Hugging Face's logo

arjunamate
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
arjunamate commited on
Commit
43d93cd
·
verified ·
1 Parent(s): 7d8c576

Second Push

Browse files
Files changed (18) 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-200112.onnx +2 -2
  7. SnowballTarget/SnowballTarget-200112.pt +2 -2
  8. SnowballTarget/SnowballTarget-49936.onnx +2 -2
  9. SnowballTarget/SnowballTarget-49936.pt +2 -2
  10. SnowballTarget/SnowballTarget-99960.onnx +2 -2
  11. SnowballTarget/SnowballTarget-99960.pt +2 -2
  12. SnowballTarget/checkpoint.pt +2 -2
  13. SnowballTarget/events.out.tfevents.1771235593.37c258d46b33.5172.0 +3 -0
  14. config.json +1 -1
  15. configuration.yaml +3 -3
  16. run_logs/Player-0.log +14 -18
  17. run_logs/timers.json +162 -155
  18. run_logs/training_status.json +58 -0
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:27868b475474b6cbe54485f0db9dcca6f4474e15b148e13064d04601fd250b95
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62426aa67bc91a6741cd401ee60ac6ec9cfc17c7444efe7f1ccd0a3081278583
3
+ size 14118135
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dcc1d8420530d5493f52b3c3b89b3ce378af3ff25b680af3614a3b2f7edcfdcf
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1dcc51493e2f5f662d89f5c15b6818ff5739e5b0f1a305b25c793a01b8ab263
3
+ size 14118135
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a75ef40475c25d87fd9fb6721b79c15a50a722e66bac4c924547beb07f43c06
3
- size 3849902
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cba63a8b269c3435d913ddb62ccb9d64081e6460de736862845787d6f42d27dc
3
+ size 84589455
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:27868b475474b6cbe54485f0db9dcca6f4474e15b148e13064d04601fd250b95
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62426aa67bc91a6741cd401ee60ac6ec9cfc17c7444efe7f1ccd0a3081278583
3
+ size 14118135
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:779255aaeedd5b9970f10e0f1a9efc7181dddaf61d70e6544aeda3c1da3119df
3
- size 3849902
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec7a8506e3ea9450f752643aaa5ddaff239e2c7c20e26fe96ef69ce2340b941f
3
+ size 84589455
SnowballTarget/SnowballTarget-200112.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:27868b475474b6cbe54485f0db9dcca6f4474e15b148e13064d04601fd250b95
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62426aa67bc91a6741cd401ee60ac6ec9cfc17c7444efe7f1ccd0a3081278583
3
+ size 14118135
SnowballTarget/SnowballTarget-200112.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9cd256f7bf11e9cee2ea140a62feb0c64deb515eb2285c32cb0ca215c1eec962
3
- size 3849902
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b16aa625e49afe23d1218fae12c5c542b92d6d27efe440f90cf40d954f8927c2
3
+ size 84589455
SnowballTarget/SnowballTarget-49936.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:caa2fc87d379b77c88df60214146c71fa658e6e0b97c37db4e1b33cf387595ae
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ca28c8868b654c35904d5a8548522fc753f5b774e05e6c32030ae6fb83bd991
3
+ size 14118135
SnowballTarget/SnowballTarget-49936.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fded5893b4d60ea75d3427a2a451a774fd9a33494aef6851efae3d4b0ee201bf
3
- size 3849827
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0795f83fd0b3a6f205d5aef4e424cd8dab2d23871c05fa9270e4c17c7bac023e
3
+ size 84589348
SnowballTarget/SnowballTarget-99960.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4774a7ce22f03a766359b9d5e689a5ce36e1c2319b932803fa9f460e222f4732
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6900001dc23ab4588de48b313f265ce3827105d23a7553b26aee6f34013b2ad9
3
+ size 14118135
SnowballTarget/SnowballTarget-99960.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f0c12a576062572ef2bb0e7f23890e941ff2c4fb4d423041819ba725e1a33304
3
- size 3849827
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15aa7d5a3776a591d6c7e5a6a5136fcd01a2ad5a40d1a734626d267902fddcc2
3
+ size 84589348
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7687844bf20cd7ae0809e4a0258cd3ebbe497ac4c31e11a727cfabb3f7f27350
3
- size 3849077
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f2516957e40bdacaa0ecb5cbbc6e2a8a7cd25b5a3369034e04355801f68aafa
3
+ size 84588278
SnowballTarget/events.out.tfevents.1771235593.37c258d46b33.5172.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:009a0bbd38d442eabe21db98d4fb0a220583032a3a458fb81f134e5d46fbcf5c
3
+ size 23380
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": 1024, "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": 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": "SnowballTarget2", "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
@@ -17,8 +17,8 @@ behaviors:
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
@@ -66,7 +66,7 @@ engine_settings:
66
  no_graphics_monitor: false
67
  environment_parameters: null
68
  checkpoint_settings:
69
- run_id: SnowballTarget1
70
  initialize_from: null
71
  load_model: false
72
  resume: false
 
17
  checkpoint_interval: 50000
18
  network_settings:
19
  normalize: false
20
+ hidden_units: 1024
21
+ num_layers: 4
22
  vis_encode_type: simple
23
  memory: null
24
  goal_conditioning_type: hyper
 
66
  no_graphics_monitor: false
67
  environment_parameters: null
68
  checkpoint_settings:
69
+ run_id: SnowballTarget2
70
  initialize_from: null
71
  load_model: false
72
  resume: 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 0.092 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)
@@ -45,16 +42,15 @@ 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: 0.689776 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
- GRPC Exception: Status(StatusCode=Cancelled, Detail="CANCELLED"). Disconnecting from trainer.
52
  Setting up 1 worker threads for Enlighten.
53
  Memory Statistics:
54
  [ALLOC_TEMP_TLS] TLS Allocator
55
  StackAllocators :
56
  [ALLOC_TEMP_MAIN]
57
- Peak usage frame count: [8.0 KB-16.0 KB]: 401 frames, [16.0 KB-32.0 KB]: 6 frames, [2.0 MB-4.0 MB]: 1 frames
58
  Initial Block Size 4.0 MB
59
  Current Block Size 4.0 MB
60
  Peak Allocated Bytes 2.0 MB
@@ -170,22 +166,22 @@ Memory Statistics:
170
  Peak Allocated Bytes 0 B
171
  Overflow Count 0
172
  [ALLOC_DEFAULT] Dual Thread Allocator
173
- Peak main deferred allocation count 33
174
  [ALLOC_BUCKET]
175
  Large Block size 4.0 MB
176
  Used Block count 1
177
  Peak Allocated bytes 1.0 MB
178
  [ALLOC_DEFAULT_MAIN]
179
- Peak usage frame count: [4.0 MB-8.0 MB]: 408 frames
180
  Requested Block Size 16.0 MB
181
  Peak Block count 1
182
- Peak Allocated memory 5.7 MB
183
  Peak Large allocation bytes 0 B
184
  [ALLOC_DEFAULT_THREAD]
185
- Peak usage frame count: [16.0 MB-32.0 MB]: 408 frames
186
  Requested Block Size 16.0 MB
187
  Peak Block count 1
188
- Peak Allocated memory 17.4 MB
189
  Peak Large allocation bytes 16.0 MB
190
  [ALLOC_TEMP_JOB_1_FRAME]
191
  Initial Block Size 2.0 MB
@@ -214,13 +210,13 @@ Memory Statistics:
214
  Used Block count 1
215
  Peak Allocated bytes 1.0 MB
216
  [ALLOC_GFX_MAIN]
217
- Peak usage frame count: [32.0 KB-64.0 KB]: 318 frames, [64.0 KB-128.0 KB]: 90 frames
218
  Requested Block Size 16.0 MB
219
  Peak Block count 1
220
  Peak Allocated memory 66.8 KB
221
  Peak Large allocation bytes 0 B
222
  [ALLOC_GFX_THREAD]
223
- Peak usage frame count: [32.0 KB-64.0 KB]: 408 frames
224
  Requested Block Size 16.0 MB
225
  Peak Block count 1
226
  Peak Allocated memory 39.6 KB
@@ -232,13 +228,13 @@ Memory Statistics:
232
  Used Block count 1
233
  Peak Allocated bytes 1.0 MB
234
  [ALLOC_CACHEOBJECTS_MAIN]
235
- Peak usage frame count: [0.5 MB-1.0 MB]: 408 frames
236
  Requested Block Size 4.0 MB
237
  Peak Block count 1
238
  Peak Allocated memory 0.6 MB
239
  Peak Large allocation bytes 0 B
240
  [ALLOC_CACHEOBJECTS_THREAD]
241
- Peak usage frame count: [0.5 MB-1.0 MB]: 407 frames, [2.0 MB-4.0 MB]: 1 frames
242
  Requested Block Size 4.0 MB
243
  Peak Block count 1
244
  Peak Allocated memory 2.2 MB
@@ -250,13 +246,13 @@ Memory Statistics:
250
  Used Block count 1
251
  Peak Allocated bytes 1.0 MB
252
  [ALLOC_TYPETREE_MAIN]
253
- Peak usage frame count: [0-1.0 KB]: 408 frames
254
  Requested Block Size 2.0 MB
255
  Peak Block count 1
256
  Peak Allocated memory 1.0 KB
257
  Peak Large allocation bytes 0 B
258
  [ALLOC_TYPETREE_THREAD]
259
- Peak usage frame count: [1.0 KB-2.0 KB]: 408 frames
260
  Requested Block Size 2.0 MB
261
  Peak Block count 1
262
  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 0.137 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: 0.900762 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.
49
  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
  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]: 5458 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
+ Peak Allocated memory 6.7 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 17.7 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]: 5190 frames, [64.0 KB-128.0 KB]: 268 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
  Peak Allocated memory 66.8 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
+ Peak usage frame count: [32.0 KB-64.0 KB]: 5458 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]: 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
  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
run_logs/timers.json CHANGED
@@ -2,213 +2,213 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 2.821643114089966,
6
- "min": 2.821643114089966,
7
- "max": 2.821643114089966,
8
- "count": 1
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 28803.333984375,
12
- "min": 28803.333984375,
13
- "max": 28803.333984375,
14
- "count": 1
15
  },
16
  "SnowballTarget.Step.mean": {
17
- "value": 9952.0,
18
  "min": 9952.0,
19
- "max": 9952.0,
20
- "count": 1
21
  },
22
  "SnowballTarget.Step.sum": {
23
- "value": 9952.0,
24
  "min": 9952.0,
25
- "max": 9952.0,
26
- "count": 1
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 0.4277043342590332,
30
- "min": 0.4277043342590332,
31
- "max": 0.4277043342590332,
32
- "count": 1
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 82.97463989257812,
36
- "min": 82.97463989257812,
37
- "max": 82.97463989257812,
38
- "count": 1
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
- "value": 0.06835801960489363,
42
- "min": 0.06835801960489363,
43
- "max": 0.06835801960489363,
44
- "count": 1
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
- "value": 0.2734320784195745,
48
- "min": 0.2734320784195745,
49
- "max": 0.2734320784195745,
50
- "count": 1
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
- "value": 0.13539279293720885,
54
- "min": 0.13539279293720885,
55
- "max": 0.13539279293720885,
56
- "count": 1
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
- "value": 0.5415711717488354,
60
- "min": 0.5415711717488354,
61
- "max": 0.5415711717488354,
62
- "count": 1
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
65
- "value": 0.000291882002706,
66
- "min": 0.000291882002706,
67
  "max": 0.000291882002706,
68
- "count": 1
69
  },
70
  "SnowballTarget.Policy.LearningRate.sum": {
71
- "value": 0.001167528010824,
72
- "min": 0.001167528010824,
73
- "max": 0.001167528010824,
74
- "count": 1
75
  },
76
  "SnowballTarget.Policy.Epsilon.mean": {
77
- "value": 0.19729400000000002,
78
- "min": 0.19729400000000002,
79
  "max": 0.19729400000000002,
80
- "count": 1
81
  },
82
  "SnowballTarget.Policy.Epsilon.sum": {
83
- "value": 0.7891760000000001,
84
- "min": 0.7891760000000001,
85
- "max": 0.7891760000000001,
86
- "count": 1
87
  },
88
  "SnowballTarget.Policy.Beta.mean": {
89
- "value": 0.0048649706,
90
- "min": 0.0048649706,
91
  "max": 0.0048649706,
92
- "count": 1
93
  },
94
  "SnowballTarget.Policy.Beta.sum": {
95
- "value": 0.0194598824,
96
- "min": 0.0194598824,
97
- "max": 0.0194598824,
98
- "count": 1
99
  },
100
  "SnowballTarget.Environment.EpisodeLength.mean": {
101
  "value": 199.0,
102
  "min": 199.0,
103
  "max": 199.0,
104
- "count": 1
105
  },
106
  "SnowballTarget.Environment.EpisodeLength.sum": {
107
  "value": 8756.0,
108
  "min": 8756.0,
109
- "max": 8756.0,
110
- "count": 1
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 3.909090909090909,
114
- "min": 3.909090909090909,
115
- "max": 3.909090909090909,
116
- "count": 1
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 172.0,
120
- "min": 172.0,
121
- "max": 172.0,
122
- "count": 1
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 3.909090909090909,
126
- "min": 3.909090909090909,
127
- "max": 3.909090909090909,
128
- "count": 1
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 172.0,
132
- "min": 172.0,
133
- "max": 172.0,
134
- "count": 1
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
- "count": 1
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
- "count": 1
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1771235480",
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": "1771235520"
160
  },
161
- "total": 39.646496189000004,
162
  "count": 1,
163
- "self": 0.48182900199992673,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.026747376000002987,
167
  "count": 1,
168
- "self": 0.026747376000002987
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 39.137919811000074,
172
  "count": 1,
173
- "self": 0.030573536997735573,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 3.461824671000045,
177
  "count": 1,
178
- "self": 3.461824671000045
179
  },
180
  "TrainerController.advance": {
181
- "total": 35.64411465700232,
182
- "count": 1359,
183
- "self": 0.0323910470018518,
184
  "children": {
185
  "env_step": {
186
- "total": 27.142750105000346,
187
- "count": 1359,
188
- "self": 21.171929606001868,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 5.9525552919989195,
192
- "count": 1359,
193
- "self": 0.1060865079988389,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 5.846468784000081,
197
- "count": 1359,
198
- "self": 5.846468784000081
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.01826520699955836,
204
- "count": 1358,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 39.02059578700164,
209
- "count": 1358,
210
  "is_parallel": true,
211
- "self": 20.516248202002203,
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": 0.005206495999914296,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.003599066999754541,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0016074290001597547,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0016074290001597547
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.08200166900007844,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.002381823000064287,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.0015376329999980953,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.0015376329999980953
244
  },
245
  "communicator.exchange": {
246
- "total": 0.0739739540000528,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.0739739540000528
250
  },
251
  "steps_from_proto": {
252
- "total": 0.004108258999963255,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.0004109260000859649,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0036973329998772897,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0036973329998772897
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 18.504347584999437,
271
- "count": 1357,
272
  "is_parallel": true,
273
- "self": 0.8520413290007127,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 0.476091859999201,
277
- "count": 1357,
278
  "is_parallel": true,
279
- "self": 0.476091859999201
280
  },
281
  "communicator.exchange": {
282
- "total": 14.00623891599912,
283
- "count": 1357,
284
  "is_parallel": true,
285
- "self": 14.00623891599912
286
  },
287
  "steps_from_proto": {
288
- "total": 3.169975480000403,
289
- "count": 1357,
290
  "is_parallel": true,
291
- "self": 0.5443843100018739,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 2.625591169998529,
295
- "count": 13570,
296
  "is_parallel": true,
297
- "self": 2.625591169998529
298
  }
299
  }
300
  }
@@ -307,24 +307,31 @@
307
  }
308
  },
309
  "trainer_advance": {
310
- "total": 8.468973505000122,
311
- "count": 1358,
312
- "self": 0.036086341999293836,
313
  "children": {
314
  "process_trajectory": {
315
- "total": 2.1546907510007713,
316
- "count": 1358,
317
- "self": 2.1546907510007713
 
 
 
 
 
 
 
318
  },
319
  "_update_policy": {
320
- "total": 6.278196412000057,
321
- "count": 6,
322
- "self": 2.508112299000004,
323
  "children": {
324
  "TorchPPOOptimizer.update": {
325
- "total": 3.7700841130000526,
326
- "count": 303,
327
- "self": 3.7700841130000526
328
  }
329
  }
330
  }
@@ -333,19 +340,19 @@
333
  }
334
  },
335
  "trainer_threads": {
336
- "total": 1.4649999684479553e-06,
337
  "count": 1,
338
- "self": 1.4649999684479553e-06
339
  },
340
  "TrainerController._save_models": {
341
- "total": 0.001405481000006148,
342
  "count": 1,
343
- "self": 2.3645000055694254e-05,
344
  "children": {
345
  "RLTrainer._checkpoint": {
346
- "total": 0.0013818359999504537,
347
  "count": 1,
348
- "self": 0.0013818359999504537
349
  }
350
  }
351
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 1.031793475151062,
6
+ "min": 1.0097428560256958,
7
+ "max": 2.8327786922454834,
8
+ "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 9806.1650390625,
12
+ "min": 9806.1650390625,
13
+ "max": 28917.00390625,
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": 13.39430046081543,
30
+ "min": 0.4049510359764099,
31
+ "max": 13.39430046081543,
32
+ "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2611.888671875,
36
+ "min": 78.56050109863281,
37
+ "max": 2717.641845703125,
38
+ "count": 20
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
+ "value": 0.06770996948790865,
42
+ "min": 0.06338850121748835,
43
+ "max": 0.07710218002908982,
44
+ "count": 20
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
+ "value": 0.2708398779516346,
48
+ "min": 0.2535540048699534,
49
+ "max": 0.3834374881839989,
50
+ "count": 20
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
+ "value": 0.18384962371897462,
54
+ "min": 0.12493921079280257,
55
+ "max": 0.3188552150101054,
56
+ "count": 20
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
+ "value": 0.7353984948758985,
60
+ "min": 0.4997568431712103,
61
+ "max": 1.5567299042846643,
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": 26.613636363636363,
114
+ "min": 3.840909090909091,
115
+ "max": 26.613636363636363,
116
+ "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1171.0,
120
+ "min": 169.0,
121
+ "max": 1446.0,
122
+ "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 26.613636363636363,
126
+ "min": 3.840909090909091,
127
+ "max": 26.613636363636363,
128
+ "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1171.0,
132
+ "min": 169.0,
133
+ "max": 1446.0,
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": "1771235592",
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=SnowballTarget2 --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": "1771236116"
160
  },
161
+ "total": 523.963878904,
162
  "count": 1,
163
+ "self": 0.4770405120002579,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.03891777099988758,
167
  "count": 1,
168
+ "self": 0.03891777099988758
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 523.4479206209999,
172
  "count": 1,
173
+ "self": 0.43900507999751426,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 2.405319562999921,
177
  "count": 1,
178
+ "self": 2.405319562999921
179
  },
180
  "TrainerController.advance": {
181
+ "total": 520.1848365720025,
182
+ "count": 18192,
183
+ "self": 0.4309070269584936,
184
  "children": {
185
  "env_step": {
186
+ "total": 371.3020106790343,
187
+ "count": 18192,
188
+ "self": 288.39580851905407,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 82.64306480999016,
192
+ "count": 18192,
193
+ "self": 1.4113672499995573,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 81.23169755999061,
197
+ "count": 18192,
198
+ "self": 81.23169755999061
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.26313734999007465,
204
+ "count": 18192,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 520.7289981980091,
209
+ "count": 18192,
210
  "is_parallel": true,
211
+ "self": 267.34545497201907,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.003138624000030177,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0008645339999020507,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.002274090000128126,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.002274090000128126
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.03977024599998913,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0005931989996952325,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.00042645000007723866,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.00042645000007723866
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.03667198300013297,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.03667198300013297
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0020786140000836895,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0003909450001629011,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0016876689999207883,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0016876689999207883
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 253.38354322599002,
271
+ "count": 18191,
272
  "is_parallel": true,
273
+ "self": 11.665370154996253,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 6.306499689992961,
277
+ "count": 18191,
278
  "is_parallel": true,
279
+ "self": 6.306499689992961
280
  },
281
  "communicator.exchange": {
282
+ "total": 192.6655155389999,
283
+ "count": 18191,
284
  "is_parallel": true,
285
+ "self": 192.6655155389999
286
  },
287
  "steps_from_proto": {
288
+ "total": 42.74615784200091,
289
+ "count": 18191,
290
  "is_parallel": true,
291
+ "self": 7.410027365939868,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 35.336130476061044,
295
+ "count": 181910,
296
  "is_parallel": true,
297
+ "self": 35.336130476061044
298
  }
299
  }
300
  }
 
307
  }
308
  },
309
  "trainer_advance": {
310
+ "total": 148.4519188660097,
311
+ "count": 18192,
312
+ "self": 0.5264141030054361,
313
  "children": {
314
  "process_trajectory": {
315
+ "total": 32.0468363040045,
316
+ "count": 18192,
317
+ "self": 30.215858211004615,
318
+ "children": {
319
+ "RLTrainer._checkpoint": {
320
+ "total": 1.8309780929998851,
321
+ "count": 4,
322
+ "self": 1.8309780929998851
323
+ }
324
+ }
325
  },
326
  "_update_policy": {
327
+ "total": 115.87866845899975,
328
+ "count": 90,
329
+ "self": 41.38713840200717,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
+ "total": 74.49153005699259,
333
+ "count": 4587,
334
+ "self": 74.49153005699259
335
  }
336
  }
337
  }
 
340
  }
341
  },
342
  "trainer_threads": {
343
+ "total": 9.539999155094847e-07,
344
  "count": 1,
345
+ "self": 9.539999155094847e-07
346
  },
347
  "TrainerController._save_models": {
348
+ "total": 0.41875845200002004,
349
  "count": 1,
350
+ "self": 0.007750537999982043,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
+ "total": 0.411007914000038,
354
  "count": 1,
355
+ "self": 0.411007914000038
356
  }
357
  }
358
  }
run_logs/training_status.json CHANGED
@@ -1,4 +1,62 @@
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "metadata": {
3
  "stats_format_version": "0.3.0",
4
  "mlagents_version": "1.2.0.dev0",
 
1
  {
2
+ "SnowballTarget": {
3
+ "checkpoints": [
4
+ {
5
+ "steps": 49936,
6
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-49936.onnx",
7
+ "reward": 14.363636363636363,
8
+ "creation_time": 1771235724.3325996,
9
+ "auxillary_file_paths": [
10
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-49936.pt"
11
+ ]
12
+ },
13
+ {
14
+ "steps": 99960,
15
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-99960.onnx",
16
+ "reward": 26.0,
17
+ "creation_time": 1771235855.0629365,
18
+ "auxillary_file_paths": [
19
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-99960.pt"
20
+ ]
21
+ },
22
+ {
23
+ "steps": 149984,
24
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.onnx",
25
+ "reward": 24.90909090909091,
26
+ "creation_time": 1771235985.8406959,
27
+ "auxillary_file_paths": [
28
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.pt"
29
+ ]
30
+ },
31
+ {
32
+ "steps": 199984,
33
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.onnx",
34
+ "reward": 27.272727272727273,
35
+ "creation_time": 1771236115.2730875,
36
+ "auxillary_file_paths": [
37
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.pt"
38
+ ]
39
+ },
40
+ {
41
+ "steps": 200112,
42
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.onnx",
43
+ "reward": 27.272727272727273,
44
+ "creation_time": 1771236115.699278,
45
+ "auxillary_file_paths": [
46
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.pt"
47
+ ]
48
+ }
49
+ ],
50
+ "final_checkpoint": {
51
+ "steps": 200112,
52
+ "file_path": "results/SnowballTarget2/SnowballTarget.onnx",
53
+ "reward": 27.272727272727273,
54
+ "creation_time": 1771236115.699278,
55
+ "auxillary_file_paths": [
56
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.pt"
57
+ ]
58
+ }
59
+ },
60
  "metadata": {
61
  "stats_format_version": "0.3.0",
62
  "mlagents_version": "1.2.0.dev0",