Hugging Face's logo

mike-krk
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files Metrics Community
mike-krk commited on
Commit
0d26b93
•
1 Parent(s): 794f1eb

More learning

Browse files
Files changed (20) hide show
  1. SnowballTarget.onnx +1 -1
  2. SnowballTarget/SnowballTarget-199960.onnx +3 -0
  3. SnowballTarget/SnowballTarget-199960.pt +3 -0
  4. SnowballTarget/SnowballTarget-200112.onnx +3 -0
  5. SnowballTarget/SnowballTarget-200112.pt +3 -0
  6. SnowballTarget/SnowballTarget-249984.onnx +3 -0
  7. SnowballTarget/SnowballTarget-249984.pt +3 -0
  8. SnowballTarget/SnowballTarget-299944.onnx +3 -0
  9. SnowballTarget/SnowballTarget-299944.pt +3 -0
  10. SnowballTarget/SnowballTarget-300520.onnx +3 -0
  11. SnowballTarget/SnowballTarget-300520.pt +3 -0
  12. SnowballTarget/checkpoint.pt +1 -1
  13. SnowballTarget/events.out.tfevents.1702854328.11e6c733cb64.4812.0 +3 -0
  14. SnowballTarget/events.out.tfevents.1702854366.11e6c733cb64.5030.0 +3 -0
  15. SnowballTarget/events.out.tfevents.1702854465.11e6c733cb64.5497.0 +3 -0
  16. config.json +1 -1
  17. configuration.yaml +4 -4
  18. run_logs/Player-0.log +15 -18
  19. run_logs/timers.json +162 -162
  20. run_logs/training_status.json +58 -4
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:320ea5853b2c820bf3ad3f39646d8fc53d2d892727c2d47659636c39c68fbdc9
3
  size 3919089
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6f10129027d2af2b654854ffb5b020bf69d2cffc856979e5e1830b5c6f3e207
3
  size 3919089
SnowballTarget/SnowballTarget-199960.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c413178c405a0a47a16c9e541e2915923f352dae36d45e510bd1a21355d53af7
3
+ size 3919089
SnowballTarget/SnowballTarget-199960.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d8cc61e0039c99b9cc39a8786c635a73a669f7437c5bea7dfc7d464d6f856bf
3
+ size 23438462
SnowballTarget/SnowballTarget-200112.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c413178c405a0a47a16c9e541e2915923f352dae36d45e510bd1a21355d53af7
3
+ size 3919089
SnowballTarget/SnowballTarget-200112.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6a86965120119aaa6809bb5c80f919fc43c9b95817cc7e105ba207bfa5f7e24
3
+ size 23438462
SnowballTarget/SnowballTarget-249984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bd0bcf95e565f6e05603988a2424b6e274ca85c4fc2d117225d62f9ce54c832
3
+ size 3919089
SnowballTarget/SnowballTarget-249984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a98e7e8d8fd2e3f6deb9ae31bd44b79324b59873910cc548b846b27f5d1474b
3
+ size 23438462
SnowballTarget/SnowballTarget-299944.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6f10129027d2af2b654854ffb5b020bf69d2cffc856979e5e1830b5c6f3e207
3
+ size 3919089
SnowballTarget/SnowballTarget-299944.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:241c2b59da53ab60fb3e90f58531d9ae0be950b77839b4ce846212257fc1278d
3
+ size 23438462
SnowballTarget/SnowballTarget-300520.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6f10129027d2af2b654854ffb5b020bf69d2cffc856979e5e1830b5c6f3e207
3
+ size 3919089
SnowballTarget/SnowballTarget-300520.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54afeb7f09aaea11f32bb84686fd4af982214622452ac49ceec3cbf8e4b1f7a1
3
+ size 23438462
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:97d990b90fb87a376490eeb4f37f4ac7157e266c36b2ecbfa715231a1d84e048
3
  size 23437285
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b555a795da2be99aeb1d1b630beeaec1161659e607ffe3b7c868b94966d97231
3
  size 23437285
SnowballTarget/events.out.tfevents.1702854328.11e6c733cb64.4812.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f55498718eeaaa4b74b95925db06afe779e5959337f0ea0bc5da46f74b2779c
3
+ size 1118
SnowballTarget/events.out.tfevents.1702854366.11e6c733cb64.5030.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01b014ebdbc6c11fd1b2192cb979dbb0a56f95e8085322c60557c92f0742a986
3
+ size 2826
SnowballTarget/events.out.tfevents.1702854465.11e6c733cb64.5497.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:423d6bc8eebe660a2c5d80d6c235a6e8022cedc1a6276300f84af6e5e9c44e6d
3
+ size 9578
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 4096, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 1, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 4, "vis_encode_type": "nature_cnn", "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": 180000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "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": 4096, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 2, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 4, "vis_encode_type": "nature_cnn", "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": 300000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "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
@@ -9,7 +9,7 @@ behaviors:
9
  beta: 0.005
10
  epsilon: 0.2
11
  lambd: 0.95
12
- num_epoch: 1
13
  shared_critic: false
14
  learning_rate_schedule: linear
15
  beta_schedule: linear
@@ -38,7 +38,7 @@ behaviors:
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
- max_steps: 180000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: true
@@ -69,8 +69,8 @@ checkpoint_settings:
69
  run_id: SnowballTarget1
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
 
9
  beta: 0.005
10
  epsilon: 0.2
11
  lambd: 0.95
12
+ num_epoch: 2
13
  shared_critic: false
14
  learning_rate_schedule: linear
15
  beta_schedule: linear
 
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
+ max_steps: 300000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: true
 
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
76
  results_dir: results
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)
@@ -45,7 +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: 0.767677 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]: 4838 frames, [16.0 KB-32.0 KB]: 82 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 41
173
  [ALLOC_BUCKET]
174
  Large Block size 4.0 MB
175
  Used Block count 1
176
  Peak Allocated bytes 1.0 MB
177
  [ALLOC_DEFAULT_MAIN]
178
- Peak usage frame count: [4.0 MB-8.0 MB]: 4921 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
- Peak Allocated memory 6.5 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
- Peak usage frame count: [16.0 MB-32.0 MB]: 4921 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]: 4317 frames, [64.0 KB-128.0 KB]: 604 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]: 4921 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]: 4921 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]: 4920 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]: 4921 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]: 4921 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 0.091 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: 0.762111 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]: 2694 frames, [16.0 KB-32.0 KB]: 45 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 33
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]: 2740 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
+ Peak Allocated memory 6.1 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 2740 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]: 2632 frames, [64.0 KB-128.0 KB]: 108 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
+ Peak Allocated memory 65.6 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
+ Peak usage frame count: [32.0 KB-64.0 KB]: 2740 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]: 2740 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]: 2739 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]: 2740 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]: 2740 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": 1.6929972171783447,
6
- "min": 1.6929972171783447,
7
- "max": 2.8880438804626465,
8
- "count": 18
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 17356.607421875,
12
- "min": 16742.732421875,
13
- "max": 29576.45703125,
14
- "count": 18
15
  },
16
  "SnowballTarget.Step.mean": {
17
- "value": 179992.0,
18
- "min": 9952.0,
19
- "max": 179992.0,
20
- "count": 18
21
  },
22
  "SnowballTarget.Step.sum": {
23
- "value": 179992.0,
24
- "min": 9952.0,
25
- "max": 179992.0,
26
- "count": 18
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 9.208724975585938,
30
- "min": 0.10320312529802322,
31
- "max": 9.208724975585938,
32
- "count": 18
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 1795.701416015625,
36
- "min": 20.021406173706055,
37
- "max": 1802.14892578125,
38
- "count": 18
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
- "count": 18
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
  "value": 10945.0,
48
  "min": 8756.0,
49
  "max": 10945.0,
50
- "count": 18
51
  },
52
  "SnowballTarget.Environment.CumulativeReward.mean": {
53
- "value": 20.068181818181817,
54
- "min": 2.659090909090909,
55
- "max": 20.068181818181817,
56
- "count": 18
57
  },
58
  "SnowballTarget.Environment.CumulativeReward.sum": {
59
- "value": 883.0,
60
- "min": 117.0,
61
- "max": 1100.0,
62
- "count": 18
63
  },
64
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
65
- "value": 20.068181818181817,
66
- "min": 2.659090909090909,
67
- "max": 20.068181818181817,
68
- "count": 18
69
  },
70
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
71
- "value": 883.0,
72
- "min": 117.0,
73
- "max": 1100.0,
74
- "count": 18
75
  },
76
  "SnowballTarget.Losses.PolicyLoss.mean": {
77
- "value": 0.06452939392286627,
78
- "min": 0.06054679269179948,
79
- "max": 0.07790721116608063,
80
- "count": 18
81
  },
82
  "SnowballTarget.Losses.PolicyLoss.sum": {
83
- "value": 0.12905878784573255,
84
- "min": 0.12109358538359896,
85
- "max": 0.2050682080871946,
86
- "count": 18
87
  },
88
  "SnowballTarget.Losses.ValueLoss.mean": {
89
- "value": 0.2846022833357839,
90
- "min": 0.09061473511896509,
91
- "max": 0.2953796546687098,
92
- "count": 18
93
  },
94
  "SnowballTarget.Losses.ValueLoss.sum": {
95
- "value": 0.5692045666715678,
96
- "min": 0.18122947023793018,
97
- "max": 0.8674189062679515,
98
- "count": 18
99
  },
100
  "SnowballTarget.Policy.LearningRate.mean": {
101
- "value": 1.048009650666666e-05,
102
- "min": 1.048009650666666e-05,
103
- "max": 0.0002891466702844444,
104
- "count": 18
105
  },
106
  "SnowballTarget.Policy.LearningRate.sum": {
107
- "value": 2.096019301333332e-05,
108
- "min": 2.096019301333332e-05,
109
- "max": 0.0007244400585199999,
110
- "count": 18
111
  },
112
  "SnowballTarget.Policy.Epsilon.mean": {
113
- "value": 0.10349333333333333,
114
- "min": 0.10349333333333333,
115
- "max": 0.19638222222222224,
116
- "count": 18
117
  },
118
  "SnowballTarget.Policy.Epsilon.sum": {
119
- "value": 0.20698666666666665,
120
- "min": 0.20698666666666665,
121
- "max": 0.5414800000000001,
122
- "count": 18
123
  },
124
  "SnowballTarget.Policy.Beta.mean": {
125
- "value": 0.00018431733333333327,
126
- "min": 0.00018431733333333327,
127
- "max": 0.00481947288888889,
128
- "count": 18
129
  },
130
  "SnowballTarget.Policy.Beta.sum": {
131
- "value": 0.00036863466666666654,
132
- "min": 0.00036863466666666654,
133
- "max": 0.012079852,
134
- "count": 18
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
- "count": 18
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
- "count": 18
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1702853704",
152
  "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
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": "1.1.0.dev0",
155
  "mlagents_envs_version": "1.1.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.1.2+cu121",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1702854078"
160
  },
161
- "total": 374.622606001,
162
  "count": 1,
163
- "self": 0.7551781009999559,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.052187521000007564,
167
  "count": 1,
168
- "self": 0.052187521000007564
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 373.81524037900004,
172
  "count": 1,
173
- "self": 0.549521746996902,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 3.2470254469999986,
177
  "count": 1,
178
- "self": 3.2470254469999986
179
  },
180
  "TrainerController.advance": {
181
- "total": 369.7275052090032,
182
- "count": 16401,
183
- "self": 0.24300600100127667,
184
  "children": {
185
  "env_step": {
186
- "total": 369.4844992080019,
187
- "count": 16401,
188
- "self": 246.1420566600101,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 123.08165968799051,
192
- "count": 16401,
193
- "self": 1.3165040729904263,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 121.76515561500008,
197
- "count": 16401,
198
- "self": 121.76515561500008
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.26078286000131357,
204
- "count": 16401,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 372.4376252899932,
209
- "count": 16401,
210
  "is_parallel": true,
211
- "self": 167.3908902529992,
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": 0.004762362999997549,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.0033200429999737935,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0014423200000237557,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0014423200000237557
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.03744889099999682,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0006182139999850733,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.000379739999971207,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.000379739999971207
244
  },
245
  "communicator.exchange": {
246
- "total": 0.034568916000011995,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.034568916000011995
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0018820210000285442,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.00036343400000760084,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0015185870000209434,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0015185870000209434
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 205.046735036994,
271
- "count": 16400,
272
  "is_parallel": true,
273
- "self": 9.746101874996214,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 4.843764070997111,
277
- "count": 16400,
278
  "is_parallel": true,
279
- "self": 4.843764070997111
280
  },
281
  "communicator.exchange": {
282
- "total": 159.58933366599837,
283
- "count": 16400,
284
  "is_parallel": true,
285
- "self": 159.58933366599837
286
  },
287
  "steps_from_proto": {
288
- "total": 30.867535425002302,
289
- "count": 16400,
290
  "is_parallel": true,
291
- "self": 5.877542509009686,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 24.989992915992616,
295
- "count": 164000,
296
  "is_parallel": true,
297
- "self": 24.989992915992616
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 0.0002773059999299221,
313
  "count": 1,
314
- "self": 0.0002773059999299221,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,36 +320,36 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 363.15500081794727,
324
- "count": 783405,
325
  "is_parallel": true,
326
- "self": 16.3650178339891,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 274.7544086049576,
330
- "count": 783405,
331
  "is_parallel": true,
332
- "self": 274.00049835895754,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
- "total": 0.7539102460000322,
336
- "count": 3,
337
  "is_parallel": true,
338
- "self": 0.7539102460000322
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
- "total": 72.0355743790006,
344
- "count": 40,
345
  "is_parallel": true,
346
- "self": 19.93166600299969,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
- "total": 52.1039083760009,
350
- "count": 1359,
351
  "is_parallel": true,
352
- "self": 52.1039083760009
353
  }
354
  }
355
  }
@@ -360,14 +360,14 @@
360
  }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.2909106700000166,
364
  "count": 1,
365
- "self": 0.005411652000020695,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.2854990179999959,
369
  "count": 1,
370
- "self": 0.2854990179999959
371
  }
372
  }
373
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 1.0691092014312744,
6
+ "min": 1.0691092014312744,
7
+ "max": 1.5942479372024536,
8
+ "count": 10
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 10972.267578125,
12
+ "min": 10888.201171875,
13
+ "max": 16309.15625,
14
+ "count": 10
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 299944.0,
18
+ "min": 209936.0,
19
+ "max": 299944.0,
20
+ "count": 10
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 299944.0,
24
+ "min": 209936.0,
25
+ "max": 299944.0,
26
+ "count": 10
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 12.593055725097656,
30
+ "min": 10.063211441040039,
31
+ "max": 12.593055725097656,
32
+ "count": 10
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2568.9833984375,
36
+ "min": 1932.1365966796875,
37
+ "max": 2568.9833984375,
38
+ "count": 10
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
+ "count": 10
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
  "value": 10945.0,
48
  "min": 8756.0,
49
  "max": 10945.0,
50
+ "count": 10
51
  },
52
  "SnowballTarget.Environment.CumulativeReward.mean": {
53
+ "value": 25.09090909090909,
54
+ "min": 21.136363636363637,
55
+ "max": 25.34090909090909,
56
+ "count": 10
57
  },
58
  "SnowballTarget.Environment.CumulativeReward.sum": {
59
+ "value": 1380.0,
60
+ "min": 930.0,
61
+ "max": 1393.0,
62
+ "count": 10
63
  },
64
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
65
+ "value": 25.09090909090909,
66
+ "min": 21.136363636363637,
67
+ "max": 25.34090909090909,
68
+ "count": 10
69
  },
70
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
71
+ "value": 1380.0,
72
+ "min": 930.0,
73
+ "max": 1393.0,
74
+ "count": 10
75
  },
76
  "SnowballTarget.Losses.PolicyLoss.mean": {
77
+ "value": 0.06916270711671506,
78
+ "min": 0.05830706287302104,
79
+ "max": 0.07310536152149058,
80
+ "count": 10
81
  },
82
  "SnowballTarget.Losses.PolicyLoss.sum": {
83
+ "value": 0.13832541423343012,
84
+ "min": 0.11661412574604207,
85
+ "max": 0.1972248834268505,
86
+ "count": 10
87
  },
88
  "SnowballTarget.Losses.ValueLoss.mean": {
89
+ "value": 0.21709369035328135,
90
+ "min": 0.20926002522601803,
91
+ "max": 0.2832611144624929,
92
+ "count": 10
93
  },
94
  "SnowballTarget.Losses.ValueLoss.sum": {
95
+ "value": 0.4341873807065627,
96
+ "min": 0.4341873807065627,
97
+ "max": 0.7940560870749109,
98
+ "count": 10
99
  },
100
  "SnowballTarget.Policy.LearningRate.mean": {
101
+ "value": 5.376098207999998e-06,
102
+ "min": 5.376098207999998e-06,
103
+ "max": 9.337606887466668e-05,
104
+ "count": 10
105
  },
106
  "SnowballTarget.Policy.LearningRate.sum": {
107
+ "value": 1.0752196415999996e-05,
108
+ "min": 1.0752196415999996e-05,
109
+ "max": 0.00019432823522399996,
110
+ "count": 10
111
  },
112
  "SnowballTarget.Policy.Epsilon.mean": {
113
+ "value": 0.10179200000000001,
114
+ "min": 0.10179200000000001,
115
+ "max": 0.13112533333333337,
116
+ "count": 10
117
  },
118
  "SnowballTarget.Policy.Epsilon.sum": {
119
+ "value": 0.20358400000000001,
120
+ "min": 0.20358400000000001,
121
+ "max": 0.364776,
122
+ "count": 10
123
  },
124
  "SnowballTarget.Policy.Beta.mean": {
125
+ "value": 9.942079999999998e-05,
126
+ "min": 9.942079999999998e-05,
127
+ "max": 0.0015631541333333333,
128
+ "count": 10
129
  },
130
  "SnowballTarget.Policy.Beta.sum": {
131
+ "value": 0.00019884159999999996,
132
+ "min": 0.00019884159999999996,
133
+ "max": 0.003262322400000001,
134
+ "count": 10
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
+ "count": 10
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
+ "count": 10
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1702854464",
152
  "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
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": "1.1.0.dev0",
155
  "mlagents_envs_version": "1.1.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.1.2+cu121",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1702854685"
160
  },
161
+ "total": 220.82709319900005,
162
  "count": 1,
163
+ "self": 0.6029564710001978,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.056017914999983986,
167
  "count": 1,
168
+ "self": 0.056017914999983986
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 220.16811881299986,
172
  "count": 1,
173
+ "self": 0.33025679398633656,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 2.0461344620000546,
177
  "count": 1,
178
+ "self": 2.0461344620000546
179
  },
180
  "TrainerController.advance": {
181
+ "total": 217.58931440201354,
182
+ "count": 9132,
183
+ "self": 0.13580619401659533,
184
  "children": {
185
  "env_step": {
186
+ "total": 217.45350820799695,
187
+ "count": 9132,
188
+ "self": 148.38303226201378,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 68.92934167998396,
192
+ "count": 9132,
193
+ "self": 0.7219665359930332,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 68.20737514399093,
197
+ "count": 9132,
198
+ "self": 68.20737514399093
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.14113426599919876,
204
+ "count": 9132,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 219.39355299799695,
209
+ "count": 9132,
210
  "is_parallel": true,
211
+ "self": 107.01856439499534,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.0016263719999187742,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.00047473800032094005,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0011516339995978342,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0011516339995978342
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.03596235300005901,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0006419720002668328,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0004035790000216366,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0004035790000216366
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.03301259499994558,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.03301259499994558
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0019042069998249644,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.00038447399970209517,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0015197330001228693,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0015197330001228693
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 112.37498860300161,
271
+ "count": 9131,
272
  "is_parallel": true,
273
+ "self": 5.284206426007586,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 2.6740532879891816,
277
+ "count": 9131,
278
  "is_parallel": true,
279
+ "self": 2.6740532879891816
280
  },
281
  "communicator.exchange": {
282
+ "total": 87.90271529498432,
283
+ "count": 9131,
284
  "is_parallel": true,
285
+ "self": 87.90271529498432
286
  },
287
  "steps_from_proto": {
288
+ "total": 16.514013594020525,
289
+ "count": 9131,
290
  "is_parallel": true,
291
+ "self": 3.078017339043754,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 13.435996254976772,
295
+ "count": 91310,
296
  "is_parallel": true,
297
+ "self": 13.435996254976772
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 0.0004031409998788149,
313
  "count": 1,
314
+ "self": 0.0004031409998788149,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 213.92445111497977,
324
+ "count": 444850,
325
  "is_parallel": true,
326
+ "self": 9.002163526009326,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 150.38162959797,
330
+ "count": 444850,
331
  "is_parallel": true,
332
+ "self": 149.88418699196995,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
+ "total": 0.49744260600004964,
336
+ "count": 2,
337
  "is_parallel": true,
338
+ "self": 0.49744260600004964
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
+ "total": 54.540657991000444,
344
+ "count": 22,
345
  "is_parallel": true,
346
+ "self": 17.89772584499974,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 36.6429321460007,
350
+ "count": 1494,
351
  "is_parallel": true,
352
+ "self": 36.6429321460007
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.20201001400005225,
364
  "count": 1,
365
+ "self": 0.004421799000056126,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.19758821499999613,
369
  "count": 1,
370
+ "self": 0.19758821499999613
371
  }
372
  }
373
  }
run_logs/training_status.json CHANGED
@@ -36,15 +36,69 @@
36
  "auxillary_file_paths": [
37
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-180312.pt"
38
  ]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
39
  }
40
  ],
41
  "final_checkpoint": {
42
- "steps": 180312,
43
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
44
- "reward": 20.545454545454547,
45
- "creation_time": 1702854077.8957617,
46
  "auxillary_file_paths": [
47
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-180312.pt"
48
  ]
49
  }
50
  },
 
36
  "auxillary_file_paths": [
37
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-180312.pt"
38
  ]
39
+ },
40
+ {
41
+ "steps": 180312,
42
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-180312.onnx",
43
+ "reward": null,
44
+ "creation_time": 1702854329.8310897,
45
+ "auxillary_file_paths": [
46
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-180312.pt"
47
+ ]
48
+ },
49
+ {
50
+ "steps": 199960,
51
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199960.onnx",
52
+ "reward": 22.727272727272727,
53
+ "creation_time": 1702854412.2912817,
54
+ "auxillary_file_paths": [
55
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-199960.pt"
56
+ ]
57
+ },
58
+ {
59
+ "steps": 200112,
60
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
61
+ "reward": 21.954545454545453,
62
+ "creation_time": 1702854412.6597676,
63
+ "auxillary_file_paths": [
64
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
65
+ ]
66
+ },
67
+ {
68
+ "steps": 249984,
69
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-249984.onnx",
70
+ "reward": 25.09090909090909,
71
+ "creation_time": 1702854576.308168,
72
+ "auxillary_file_paths": [
73
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-249984.pt"
74
+ ]
75
+ },
76
+ {
77
+ "steps": 299944,
78
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-299944.onnx",
79
+ "reward": 24.954545454545453,
80
+ "creation_time": 1702854684.4286485,
81
+ "auxillary_file_paths": [
82
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-299944.pt"
83
+ ]
84
+ },
85
+ {
86
+ "steps": 300520,
87
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-300520.onnx",
88
+ "reward": 24.954545454545453,
89
+ "creation_time": 1702854684.6838958,
90
+ "auxillary_file_paths": [
91
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-300520.pt"
92
+ ]
93
  }
94
  ],
95
  "final_checkpoint": {
96
+ "steps": 300520,
97
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
98
+ "reward": 24.954545454545453,
99
+ "creation_time": 1702854684.6838958,
100
  "auxillary_file_paths": [
101
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-300520.pt"
102
  ]
103
  }
104
  },