Hugging Face's logo

Monadillo
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
Monadillo commited on
Commit
1b6cef9
·
verified ·
1 Parent(s): c000905

First Push

Browse files
Files changed (26) hide show
  1. SnowballTarget.onnx +1 -1
  2. SnowballTarget/SnowballTarget-249984.onnx +3 -0
  3. SnowballTarget/SnowballTarget-249984.pt +3 -0
  4. SnowballTarget/SnowballTarget-299944.onnx +3 -0
  5. SnowballTarget/SnowballTarget-299944.pt +3 -0
  6. SnowballTarget/SnowballTarget-349968.onnx +3 -0
  7. SnowballTarget/SnowballTarget-349968.pt +3 -0
  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-549976.onnx +3 -0
  15. SnowballTarget/SnowballTarget-549976.pt +3 -0
  16. SnowballTarget/SnowballTarget-599976.onnx +3 -0
  17. SnowballTarget/SnowballTarget-599976.pt +3 -0
  18. SnowballTarget/SnowballTarget-600424.onnx +3 -0
  19. SnowballTarget/SnowballTarget-600424.pt +3 -0
  20. SnowballTarget/checkpoint.pt +1 -1
  21. SnowballTarget/events.out.tfevents.1744014827.d65b556c3549.6037.0 +3 -0
  22. config.json +1 -1
  23. configuration.yaml +2 -2
  24. run_logs/Player-0.log +15 -18
  25. run_logs/timers.json +162 -162
  26. run_logs/training_status.json +73 -28
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:02aa09a58c245d97c6b81c75509fae903e8739c6c430110d0b52b3db9ba4e345
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b785ce816b93939d174e3bfb3bdc4b691607aabf04f3ee83f4408ec435517f77
3
  size 650646
SnowballTarget/SnowballTarget-249984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4476103b92e5d1cbca993c928620dfe51f85fbc50faa4b62ceb04e733221535
3
+ size 650646
SnowballTarget/SnowballTarget-249984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:898dd5e5c2b212d050266cb4d02b5019e9c01c0e826e0ecaff1e78e423e978c0
3
+ size 3850075
SnowballTarget/SnowballTarget-299944.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:210b3cc00946928d2492fbd9735cafbe5d57f823eca2ce0d346ce491519cbe60
3
+ size 650646
SnowballTarget/SnowballTarget-299944.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bce0f5b9da9031af01c5bd5101272d9b6f244a2260688a5387209c87ebe1d83c
3
+ size 3850075
SnowballTarget/SnowballTarget-349968.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ad73c3ea2a9e86ba2d94cf9093cdf666de4ae4cbe17100408757f29e9568046
3
+ size 650646
SnowballTarget/SnowballTarget-349968.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d9c2dd67ff84fa84d3e302f069e4fa7a68353cddcda7965dcdbde49d75f4f6d
3
+ size 3850075
SnowballTarget/SnowballTarget-399968.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20114b9c21db81c431afac297816f79b283273e8d2c8d6ad8c2bf8b1d8d865c0
3
+ size 650646
SnowballTarget/SnowballTarget-399968.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:119fc433cf348280e7d53ef38789cf5ef1af59762028e045e9ed8f2db72acbbd
3
+ size 3850075
SnowballTarget/SnowballTarget-449992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30166299b35f87622428d6687233fe6cf6949bdf777551bfc71f800874a649b5
3
+ size 650646
SnowballTarget/SnowballTarget-449992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f0eedafcec8549b0de3f9dce24e850e0f4c7d1e02edfd6446bdee815b18bc3c
3
+ size 3850075
SnowballTarget/SnowballTarget-499952.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d440f089a0c765997ad88a8ee5d6c6bd8303268e5ae77b0502db4540a166009f
3
+ size 650646
SnowballTarget/SnowballTarget-499952.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:128eb3a4f71aeeee37c6cb4c7153446e4ba0fbe7236cc924763e5f832232cd64
3
+ size 3850075
SnowballTarget/SnowballTarget-549976.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73df0f7495abcbba24d5b259baef45b680cbc27f58ac6f794f8708be4fb5cb3e
3
+ size 650646
SnowballTarget/SnowballTarget-549976.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0252cb22b4b7362ad58320728f79f0b9706854f6143b52d76af4785d8e0ed906
3
+ size 3850075
SnowballTarget/SnowballTarget-599976.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b785ce816b93939d174e3bfb3bdc4b691607aabf04f3ee83f4408ec435517f77
3
+ size 650646
SnowballTarget/SnowballTarget-599976.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a37a1bbbe2ca418eda471e1c3e836f3facc186c4fbd09275172c044a568f76b
3
+ size 3850075
SnowballTarget/SnowballTarget-600424.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b785ce816b93939d174e3bfb3bdc4b691607aabf04f3ee83f4408ec435517f77
3
+ size 650646
SnowballTarget/SnowballTarget-600424.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0478774a76a13fbabac48904fa5bd009b6e9a080b2560537f2f2e88f94633c8d
3
+ size 3850075
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:28bf6cc2f8cc6d74e7e216e0b136470780d59233e4b67e09631be6bc899483bf
3
  size 3849250
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85a4b1415ee2fdc09c326b4be1b9b1860026b29cfa6a4263eda1c542400df7a6
3
  size 3849250
SnowballTarget/events.out.tfevents.1744014827.d65b556c3549.6037.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee23dd7eb18886e37bfa188317e2221738364f64c9a785fc0a220434e8977ee5
3
+ size 33801
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": 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": 600000, "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": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -38,7 +38,7 @@ behaviors:
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
- max_steps: 200000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: false
@@ -69,7 +69,7 @@ checkpoint_settings:
69
  run_id: SnowballTarget1
70
  initialize_from: null
71
  load_model: false
72
- resume: false
73
  force: false
74
  train_model: false
75
  inference: false
 
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
+ max_steps: 600000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: false
 
69
  run_id: SnowballTarget1
70
  initialize_from: null
71
  load_model: false
72
+ resume: true
73
  force: false
74
  train_model: false
75
  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: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 0.089 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: 0.667505 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]: 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 +166,22 @@ Memory Statistics:
169
  Peak Allocated Bytes 0 B
170
  Overflow Count 0
171
  [ALLOC_DEFAULT] Dual Thread Allocator
172
- Peak main deferred allocation count 40
173
  [ALLOC_BUCKET]
174
  Large Block size 4.0 MB
175
  Used Block count 1
176
  Peak Allocated bytes 1.0 MB
177
  [ALLOC_DEFAULT_MAIN]
178
- Peak usage frame count: [4.0 MB-8.0 MB]: 5458 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
- Peak Allocated memory 6.6 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
- Peak usage frame count: [16.0 MB-32.0 MB]: 5458 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
- Peak Allocated memory 17.8 MB
188
  Peak Large allocation bytes 16.0 MB
189
  [ALLOC_TEMP_JOB_1_FRAME]
190
  Initial Block Size 2.0 MB
@@ -213,13 +210,13 @@ Memory Statistics:
213
  Used Block count 1
214
  Peak Allocated bytes 1.0 MB
215
  [ALLOC_GFX_MAIN]
216
- Peak usage frame count: [32.0 KB-64.0 KB]: 4946 frames, [64.0 KB-128.0 KB]: 512 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]: 5458 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]: 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 +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]: 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
 
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 0.085 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: 0.730230 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]: 10736 frames, [16.0 KB-32.0 KB]: 181 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 36
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]: 10693 frames, [8.0 MB-16.0 MB]: 225 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
+ Peak Allocated memory 8.6 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 10918 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
+ Peak Allocated memory 17.5 MB
185
  Peak Large allocation bytes 16.0 MB
186
  [ALLOC_TEMP_JOB_1_FRAME]
187
  Initial Block Size 2.0 MB
 
210
  Used Block count 1
211
  Peak Allocated bytes 1.0 MB
212
  [ALLOC_GFX_MAIN]
213
+ Peak usage frame count: [32.0 KB-64.0 KB]: 10640 frames, [64.0 KB-128.0 KB]: 278 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
+ Peak Allocated memory 66.3 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
+ Peak usage frame count: [32.0 KB-64.0 KB]: 10918 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]: 10918 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]: 10917 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]: 10918 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]: 10918 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
@@ -2,213 +2,213 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 0.8510339856147766,
6
- "min": 0.8510339856147766,
7
- "max": 2.8751208782196045,
8
- "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 8088.22705078125,
12
- "min": 8088.22705078125,
13
- "max": 29349.234375,
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": 13.16726016998291,
30
- "min": 0.3833582103252411,
31
- "max": 13.16726016998291,
32
- "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2567.61572265625,
36
- "min": 74.37149047851562,
37
- "max": 2673.70166015625,
38
- "count": 20
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
- "value": 0.07005469284665784,
42
- "min": 0.06169717844593334,
43
- "max": 0.07423698450424233,
44
- "count": 20
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
- "value": 0.28021877138663137,
48
- "min": 0.24678871378373335,
49
- "max": 0.3696137725571901,
50
- "count": 20
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
- "value": 0.19273220999714208,
54
- "min": 0.1290213376735611,
55
- "max": 0.2861855329251757,
56
- "count": 20
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
- "value": 0.7709288399885683,
60
- "min": 0.5160853506942444,
61
- "max": 1.4309276646258784,
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": 25.90909090909091,
114
- "min": 3.3863636363636362,
115
- "max": 26.15909090909091,
116
- "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1140.0,
120
- "min": 149.0,
121
- "max": 1413.0,
122
- "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 25.90909090909091,
126
- "min": 3.3863636363636362,
127
- "max": 26.15909090909091,
128
- "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1140.0,
132
- "min": 149.0,
133
- "max": 1413.0,
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": "1744013830",
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",
155
  "mlagents_envs_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": "1744014269"
160
  },
161
- "total": 439.60087541799993,
162
  "count": 1,
163
- "self": 0.43740649399995846,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.022754302999999254,
167
  "count": 1,
168
- "self": 0.022754302999999254
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 439.140714621,
172
  "count": 1,
173
- "self": 0.373375250995025,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 2.9013213759999985,
177
  "count": 1,
178
- "self": 2.9013213759999985
179
  },
180
  "TrainerController.advance": {
181
- "total": 435.7798850590049,
182
- "count": 18192,
183
- "self": 0.3996947630085401,
184
  "children": {
185
  "env_step": {
186
- "total": 310.93616966799664,
187
- "count": 18192,
188
- "self": 236.74090274698688,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 73.97854171800856,
192
- "count": 18192,
193
- "self": 1.3314048809993437,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 72.64713683700921,
197
- "count": 18192,
198
- "self": 72.64713683700921
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.21672520300120368,
204
- "count": 18192,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 437.6342574350007,
209
- "count": 18192,
210
  "is_parallel": true,
211
- "self": 230.24996822800165,
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": 0.005324777999987873,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.003656945999864547,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.001667832000123326,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.001667832000123326
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.03746179000000893,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0006512140000722866,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.00041717900001003727,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.00041717900001003727
244
  },
245
  "communicator.exchange": {
246
- "total": 0.03456152899997278,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.03456152899997278
250
  },
251
  "steps_from_proto": {
252
- "total": 0.001831867999953829,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.00034025999997311374,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0014916079999807152,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0014916079999807152
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 207.38428920699903,
271
- "count": 18191,
272
  "is_parallel": true,
273
- "self": 9.892401289007353,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 5.611036559000297,
277
- "count": 18191,
278
  "is_parallel": true,
279
- "self": 5.611036559000297
280
  },
281
  "communicator.exchange": {
282
- "total": 158.9957084799974,
283
- "count": 18191,
284
  "is_parallel": true,
285
- "self": 158.9957084799974
286
  },
287
  "steps_from_proto": {
288
- "total": 32.885142878993975,
289
- "count": 18191,
290
  "is_parallel": true,
291
- "self": 5.907574949992977,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 26.977567929000998,
295
- "count": 181910,
296
  "is_parallel": true,
297
- "self": 26.977567929000998
298
  }
299
  }
300
  }
@@ -307,31 +307,31 @@
307
  }
308
  },
309
  "trainer_advance": {
310
- "total": 124.44402062799975,
311
- "count": 18192,
312
- "self": 0.44685120099956066,
313
  "children": {
314
  "process_trajectory": {
315
- "total": 27.678757379000047,
316
- "count": 18192,
317
- "self": 27.199399830000004,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
- "total": 0.4793575490000421,
321
- "count": 4,
322
- "self": 0.4793575490000421
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
- "total": 96.31841204800014,
328
- "count": 90,
329
- "self": 39.43467782499965,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
- "total": 56.88373422300049,
333
- "count": 4587,
334
- "self": 56.88373422300049
335
  }
336
  }
337
  }
@@ -340,19 +340,19 @@
340
  }
341
  },
342
  "trainer_threads": {
343
- "total": 1.040000029206567e-06,
344
  "count": 1,
345
- "self": 1.040000029206567e-06
346
  },
347
  "TrainerController._save_models": {
348
- "total": 0.08613189499999407,
349
  "count": 1,
350
- "self": 0.000912300999971194,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
- "total": 0.08521959400002288,
354
  "count": 1,
355
- "self": 0.08521959400002288
356
  }
357
  }
358
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.6334779262542725,
6
+ "min": 0.6207982301712036,
7
+ "max": 0.9066750407218933,
8
+ "count": 40
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 6466.54296875,
12
+ "min": 5900.06640625,
13
+ "max": 9335.1259765625,
14
+ "count": 40
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 599976.0,
18
+ "min": 209936.0,
19
+ "max": 599976.0,
20
+ "count": 40
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 599976.0,
24
+ "min": 209936.0,
25
+ "max": 599976.0,
26
+ "count": 40
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 13.873224258422852,
30
+ "min": 13.047223091125488,
31
+ "max": 13.905513763427734,
32
+ "count": 40
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2705.27880859375,
36
+ "min": 2535.58544921875,
37
+ "max": 2829.4677734375,
38
+ "count": 40
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
+ "value": 0.07047517671034097,
42
+ "min": 0.05911132975483732,
43
+ "max": 0.07519401556683257,
44
+ "count": 40
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
+ "value": 0.28190070684136387,
48
+ "min": 0.2364453190193493,
49
+ "max": 0.3726317275608844,
50
+ "count": 40
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
+ "value": 0.15974355364839235,
54
+ "min": 0.15134727390957814,
55
+ "max": 0.20510832848502142,
56
+ "count": 40
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
+ "value": 0.6389742145935694,
60
+ "min": 0.6181908014650438,
61
+ "max": 0.9627516944618786,
62
+ "count": 40
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
65
+ "value": 2.5380991539999983e-06,
66
+ "min": 2.5380991539999983e-06,
67
+ "max": 0.000197238034254,
68
+ "count": 40
69
  },
70
  "SnowballTarget.Policy.LearningRate.sum": {
71
+ "value": 1.0152396615999993e-05,
72
+ "min": 1.0152396615999993e-05,
73
+ "max": 0.00096144017952,
74
+ "count": 40
75
  },
76
  "SnowballTarget.Policy.Epsilon.mean": {
77
+ "value": 0.100846,
78
+ "min": 0.100846,
79
+ "max": 0.165746,
80
+ "count": 40
81
  },
82
  "SnowballTarget.Policy.Epsilon.sum": {
83
+ "value": 0.403384,
84
+ "min": 0.403384,
85
+ "max": 0.82048,
86
+ "count": 40
87
  },
88
  "SnowballTarget.Policy.Beta.mean": {
89
+ "value": 5.2215399999999974e-05,
90
+ "min": 5.2215399999999974e-05,
91
+ "max": 0.0032907254000000006,
92
+ "count": 40
93
  },
94
  "SnowballTarget.Policy.Beta.sum": {
95
+ "value": 0.0002088615999999999,
96
+ "min": 0.0002088615999999999,
97
+ "max": 0.016041952000000005,
98
+ "count": 40
99
  },
100
  "SnowballTarget.Environment.EpisodeLength.mean": {
101
  "value": 199.0,
102
  "min": 199.0,
103
  "max": 199.0,
104
+ "count": 40
105
  },
106
  "SnowballTarget.Environment.EpisodeLength.sum": {
107
  "value": 8756.0,
108
  "min": 8756.0,
109
  "max": 10945.0,
110
+ "count": 40
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 27.045454545454547,
114
+ "min": 25.363636363636363,
115
+ "max": 27.65909090909091,
116
+ "count": 40
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1190.0,
120
+ "min": 1116.0,
121
+ "max": 1493.0,
122
+ "count": 40
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 27.045454545454547,
126
+ "min": 25.363636363636363,
127
+ "max": 27.65909090909091,
128
+ "count": 40
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1190.0,
132
+ "min": 1116.0,
133
+ "max": 1493.0,
134
+ "count": 40
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
+ "count": 40
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
+ "count": 40
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1744014826",
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 --resume",
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": "2.6.0+cu124",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1744015705"
160
  },
161
+ "total": 878.6037278650001,
162
  "count": 1,
163
+ "self": 0.43774447400005556,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.023251321999850916,
167
  "count": 1,
168
+ "self": 0.023251321999850916
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 878.1427320690002,
172
  "count": 1,
173
+ "self": 0.7396353000456202,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 2.002484493999873,
177
  "count": 1,
178
+ "self": 2.002484493999873
179
  },
180
  "TrainerController.advance": {
181
+ "total": 875.307620128955,
182
+ "count": 36392,
183
+ "self": 0.7546325989544584,
184
  "children": {
185
  "env_step": {
186
+ "total": 624.4844617490025,
187
+ "count": 36392,
188
+ "self": 475.44420636804557,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 148.59203284697924,
192
+ "count": 36392,
193
+ "self": 2.610926098949676,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 145.98110674802956,
197
+ "count": 36392,
198
+ "self": 145.98110674802956
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.4482225339777415,
204
+ "count": 36392,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 875.3422665909873,
209
+ "count": 36392,
210
  "is_parallel": true,
211
+ "self": 458.74792514104206,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.0022797660001288023,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0007739850002508319,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0015057809998779703,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0015057809998779703
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.03830807800000002,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0006039380000402161,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0004521050000221294,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0004521050000221294
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.03497384999991482,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.03497384999991482
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0022781850000228587,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.00043533600023693,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0018428489997859288,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0018428489997859288
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 416.5943414499452,
271
+ "count": 36391,
272
  "is_parallel": true,
273
+ "self": 19.72895361689416,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 11.066761758010443,
277
+ "count": 36391,
278
  "is_parallel": true,
279
+ "self": 11.066761758010443
280
  },
281
  "communicator.exchange": {
282
+ "total": 319.7813514570007,
283
+ "count": 36391,
284
  "is_parallel": true,
285
+ "self": 319.7813514570007
286
  },
287
  "steps_from_proto": {
288
+ "total": 66.01727461803989,
289
+ "count": 36391,
290
  "is_parallel": true,
291
+ "self": 11.884214868036224,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 54.13305975000367,
295
+ "count": 363910,
296
  "is_parallel": true,
297
+ "self": 54.13305975000367
298
  }
299
  }
300
  }
 
307
  }
308
  },
309
  "trainer_advance": {
310
+ "total": 250.06852578099802,
311
+ "count": 36392,
312
+ "self": 0.9112952680043236,
313
  "children": {
314
  "process_trajectory": {
315
+ "total": 55.24219562699318,
316
+ "count": 36392,
317
+ "self": 54.37556592799251,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
+ "total": 0.8666296990006686,
321
+ "count": 8,
322
+ "self": 0.8666296990006686
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
+ "total": 193.9150348860005,
328
+ "count": 181,
329
+ "self": 76.92663030999051,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
+ "total": 116.98840457601,
333
+ "count": 9228,
334
+ "self": 116.98840457601
335
  }
336
  }
337
  }
 
340
  }
341
  },
342
  "trainer_threads": {
343
+ "total": 9.619998309062794e-07,
344
  "count": 1,
345
+ "self": 9.619998309062794e-07
346
  },
347
  "TrainerController._save_models": {
348
+ "total": 0.09299118399985673,
349
  "count": 1,
350
+ "self": 0.0012585089998538024,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
+ "total": 0.09173267500000293,
354
  "count": 1,
355
+ "self": 0.09173267500000293
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/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 16.454545454545453,
8
- "creation_time": 1744013942.098285,
 
 
 
 
 
 
 
 
 
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": 24.09090909090909,
17
- "creation_time": 1744014050.429006,
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": 26.09090909090909,
26
- "creation_time": 1744014159.6680856,
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": 26.0,
35
- "creation_time": 1744014269.4340312,
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": 26.0,
44
- "creation_time": 1744014269.5324588,
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": 26.0,
54
- "creation_time": 1744014269.5324588,
55
  "auxillary_file_paths": [
56
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },
 
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
+ "steps": 200112,
6
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
7
+ "reward": 26.0,
8
+ "creation_time": 1744014269.5324588,
9
+ "auxillary_file_paths": [
10
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
11
+ ]
12
+ },
13
+ {
14
+ "steps": 249984,
15
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-249984.onnx",
16
+ "reward": 25.545454545454547,
17
+ "creation_time": 1744014937.2066498,
18
  "auxillary_file_paths": [
19
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-249984.pt"
20
  ]
21
  },
22
  {
23
+ "steps": 299944,
24
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-299944.onnx",
25
+ "reward": 26.454545454545453,
26
+ "creation_time": 1744015044.505237,
27
  "auxillary_file_paths": [
28
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-299944.pt"
29
  ]
30
  },
31
  {
32
+ "steps": 349968,
33
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-349968.onnx",
34
  "reward": 26.09090909090909,
35
+ "creation_time": 1744015153.493432,
36
  "auxillary_file_paths": [
37
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-349968.pt"
38
  ]
39
  },
40
  {
41
+ "steps": 399968,
42
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-399968.onnx",
43
+ "reward": 26.181818181818183,
44
+ "creation_time": 1744015259.625503,
45
  "auxillary_file_paths": [
46
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-399968.pt"
47
  ]
48
  },
49
  {
50
+ "steps": 449992,
51
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-449992.onnx",
52
+ "reward": 26.636363636363637,
53
+ "creation_time": 1744015368.395237,
54
  "auxillary_file_paths": [
55
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-449992.pt"
56
+ ]
57
+ },
58
+ {
59
+ "steps": 499952,
60
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-499952.onnx",
61
+ "reward": 26.727272727272727,
62
+ "creation_time": 1744015478.2337365,
63
+ "auxillary_file_paths": [
64
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-499952.pt"
65
+ ]
66
+ },
67
+ {
68
+ "steps": 549976,
69
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-549976.onnx",
70
+ "reward": 26.727272727272727,
71
+ "creation_time": 1744015592.6854846,
72
+ "auxillary_file_paths": [
73
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-549976.pt"
74
+ ]
75
+ },
76
+ {
77
+ "steps": 599976,
78
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-599976.onnx",
79
+ "reward": 27.181818181818183,
80
+ "creation_time": 1744015704.4355943,
81
+ "auxillary_file_paths": [
82
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-599976.pt"
83
+ ]
84
+ },
85
+ {
86
+ "steps": 600424,
87
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-600424.onnx",
88
+ "reward": 27.181818181818183,
89
+ "creation_time": 1744015704.5700502,
90
+ "auxillary_file_paths": [
91
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-600424.pt"
92
  ]
93
  }
94
  ],
95
  "final_checkpoint": {
96
+ "steps": 600424,
97
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
98
+ "reward": 27.181818181818183,
99
+ "creation_time": 1744015704.5700502,
100
  "auxillary_file_paths": [
101
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-600424.pt"
102
  ]
103
  }
104
  },