956184542,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0010378009956184542
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.022094554999057436,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.00025103399821091443,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.00021005199960200116,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.00021005199960200116
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.0206373609998991,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.0206373609998991
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0009961080013454193,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.00017358199693262577,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0008225260044127936,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0008225260044127936
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 574.5891993475543,
271
+ "count": 90927,
272
  "is_parallel": true,
273
+ "self": 22.49901147006858,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 12.9481893847842,
277
+ "count": 90927,
278
  "is_parallel": true,
279
+ "self": 12.9481893847842
280
  },
281
  "communicator.exchange": {
282
+ "total": 472.0681196437363,
283
+ "count": 90927,
284
  "is_parallel": true,
285
+ "self": 472.0681196437363
286
  },
287
  "steps_from_proto": {
288
+ "total": 67.07387884896525,
289
+ "count": 90927,
290
  "is_parallel": true,
291
+ "self": 14.65100613965842,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 52.42287270930683,
295
+ "count": 909270,
296
  "is_parallel": true,
297
+ "self": 52.42287270930683
298
  }
299
  }
300
  }
 
307
  }
308
  },
309
  "trainer_advance": {
310
+ "total": 415.213126384695,
311
+ "count": 90928,
312
+ "self": 2.03284699379401,
313
  "children": {
314
  "process_trajectory": {
315
+ "total": 87.78375979090924,
316
+ "count": 90928,
317
+ "self": 85.65173599091031,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
+ "total": 2.132023799998933,
321
+ "count": 10,
322
+ "self": 2.132023799998933
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
+ "total": 325.39651959999173,
328
+ "count": 454,
329
+ "self": 129.20730124482725,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
+ "total": 196.18921835516448,
333
+ "count": 23151,
334
+ "self": 196.18921835516448
335
  }
336
  }
337
  }
 
340
  }
341
  },
342
  "trainer_threads": {
343
+ "total": 6.310001481324434e-07,
344
  "count": 1,
345
+ "self": 6.310001481324434e-07
346
  },
347
  "TrainerController._save_models": {
348
+ "total": 0.19578593699952762,
349
  "count": 1,
350
+ "self": 0.002276352999615483,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
+ "total": 0.19350958399991214,
354
  "count": 1,
355
+ "self": 0.19350958399991214
356
  }
357
  }
358
  }
run_logs/training_status.json CHANGED
@@ -2,58 +2,103 @@
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
- "steps": 49936,
6
- "file_path": "results/SnowballTarget-v3/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 15.181818181818182,
8
- "creation_time": 1748868391.8961005,
9
  "auxillary_file_paths": [
10
- "results/SnowballTarget-v3/SnowballTarget/SnowballTarget-49936.pt"
11
  ]
12
  },
13
  {
14
- "steps": 99960,
15
- "file_path": "results/SnowballTarget-v3/SnowballTarget/SnowballTarget-99960.onnx",
16
- "reward": 20.818181818181817,
17
- "creation_time": 1748868443.3380282,
18
  "auxillary_file_paths": [
19
- "results/SnowballTarget-v3/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
21
  },
22
  {
23
- "steps": 149984,
24
- "file_path": "results/SnowballTarget-v3/SnowballTarget/SnowballTarget-149984.onnx",
25
- "reward": 22.363636363636363,
26
- "creation_time": 1748868498.495421,
27
  "auxillary_file_paths": [
28
- "results/SnowballTarget-v3/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
30
  },
31
  {
32
- "steps": 199984,
33
- "file_path": "results/SnowballTarget-v3/SnowballTarget/SnowballTarget-199984.onnx",
34
- "reward": 23.363636363636363,
35
- "creation_time": 1748868553.9300377,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
36
  "auxillary_file_paths": [
37
- "results/SnowballTarget-v3/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
39
  },
40
  {
41
- "steps": 200112,
42
- "file_path": "results/SnowballTarget-v3/SnowballTarget/SnowballTarget-200112.onnx",
43
- "reward": 23.363636363636363,
44
- "creation_time": 1748868553.9825795,
45
  "auxillary_file_paths": [
46
- "results/SnowballTarget-v3/SnowballTarget/SnowballTarget-200112.pt"
47
  ]
48
  }
49
  ],
50
  "final_checkpoint": {
51
- "steps": 200112,
52
- "file_path": "results/SnowballTarget-v3/SnowballTarget.onnx",
53
- "reward": 23.363636363636363,
54
- "creation_time": 1748868553.9825795,
55
  "auxillary_file_paths": [
56
- "results/SnowballTarget-v3/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },
 
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
+ "steps": 199984,
6
+ "file_path": "results/SnowballTarget/SnowballTarget/SnowballTarget-199984.onnx",
7
+ "reward": 25.181818181818183,
8
+ "creation_time": 1748872738.1203287,
9
  "auxillary_file_paths": [
10
+ "results/SnowballTarget/SnowballTarget/SnowballTarget-199984.pt"
11
  ]
12
  },
13
  {
14
+ "steps": 299968,
15
+ "file_path": "results/SnowballTarget/SnowballTarget/SnowballTarget-299968.onnx",
16
+ "reward": 25.90909090909091,
17
+ "creation_time": 1748872871.910761,
18
  "auxillary_file_paths": [
19
+ "results/SnowballTarget/SnowballTarget/SnowballTarget-299968.pt"
20
  ]
21
  },
22
  {
23
+ "steps": 399992,
24
+ "file_path": "results/SnowballTarget/SnowballTarget/SnowballTarget-399992.onnx",
25
+ "reward": 25.90909090909091,
26
+ "creation_time": 1748873018.3957517,
27
  "auxillary_file_paths": [
28
+ "results/SnowballTarget/SnowballTarget/SnowballTarget-399992.pt"
29
  ]
30
  },
31
  {
32
+ "steps": 499976,
33
+ "file_path": "results/SnowballTarget/SnowballTarget/SnowballTarget-499976.onnx",
34
+ "reward": 26.636363636363637,
35
+ "creation_time": 1748873154.4456918,
36
+ "auxillary_file_paths": [
37
+ "results/SnowballTarget/SnowballTarget/SnowballTarget-499976.pt"
38
+ ]
39
+ },
40
+ {
41
+ "steps": 599936,
42
+ "file_path": "results/SnowballTarget/SnowballTarget/SnowballTarget-599936.onnx",
43
+ "reward": 27.181818181818183,
44
+ "creation_time": 1748873289.8007784,
45
+ "auxillary_file_paths": [
46
+ "results/SnowballTarget/SnowballTarget/SnowballTarget-599936.pt"
47
+ ]
48
+ },
49
+ {
50
+ "steps": 699984,
51
+ "file_path": "results/SnowballTarget/SnowballTarget/SnowballTarget-699984.onnx",
52
+ "reward": 27.181818181818183,
53
+ "creation_time": 1748873424.9048839,
54
+ "auxillary_file_paths": [
55
+ "results/SnowballTarget/SnowballTarget/SnowballTarget-699984.pt"
56
+ ]
57
+ },
58
+ {
59
+ "steps": 799944,
60
+ "file_path": "results/SnowballTarget/SnowballTarget/SnowballTarget-799944.onnx",
61
+ "reward": 28.454545454545453,
62
+ "creation_time": 1748873557.0257964,
63
+ "auxillary_file_paths": [
64
+ "results/SnowballTarget/SnowballTarget/SnowballTarget-799944.pt"
65
+ ]
66
+ },
67
+ {
68
+ "steps": 899992,
69
+ "file_path": "results/SnowballTarget/SnowballTarget/SnowballTarget-899992.onnx",
70
+ "reward": 28.545454545454547,
71
+ "creation_time": 1748873696.8157957,
72
+ "auxillary_file_paths": [
73
+ "results/SnowballTarget/SnowballTarget/SnowballTarget-899992.pt"
74
+ ]
75
+ },
76
+ {
77
+ "steps": 999952,
78
+ "file_path": "results/SnowballTarget/SnowballTarget/SnowballTarget-999952.onnx",
79
+ "reward": 28.727272727272727,
80
+ "creation_time": 1748873826.3449576,
81
  "auxillary_file_paths": [
82
+ "results/SnowballTarget/SnowballTarget/SnowballTarget-999952.pt"
83
  ]
84
  },
85
  {
86
+ "steps": 1000208,
87
+ "file_path": "results/SnowballTarget/SnowballTarget/SnowballTarget-1000208.onnx",
88
+ "reward": 28.727272727272727,
89
+ "creation_time": 1748873826.550466,
90
  "auxillary_file_paths": [
91
+ "results/SnowballTarget/SnowballTarget/SnowballTarget-1000208.pt"
92
  ]
93
  }
94
  ],
95
  "final_checkpoint": {
96
+ "steps": 1000208,
97
+ "file_path": "results/SnowballTarget/SnowballTarget.onnx",
98
+ "reward": 28.727272727272727,
99
+ "creation_time": 1748873826.550466,
100
  "auxillary_file_paths": [
101
+ "results/SnowballTarget/SnowballTarget/SnowballTarget-1000208.pt"
102
  ]
103
  }
104
  },