Hugging Face's logo

FranticUser
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
FranticUser commited on
Commit
f0a4dcd
·
verified ·
1 Parent(s): 0f18fd8

Third Push

Browse files
Files changed (20) 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-249944.onnx +3 -0
  7. SnowballTarget/SnowballTarget-249944.pt +3 -0
  8. SnowballTarget/SnowballTarget-250008.onnx +3 -0
  9. SnowballTarget/SnowballTarget-250008.pt +3 -0
  10. SnowballTarget/SnowballTarget-49936.onnx +2 -2
  11. SnowballTarget/SnowballTarget-49936.pt +2 -2
  12. SnowballTarget/SnowballTarget-99960.onnx +2 -2
  13. SnowballTarget/SnowballTarget-99960.pt +2 -2
  14. SnowballTarget/checkpoint.pt +2 -2
  15. SnowballTarget/events.out.tfevents.1769894146.2712c3622527.4461.0 +3 -0
  16. config.json +1 -1
  17. configuration.yaml +3 -3
  18. run_logs/Player-0.log +17 -14
  19. run_logs/timers.json +161 -161
  20. run_logs/training_status.json +27 -18
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:68464642da5fe7eef5742a830e7e3507de4c499c8e70ea85f8cdd9822b2ce1ba
3
- size 59101
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81fd1f01941456a3d422d298362ed37e147a4e7a2eb69ce3bd3057cfff19abb1
3
+ size 650646
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8dedb8bef27a25185ef7f071667641e42bde5cc7f112d5c1c691e78ca002e9d5
3
- size 59101
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa4b475b542101355dc45e31f68f2f2aa3f819fb448e3935197c611908e092f7
3
+ size 650646
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1fa5e0f4930d699ddbd308656747e89784436d2e7992193a2fcf448b4ae7a11f
3
- size 3850564
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffef77f9c4f5d95d9eca88a2252a63dde2b0156585a6480514f4175ea283dc08
3
+ size 3849902
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:facc1af6131d2809403ce7d669f560cd76bbf869a26c8e94f0b52cf71eca4cf3
3
- size 59101
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f503bcc0d7e947993bc773972352b3766b6a5ebff92e7abed02e248025e19738
3
+ size 650646
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a42bdff68dcd232ffbdac95606031dc1b9c430b91ac7044b1a8d0719404204bb
3
- size 3850564
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a2d289043cf0ba16f760b1e9fd586804df79838ab2782f8695badc5a04b3175
3
+ size 3849902
SnowballTarget/SnowballTarget-249944.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81fd1f01941456a3d422d298362ed37e147a4e7a2eb69ce3bd3057cfff19abb1
3
+ size 650646
SnowballTarget/SnowballTarget-249944.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4caa299f20ca3df5021188f826cdccb711978f3f7232ed8f0279ebc2c784421
3
+ size 3849902
SnowballTarget/SnowballTarget-250008.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81fd1f01941456a3d422d298362ed37e147a4e7a2eb69ce3bd3057cfff19abb1
3
+ size 650646
SnowballTarget/SnowballTarget-250008.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:827135c704ae755c6b4d10cb7f4e8a2347b75b22ab3eaf173bd1c44ed0e195a5
3
+ size 3849902
SnowballTarget/SnowballTarget-49936.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5d0b70f904cff800b4a049702dca142f9aeb36ea917868d68d20e85f6fa526f9
3
- size 59094
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:592344614e6fb91cd4848d551c21ddad344bd3507ccff9699f2cb9d4d8194656
3
+ size 650646
SnowballTarget/SnowballTarget-49936.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:250be8cadc0bffb9c5ed5689088f1e4631c2ca5f0c85b6f393111b7b7e89cead
3
- size 3850487
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90faacf90c5f1d5c566dff8388925c10bb0300b7a75d88d006074ce94ee944a7
3
+ size 3849827
SnowballTarget/SnowballTarget-99960.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1269d4160f3ac5eb296e2d0be3918441c55aac2760734bc9ea7d1e8f786d41cf
3
- size 59094
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1eb6a6c33e5246d4c78d3eb8ba812ea9c61294f840e6efa75b37ea5a0b24017c
3
+ size 650646
SnowballTarget/SnowballTarget-99960.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e5a1b2f440f5b42b8c12f4d7068fd2a5918bcb5ef7b173c300c0393019c180b0
3
- size 3850487
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84c7eaff9bd4fe5cf8a52f06ae65e2ccd35638bb3007ed0073dae8beeedb97e3
3
+ size 3849827
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c2a268999a3264684a575836eda6790a9639c488a3667ef1ee4773b119e9cce8
3
- size 3849717
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:097f00c4230eadc1ba7943ad7a66a9c8055b26c80af8fdca5628926f062cadb4
3
+ size 3849077
SnowballTarget/events.out.tfevents.1769894146.2712c3622527.4461.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:268a9d181180e7ad86580c9cfc65ca6cb6e1a1df7c4eea9a6a85d1658bd896fb
3
+ size 32284
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": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
 
1
+ {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.93, "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": 250000, "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}
configuration.yaml CHANGED
@@ -8,7 +8,7 @@ behaviors:
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
@@ -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
@@ -70,7 +70,7 @@ checkpoint_settings:
70
  initialize_from: null
71
  load_model: false
72
  resume: false
73
- force: true
74
  train_model: false
75
  inference: false
76
  results_dir: results
 
8
  learning_rate: 0.0003
9
  beta: 0.005
10
  epsilon: 0.2
11
+ lambd: 0.93
12
  num_epoch: 3
13
  shared_critic: false
14
  learning_rate_schedule: linear
 
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
+ max_steps: 250000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: false
 
70
  initialize_from: null
71
  load_model: false
72
  resume: false
73
+ force: false
74
  train_model: false
75
  inference: false
76
  results_dir: results
run_logs/Player-0.log CHANGED
@@ -2,6 +2,9 @@ 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
  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
@@ -31,7 +34,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
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 0.079 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)
@@ -42,7 +45,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
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: 0.597635 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.
@@ -50,7 +53,7 @@ Memory Statistics:
50
  [ALLOC_TEMP_TLS] TLS Allocator
51
  StackAllocators :
52
  [ALLOC_TEMP_MAIN]
53
- 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
54
  Initial Block Size 4.0 MB
55
  Current Block Size 4.0 MB
56
  Peak Allocated Bytes 2.0 MB
@@ -166,19 +169,19 @@ Memory Statistics:
166
  Peak Allocated Bytes 0 B
167
  Overflow Count 0
168
  [ALLOC_DEFAULT] Dual Thread Allocator
169
- Peak main deferred allocation count 44
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]: 5458 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
- Peak Allocated memory 7.2 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
- Peak usage frame count: [16.0 MB-32.0 MB]: 5458 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
  Peak Allocated memory 17.3 MB
@@ -210,13 +213,13 @@ Memory Statistics:
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]: 2447 frames, [64.0 KB-128.0 KB]: 3011 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
- Peak Allocated memory 68.2 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
- Peak usage frame count: [32.0 KB-64.0 KB]: 5458 frames
220
  Requested Block Size 16.0 MB
221
  Peak Block count 1
222
  Peak Allocated memory 39.6 KB
@@ -228,13 +231,13 @@ Memory Statistics:
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]: 5458 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]: 5457 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
@@ -246,13 +249,13 @@ Memory Statistics:
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]: 5458 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]: 5458 frames
256
  Requested Block Size 2.0 MB
257
  Peak Block count 1
258
  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
+ 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
  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 0.082 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: 0.654795 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]: 6705 frames, [16.0 KB-32.0 KB]: 113 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 36
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]: 6819 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
+ Peak Allocated memory 7.7 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
+ Peak usage frame count: [16.0 MB-32.0 MB]: 6819 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
  Peak Allocated memory 17.3 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]: 6440 frames, [64.0 KB-128.0 KB]: 379 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
+ Peak Allocated memory 66.4 KB
220
  Peak Large allocation bytes 0 B
221
  [ALLOC_GFX_THREAD]
222
+ Peak usage frame count: [32.0 KB-64.0 KB]: 6819 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]: 6819 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]: 6818 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]: 6819 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]: 6819 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
@@ -2,213 +2,213 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 1.1120237112045288,
6
- "min": 1.0221964120864868,
7
- "max": 2.8125956058502197,
8
- "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 10568.673828125,
12
- "min": 10434.5810546875,
13
- "max": 28710.9765625,
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": 10.936310768127441,
30
- "min": 0.24286645650863647,
31
- "max": 10.936310768127441,
32
- "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2132.58056640625,
36
- "min": 47.116092681884766,
37
- "max": 2226.1708984375,
38
- "count": 20
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
- "value": 0.07260002126214185,
42
- "min": 0.06467748650906216,
43
- "max": 0.07374800986464262,
44
- "count": 20
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
- "value": 0.2904000850485674,
48
- "min": 0.25870994603624864,
49
- "max": 0.36874004932321314,
50
- "count": 20
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
- "value": 0.18903927512320817,
54
- "min": 0.14099524074517117,
55
- "max": 0.2730388129458708,
56
- "count": 20
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
- "value": 0.7561571004928327,
60
- "min": 0.5639809629806847,
61
- "max": 1.365194064729354,
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": 21.636363636363637,
114
- "min": 3.772727272727273,
115
- "max": 21.636363636363637,
116
- "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 952.0,
120
- "min": 166.0,
121
- "max": 1178.0,
122
- "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 21.636363636363637,
126
- "min": 3.772727272727273,
127
- "max": 21.636363636363637,
128
- "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 952.0,
132
- "min": 166.0,
133
- "max": 1178.0,
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": "1769891502",
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 --force",
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": "2.10.0+cu128",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1769891938"
160
  },
161
- "total": 435.53454671300005,
162
  "count": 1,
163
- "self": 0.4280878899999152,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.024383125999975164,
167
  "count": 1,
168
- "self": 0.024383125999975164
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 435.08207569700016,
172
  "count": 1,
173
- "self": 0.33599969897522897,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 2.1866478430001735,
177
  "count": 1,
178
- "self": 2.1866478430001735
179
  },
180
  "TrainerController.advance": {
181
- "total": 430.6947136500248,
182
- "count": 18192,
183
- "self": 0.3362591200602765,
184
  "children": {
185
  "env_step": {
186
- "total": 305.69837874198356,
187
- "count": 18192,
188
- "self": 239.00231539799324,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 66.48070533299415,
192
- "count": 18192,
193
- "self": 1.2163548089861251,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 65.26435052400802,
197
- "count": 18192,
198
- "self": 65.26435052400802
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.21535801099616947,
204
- "count": 18192,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 428.92654440099705,
209
- "count": 18192,
210
  "is_parallel": true,
211
- "self": 218.68688461299325,
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": 0.0018740169998636702,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.0005569139989347605,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0013171030009289098,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0013171030009289098
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.07094306299995878,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0005387800001699361,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.0004080789999534318,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.0004080789999534318
244
  },
245
  "communicator.exchange": {
246
- "total": 0.06602191399997537,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.06602191399997537
250
  },
251
  "steps_from_proto": {
252
- "total": 0.003974289999860048,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.0004329550010879757,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.003541334998772072,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.003541334998772072
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 210.2396597880038,
271
- "count": 18191,
272
  "is_parallel": true,
273
- "self": 9.836912392081103,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 5.210151998959191,
277
- "count": 18191,
278
  "is_parallel": true,
279
- "self": 5.210151998959191
280
  },
281
  "communicator.exchange": {
282
- "total": 160.18188624398408,
283
- "count": 18191,
284
  "is_parallel": true,
285
- "self": 160.18188624398408
286
  },
287
  "steps_from_proto": {
288
- "total": 35.010709152979416,
289
- "count": 18191,
290
  "is_parallel": true,
291
- "self": 6.368384373154186,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 28.64232477982523,
295
- "count": 181910,
296
  "is_parallel": true,
297
- "self": 28.64232477982523
298
  }
299
  }
300
  }
@@ -307,31 +307,31 @@
307
  }
308
  },
309
  "trainer_advance": {
310
- "total": 124.66007578798099,
311
- "count": 18192,
312
- "self": 0.40798532700182477,
313
  "children": {
314
  "process_trajectory": {
315
- "total": 35.02175048697973,
316
- "count": 18192,
317
- "self": 25.731180004979706,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
- "total": 9.290570482000021,
321
- "count": 4,
322
- "self": 9.290570482000021
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
- "total": 89.23033997399943,
328
- "count": 90,
329
- "self": 36.98271864301296,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
- "total": 52.247621330986476,
333
- "count": 4587,
334
- "self": 52.247621330986476
335
  }
336
  }
337
  }
@@ -340,19 +340,19 @@
340
  }
341
  },
342
  "trainer_threads": {
343
- "total": 1.0160001693293452e-06,
344
  "count": 1,
345
- "self": 1.0160001693293452e-06
346
  },
347
  "TrainerController._save_models": {
348
- "total": 1.8647134889997687,
349
  "count": 1,
350
- "self": 0.00045965299977979157,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
- "total": 1.864253835999989,
354
  "count": 1,
355
- "self": 1.864253835999989
356
  }
357
  }
358
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.7498764395713806,
6
+ "min": 0.7498764395713806,
7
+ "max": 2.853954792022705,
8
+ "count": 25
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 7126.82568359375,
12
+ "min": 7126.82568359375,
13
+ "max": 29133.169921875,
14
+ "count": 25
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 249944.0,
18
  "min": 9952.0,
19
+ "max": 249944.0,
20
+ "count": 25
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 249944.0,
24
  "min": 9952.0,
25
+ "max": 249944.0,
26
+ "count": 25
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 13.129326820373535,
30
+ "min": 0.21694935858249664,
31
+ "max": 13.302552223205566,
32
+ "count": 25
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2547.08935546875,
36
+ "min": 42.08817672729492,
37
+ "max": 2713.720703125,
38
+ "count": 25
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
+ "value": 0.06237361735796131,
42
+ "min": 0.06102633918549948,
43
+ "max": 0.076506828447272,
44
+ "count": 25
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
+ "value": 0.24949446943184525,
48
+ "min": 0.24410535674199793,
49
+ "max": 0.38087669455340156,
50
+ "count": 25
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
+ "value": 0.15757101412643404,
54
+ "min": 0.09607985840343378,
55
+ "max": 0.2495065285879023,
56
+ "count": 25
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
+ "value": 0.6302840565057362,
60
+ "min": 0.3843194336137351,
61
+ "max": 1.2475326429395115,
62
+ "count": 25
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
65
+ "value": 5.7456980848e-06,
66
+ "min": 5.7456980848e-06,
67
+ "max": 0.0002935056021648,
68
+ "count": 25
69
  },
70
  "SnowballTarget.Policy.LearningRate.sum": {
71
+ "value": 2.29827923392e-05,
72
+ "min": 2.29827923392e-05,
73
+ "max": 0.0014081280306239997,
74
+ "count": 25
75
  },
76
  "SnowballTarget.Policy.Epsilon.mean": {
77
+ "value": 0.10191520000000001,
78
+ "min": 0.10191520000000001,
79
+ "max": 0.19783520000000002,
80
+ "count": 25
81
  },
82
  "SnowballTarget.Policy.Epsilon.sum": {
83
+ "value": 0.40766080000000005,
84
+ "min": 0.40766080000000005,
85
+ "max": 0.9693760000000002,
86
+ "count": 25
87
  },
88
  "SnowballTarget.Policy.Beta.mean": {
89
+ "value": 0.00010556848000000002,
90
+ "min": 0.00010556848000000002,
91
+ "max": 0.004891976480000001,
92
+ "count": 25
93
  },
94
  "SnowballTarget.Policy.Beta.sum": {
95
+ "value": 0.0004222739200000001,
96
+ "min": 0.0004222739200000001,
97
+ "max": 0.023471862399999998,
98
+ "count": 25
99
  },
100
  "SnowballTarget.Environment.EpisodeLength.mean": {
101
  "value": 199.0,
102
  "min": 199.0,
103
  "max": 199.0,
104
+ "count": 25
105
  },
106
  "SnowballTarget.Environment.EpisodeLength.sum": {
107
  "value": 8756.0,
108
  "min": 8756.0,
109
  "max": 10945.0,
110
+ "count": 25
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 25.65909090909091,
114
+ "min": 3.7045454545454546,
115
+ "max": 26.09090909090909,
116
+ "count": 25
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1129.0,
120
+ "min": 163.0,
121
+ "max": 1435.0,
122
+ "count": 25
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 25.65909090909091,
126
+ "min": 3.7045454545454546,
127
+ "max": 26.09090909090909,
128
+ "count": 25
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1129.0,
132
+ "min": 163.0,
133
+ "max": 1435.0,
134
+ "count": 25
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
+ "count": 25
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
+ "count": 25
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1769894145",
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": "2.8.0+cu128",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1769894671"
160
  },
161
+ "total": 525.4305488040001,
162
  "count": 1,
163
+ "self": 0.43517932300017037,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.026357548999953906,
167
  "count": 1,
168
+ "self": 0.026357548999953906
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 524.969011932,
172
  "count": 1,
173
+ "self": 0.4063689640138364,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 2.943450650999921,
177
  "count": 1,
178
+ "self": 2.943450650999921
179
  },
180
  "TrainerController.advance": {
181
+ "total": 521.545380152986,
182
+ "count": 22728,
183
+ "self": 0.4219052990054024,
184
  "children": {
185
  "env_step": {
186
+ "total": 375.5976816529925,
187
+ "count": 22728,
188
+ "self": 294.5825825719918,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 80.7671016880114,
192
+ "count": 22728,
193
+ "self": 1.460853781005767,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 79.30624790700563,
197
+ "count": 22728,
198
+ "self": 79.30624790700563
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.2479973929893049,
204
+ "count": 22728,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 522.802646034005,
209
+ "count": 22728,
210
  "is_parallel": true,
211
+ "self": 263.63541238800747,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.005017296999994869,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0036315639999884297,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0013857330000064394,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0013857330000064394
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.0364463920000162,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0005731820000391963,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.00038880099998550577,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.00038880099998550577
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.03368637799997032,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.03368637799997032
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.001798031000021183,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0003431369999589151,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0014548940000622679,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0014548940000622679
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 259.1672336459975,
271
+ "count": 22727,
272
  "is_parallel": true,
273
+ "self": 12.50310607400661,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 6.524809306989027,
277
+ "count": 22727,
278
  "is_parallel": true,
279
+ "self": 6.524809306989027
280
  },
281
  "communicator.exchange": {
282
+ "total": 197.82578640198744,
283
+ "count": 22727,
284
  "is_parallel": true,
285
+ "self": 197.82578640198744
286
  },
287
  "steps_from_proto": {
288
+ "total": 42.31353186301442,
289
+ "count": 22727,
290
  "is_parallel": true,
291
+ "self": 7.6822490900301545,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 34.631282772984264,
295
+ "count": 227270,
296
  "is_parallel": true,
297
+ "self": 34.631282772984264
298
  }
299
  }
300
  }
 
307
  }
308
  },
309
  "trainer_advance": {
310
+ "total": 145.52579320098812,
311
+ "count": 22728,
312
+ "self": 0.5145760540027595,
313
  "children": {
314
  "process_trajectory": {
315
+ "total": 30.967017710985942,
316
+ "count": 22728,
317
+ "self": 30.40582623298576,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
+ "total": 0.5611914780001825,
321
+ "count": 5,
322
+ "self": 0.5611914780001825
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
+ "total": 114.04419943599942,
328
+ "count": 113,
329
+ "self": 47.25833948199977,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
+ "total": 66.78585995399965,
333
+ "count": 5760,
334
+ "self": 66.78585995399965
335
  }
336
  }
337
  }
 
340
  }
341
  },
342
  "trainer_threads": {
343
+ "total": 1.0220001058769412e-06,
344
  "count": 1,
345
+ "self": 1.0220001058769412e-06
346
  },
347
  "TrainerController._save_models": {
348
+ "total": 0.07381114200006778,
349
  "count": 1,
350
+ "self": 0.0006677950002540456,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
+ "total": 0.07314334699981373,
354
  "count": 1,
355
+ "self": 0.07314334699981373
356
  }
357
  }
358
  }
run_logs/training_status.json CHANGED
@@ -4,8 +4,8 @@
4
  {
5
  "steps": 49936,
6
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 13.181818181818182,
8
- "creation_time": 1769891612.1475348,
9
  "auxillary_file_paths": [
10
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
11
  ]
@@ -13,8 +13,8 @@
13
  {
14
  "steps": 99960,
15
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
16
- "reward": 15.909090909090908,
17
- "creation_time": 1769891718.7945433,
18
  "auxillary_file_paths": [
19
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
@@ -22,8 +22,8 @@
22
  {
23
  "steps": 149984,
24
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
25
- "reward": 21.545454545454547,
26
- "creation_time": 1769891826.9017894,
27
  "auxillary_file_paths": [
28
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
@@ -31,35 +31,44 @@
31
  {
32
  "steps": 199984,
33
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
34
- "reward": 21.636363636363637,
35
- "creation_time": 1769891935.8171434,
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": 21.636363636363637,
44
- "creation_time": 1769891937.6938882,
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": 21.636363636363637,
54
- "creation_time": 1769891937.6938882,
55
  "auxillary_file_paths": [
56
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },
60
  "metadata": {
61
  "stats_format_version": "0.3.0",
62
  "mlagents_version": "1.2.0.dev0",
63
- "torch_version": "2.10.0+cu128"
64
  }
65
  }
 
4
  {
5
  "steps": 49936,
6
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
+ "reward": 15.363636363636363,
8
+ "creation_time": 1769894253.5645304,
9
  "auxillary_file_paths": [
10
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
11
  ]
 
13
  {
14
  "steps": 99960,
15
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
16
+ "reward": 22.818181818181817,
17
+ "creation_time": 1769894358.3183887,
18
  "auxillary_file_paths": [
19
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
 
22
  {
23
  "steps": 149984,
24
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
25
+ "reward": 26.09090909090909,
26
+ "creation_time": 1769894462.370743,
27
  "auxillary_file_paths": [
28
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
 
31
  {
32
  "steps": 199984,
33
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
34
+ "reward": 25.818181818181817,
35
+ "creation_time": 1769894565.860241,
36
  "auxillary_file_paths": [
37
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
39
  },
40
  {
41
+ "steps": 249944,
42
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-249944.onnx",
43
+ "reward": 25.181818181818183,
44
+ "creation_time": 1769894670.5026116,
45
  "auxillary_file_paths": [
46
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-249944.pt"
47
+ ]
48
+ },
49
+ {
50
+ "steps": 250008,
51
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-250008.onnx",
52
+ "reward": 25.181818181818183,
53
+ "creation_time": 1769894670.5819893,
54
+ "auxillary_file_paths": [
55
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-250008.pt"
56
  ]
57
  }
58
  ],
59
  "final_checkpoint": {
60
+ "steps": 250008,
61
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
62
+ "reward": 25.181818181818183,
63
+ "creation_time": 1769894670.5819893,
64
  "auxillary_file_paths": [
65
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-250008.pt"
66
  ]
67
  }
68
  },
69
  "metadata": {
70
  "stats_format_version": "0.3.0",
71
  "mlagents_version": "1.2.0.dev0",
72
+ "torch_version": "2.8.0+cu128"
73
  }
74
  }