Hugging Face's logo

vldnechai
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
vldnechai commited on
Commit
135d061
·
1 Parent(s): 3cea0ad

Second Push

Browse files
Files changed (19) hide show
  1. SnowballTarget.onnx +1 -1
  2. SnowballTarget/{SnowballTarget-49936.onnx → SnowballTarget-249984.onnx} +1 -1
  3. SnowballTarget/{SnowballTarget-49936.pt → SnowballTarget-249984.pt} +1 -1
  4. SnowballTarget/SnowballTarget-299944.onnx +3 -0
  5. SnowballTarget/SnowballTarget-299944.pt +3 -0
  6. SnowballTarget/SnowballTarget-349968.onnx +3 -0
  7. SnowballTarget/SnowballTarget-349968.pt +3 -0
  8. SnowballTarget/SnowballTarget-399968.onnx +3 -0
  9. SnowballTarget/SnowballTarget-399968.pt +3 -0
  10. SnowballTarget/SnowballTarget-400224.onnx +3 -0
  11. SnowballTarget/SnowballTarget-400224.pt +3 -0
  12. SnowballTarget/checkpoint.pt +1 -1
  13. SnowballTarget/events.out.tfevents.1682000879.4429b7bd17cb.11813.0 +3 -0
  14. SnowballTarget/events.out.tfevents.1682001032.4429b7bd17cb.12533.0 +3 -0
  15. config.json +1 -1
  16. configuration.yaml +2 -2
  17. run_logs/Player-0.log +14 -17
  18. run_logs/timers.json +135 -135
  19. run_logs/training_status.json +58 -13
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:db5cc79a0c22505f1a5bbcca18ec618b25d34fbc5eb33e8a7365e847c5740ffb
3
  size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd51e625dc2da2ca49116a26b20569191e9d1314d84ec9230dec9aaf437f7618
3
  size 646532
SnowballTarget/{SnowballTarget-49936.onnx → SnowballTarget-249984.onnx} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:959cd02777b274005a64cc3a24b850a4c147f7b7671a0bf4ce498b5856962f4b
3
  size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce58306a8b8be41d4c31edc372a66c932c73627c6448a7812806780cbce82022
3
  size 646532
SnowballTarget/{SnowballTarget-49936.pt → SnowballTarget-249984.pt} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d681b2c96c5d2857a2313c893bfb7ef869a3e2211a84b3e82d138b7cef96328
3
  size 3843968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a69986e65fd285a59f24e8de115c04830e45fdd07282f9e2a7da6986c2d87591
3
  size 3843968
SnowballTarget/SnowballTarget-299944.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3932a6f22334e6dcf72a34cf475bb00a400fe27d9916b39d682ba7566c453de6
3
+ size 646532
SnowballTarget/SnowballTarget-299944.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28dcd3ae761938e6097ac00534129e645df3b8d570353ead7200ccceed009a92
3
+ size 3843968
SnowballTarget/SnowballTarget-349968.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e01fe3fa6f66d86637a404249427636b5082103c654274f6d4073160908b194d
3
+ size 646532
SnowballTarget/SnowballTarget-349968.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c17fe7f6a8e1aae171d70352e34bf5eb8933159af7b8b04aae0ef8570586d44
3
+ size 3843968
SnowballTarget/SnowballTarget-399968.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd51e625dc2da2ca49116a26b20569191e9d1314d84ec9230dec9aaf437f7618
3
+ size 646532
SnowballTarget/SnowballTarget-399968.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c87954ed83af9b6fa8cc7cccd37c6ef973700e079addf8c72f9ca0b4ba9e8d80
3
+ size 3843968
SnowballTarget/SnowballTarget-400224.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd51e625dc2da2ca49116a26b20569191e9d1314d84ec9230dec9aaf437f7618
3
+ size 646532
SnowballTarget/SnowballTarget-400224.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5515849e358fad034ee444845c5032bd4a306f76571808ab29d8f4d11027ae38
3
+ size 3843968
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e2d68985385f25cacd4632d813328950411ff4815bb86b64698262f8fbb6c0f
3
  size 3843968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5515849e358fad034ee444845c5032bd4a306f76571808ab29d8f4d11027ae38
3
  size 3843968
SnowballTarget/events.out.tfevents.1682000879.4429b7bd17cb.11813.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5edce1c06a54955e74bcb98da95ac4d325f8e74c84254087571d556f2dbe4829
3
+ size 1113
SnowballTarget/events.out.tfevents.1682001032.4429b7bd17cb.12533.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96b15dff4e05b6555d38e0b7a50e7d8dce007730844c2f9920a3506dd292173d
3
+ size 17504
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 256, "buffer_size": 4096, "learning_rate": 0.001, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 4, "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": 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, "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}, "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": 256, "buffer_size": 4096, "learning_rate": 0.001, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 4, "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": 400000, "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, "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}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -38,7 +38,7 @@ behaviors:
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
- max_steps: 200000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: true
@@ -67,7 +67,7 @@ checkpoint_settings:
67
  run_id: SnowballTarget1
68
  initialize_from: null
69
  load_model: false
70
- resume: false
71
  force: false
72
  train_model: false
73
  inference: false
 
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
+ max_steps: 400000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: true
 
67
  run_id: SnowballTarget1
68
  initialize_from: null
69
  load_model: false
70
+ resume: true
71
  force: false
72
  train_model: false
73
  inference: false
run_logs/Player-0.log CHANGED
@@ -2,9 +2,6 @@ Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarge
2
  Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
3
  Preloaded 'lib_burst_generated.so'
4
  Preloaded 'libgrpc_csharp_ext.x64.so'
5
- PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face
6
- PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face/SnowballTarget
7
- Unable to load player prefs
8
  Initialize engine version: 2021.3.14f1 (eee1884e7226)
9
  [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
10
  Forcing GfxDevice: Null
@@ -34,7 +31,7 @@ ALSA lib pcm.c:2642:(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 0.239 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: 0.848593 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]: 5374 frames, [16.0 KB-32.0 KB]: 91 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
@@ -169,19 +166,19 @@ Memory Statistics:
169
  Peak Allocated Bytes 0 B
170
  Overflow Count 0
171
  [ALLOC_DEFAULT] Dual Thread Allocator
172
- Peak main deferred allocation count 40
173
  [ALLOC_BUCKET]
174
  Large Block size 4.0 MB
175
  Used Block count 1
176
  Peak Allocated bytes 1.0 MB
177
  [ALLOC_DEFAULT_MAIN]
178
- Peak usage frame count: [4.0 MB-8.0 MB]: 5466 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
- Peak Allocated memory 6.6 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
- Peak usage frame count: [16.0 MB-32.0 MB]: 5466 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
  Peak Allocated memory 17.8 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]: 4519 frames, [64.0 KB-128.0 KB]: 947 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
- Peak Allocated memory 67.3 KB
220
  Peak Large allocation bytes 0 B
221
  [ALLOC_GFX_THREAD]
222
- Peak usage frame count: [32.0 KB-64.0 KB]: 5466 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]: 5466 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]: 5465 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]: 5466 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]: 5466 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 0.082 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: 0.655943 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]: 5368 frames, [16.0 KB-32.0 KB]: 91 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]: 5460 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
+ Peak Allocated memory 6.8 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 5460 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
  Peak Allocated memory 17.8 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]: 5127 frames, [64.0 KB-128.0 KB]: 333 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]: 5460 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]: 5460 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]: 5459 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]: 5460 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]: 5460 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
@@ -2,39 +2,39 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 1.2964332103729248,
6
- "min": 1.2964332103729248,
7
- "max": 2.876581907272339,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 12421.126953125,
12
- "min": 12421.126953125,
13
- "max": 29490.71875,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
17
- "value": 199984.0,
18
- "min": 9952.0,
19
- "max": 199984.0,
20
  "count": 20
21
  },
22
  "SnowballTarget.Step.sum": {
23
- "value": 199984.0,
24
- "min": 9952.0,
25
- "max": 199984.0,
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 11.874255180358887,
30
- "min": 0.0630207434296608,
31
- "max": 11.874255180358887,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2315.479736328125,
36
- "min": 12.226024627685547,
37
- "max": 2360.9970703125,
38
  "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
@@ -50,87 +50,87 @@
50
  "count": 20
51
  },
52
  "SnowballTarget.Environment.CumulativeReward.mean": {
53
- "value": 24.954545454545453,
54
- "min": 3.159090909090909,
55
- "max": 24.954545454545453,
56
  "count": 20
57
  },
58
  "SnowballTarget.Environment.CumulativeReward.sum": {
59
- "value": 1098.0,
60
- "min": 139.0,
61
- "max": 1340.0,
62
  "count": 20
63
  },
64
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
65
- "value": 24.954545454545453,
66
- "min": 3.159090909090909,
67
- "max": 24.954545454545453,
68
  "count": 20
69
  },
70
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
71
- "value": 1098.0,
72
- "min": 139.0,
73
- "max": 1340.0,
74
  "count": 20
75
  },
76
  "SnowballTarget.Losses.PolicyLoss.mean": {
77
- "value": 0.05138360678820926,
78
- "min": 0.045204958968765016,
79
- "max": 0.05490300402230145,
80
  "count": 20
81
  },
82
  "SnowballTarget.Losses.PolicyLoss.sum": {
83
- "value": 0.10276721357641852,
84
- "min": 0.09040991793753003,
85
- "max": 0.1467789236100062,
86
  "count": 20
87
  },
88
  "SnowballTarget.Losses.ValueLoss.mean": {
89
- "value": 0.21666038518442826,
90
- "min": 0.11178035836885958,
91
- "max": 0.2929615406867336,
92
  "count": 20
93
  },
94
  "SnowballTarget.Losses.ValueLoss.sum": {
95
- "value": 0.4333207703688565,
96
- "min": 0.22356071673771916,
97
- "max": 0.8788846220602008,
98
  "count": 20
99
  },
100
  "SnowballTarget.Policy.LearningRate.mean": {
101
- "value": 2.1440097856000007e-05,
102
- "min": 2.1440097856000007e-05,
103
- "max": 0.000967440003256,
104
  "count": 20
105
  },
106
  "SnowballTarget.Policy.LearningRate.sum": {
107
- "value": 4.2880195712000015e-05,
108
- "min": 4.2880195712000015e-05,
109
- "max": 0.002473320052668,
110
  "count": 20
111
  },
112
  "SnowballTarget.Policy.Epsilon.mean": {
113
- "value": 0.10214400000000001,
114
- "min": 0.10214400000000001,
115
- "max": 0.19674399999999997,
116
  "count": 20
117
  },
118
  "SnowballTarget.Policy.Epsilon.sum": {
119
- "value": 0.20428800000000003,
120
- "min": 0.20428800000000003,
121
- "max": 0.5473320000000002,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.Beta.mean": {
125
- "value": 0.00011698560000000007,
126
- "min": 0.00011698560000000007,
127
- "max": 0.004837525599999999,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.Beta.sum": {
131
- "value": 0.00023397120000000015,
132
- "min": 0.00023397120000000015,
133
- "max": 0.012371866800000002,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
@@ -148,67 +148,67 @@
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1681999912",
152
  "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]",
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",
154
  "mlagents_version": "0.31.0.dev0",
155
  "mlagents_envs_version": "0.31.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "1.11.0+cu102",
158
  "numpy_version": "1.21.2",
159
- "end_time_seconds": "1682000421"
160
  },
161
- "total": 509.1392612510001,
162
  "count": 1,
163
- "self": 0.7895072819999314,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.1247930780000388,
167
  "count": 1,
168
- "self": 0.1247930780000388
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 508.22496089100014,
172
  "count": 1,
173
- "self": 0.5903146569958153,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 5.743534064000187,
177
  "count": 1,
178
- "self": 5.743534064000187
179
  },
180
  "TrainerController.advance": {
181
- "total": 501.6806136450043,
182
- "count": 18217,
183
- "self": 0.29399153302301784,
184
  "children": {
185
  "env_step": {
186
- "total": 501.3866221119813,
187
- "count": 18217,
188
- "self": 373.7101186559669,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 127.38157745900344,
192
- "count": 18217,
193
- "self": 1.8533085040285187,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 125.52826895497492,
197
- "count": 18217,
198
- "self": 125.52826895497492
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.2949259970109779,
204
- "count": 18217,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 506.54920564398276,
209
- "count": 18217,
210
  "is_parallel": true,
211
- "self": 243.04672060098483,
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": 0.007642546999932165,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.005566955999711354,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.002075591000220811,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.002075591000220811
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.11248527099996863,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0015077499999733845,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.0005064300000867661,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.0005064300000867661
244
  },
245
  "communicator.exchange": {
246
- "total": 0.10583866199999648,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.10583866199999648
250
  },
251
  "steps_from_proto": {
252
- "total": 0.004632428999912008,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.00046936699936850346,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.004163062000543505,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.004163062000543505
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 263.50248504299793,
271
- "count": 18216,
272
  "is_parallel": true,
273
- "self": 10.67647613702934,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 6.145170260005216,
277
- "count": 18216,
278
  "is_parallel": true,
279
- "self": 6.145170260005216
280
  },
281
  "communicator.exchange": {
282
- "total": 210.9219759910004,
283
- "count": 18216,
284
  "is_parallel": true,
285
- "self": 210.9219759910004
286
  },
287
  "steps_from_proto": {
288
- "total": 35.75886265496297,
289
- "count": 18216,
290
  "is_parallel": true,
291
- "self": 7.25186004895636,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 28.50700260600661,
295
- "count": 182160,
296
  "is_parallel": true,
297
- "self": 28.50700260600661
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 0.00011929599986615358,
313
  "count": 1,
314
- "self": 0.00011929599986615358,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,36 +320,36 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 496.54639711896834,
324
- "count": 555919,
325
  "is_parallel": true,
326
- "self": 14.262296219839982,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 327.95297185412824,
330
- "count": 555919,
331
  "is_parallel": true,
332
- "self": 326.7055392651282,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
- "total": 1.2474325890000273,
336
  "count": 4,
337
  "is_parallel": true,
338
- "self": 1.2474325890000273
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
- "total": 154.33112904500013,
344
  "count": 45,
345
  "is_parallel": true,
346
- "self": 82.38431791299513,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
- "total": 71.946811132005,
350
  "count": 3056,
351
  "is_parallel": true,
352
- "self": 71.946811132005
353
  }
354
  }
355
  }
@@ -360,14 +360,14 @@
360
  }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.21037922899995465,
364
  "count": 1,
365
- "self": 0.00540428400017845,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.2049749449997762,
369
  "count": 1,
370
- "self": 0.2049749449997762
371
  }
372
  }
373
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.8036160469055176,
6
+ "min": 0.8036160469055176,
7
+ "max": 1.2397760152816772,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 8167.95361328125,
12
+ "min": 7850.01904296875,
13
+ "max": 12710.18359375,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 399968.0,
18
+ "min": 209936.0,
19
+ "max": 399968.0,
20
  "count": 20
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 399968.0,
24
+ "min": 209936.0,
25
+ "max": 399968.0,
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 13.465797424316406,
30
+ "min": 12.02122974395752,
31
+ "max": 13.465797424316406,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2625.83056640625,
36
+ "min": 2308.076171875,
37
+ "max": 2736.95458984375,
38
  "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
 
50
  "count": 20
51
  },
52
  "SnowballTarget.Environment.CumulativeReward.mean": {
53
+ "value": 26.568181818181817,
54
+ "min": 24.931818181818183,
55
+ "max": 26.568181818181817,
56
  "count": 20
57
  },
58
  "SnowballTarget.Environment.CumulativeReward.sum": {
59
+ "value": 1169.0,
60
+ "min": 1097.0,
61
+ "max": 1457.0,
62
  "count": 20
63
  },
64
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
65
+ "value": 26.568181818181817,
66
+ "min": 24.931818181818183,
67
+ "max": 26.568181818181817,
68
  "count": 20
69
  },
70
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
71
+ "value": 1169.0,
72
+ "min": 1097.0,
73
+ "max": 1457.0,
74
  "count": 20
75
  },
76
  "SnowballTarget.Losses.PolicyLoss.mean": {
77
+ "value": 0.04708093827952432,
78
+ "min": 0.043778610084486635,
79
+ "max": 0.05104426599385025,
80
  "count": 20
81
  },
82
  "SnowballTarget.Losses.PolicyLoss.sum": {
83
+ "value": 0.09416187655904865,
84
+ "min": 0.08755722016897327,
85
+ "max": 0.15002422893560247,
86
  "count": 20
87
  },
88
  "SnowballTarget.Losses.ValueLoss.mean": {
89
+ "value": 0.15656700511189067,
90
+ "min": 0.15656700511189067,
91
+ "max": 0.20614122719887426,
92
  "count": 20
93
  },
94
  "SnowballTarget.Losses.ValueLoss.sum": {
95
+ "value": 0.31313401022378134,
96
+ "min": 0.31313401022378134,
97
+ "max": 0.576292968409903,
98
  "count": 20
99
  },
100
  "SnowballTarget.Policy.LearningRate.mean": {
101
+ "value": 1.0440098956000007e-05,
102
+ "min": 1.0440098956000007e-05,
103
+ "max": 0.00048344005165599997,
104
  "count": 20
105
  },
106
  "SnowballTarget.Policy.LearningRate.sum": {
107
+ "value": 2.0880197912000014e-05,
108
+ "min": 2.0880197912000014e-05,
109
+ "max": 0.0012358201764179999,
110
  "count": 20
111
  },
112
  "SnowballTarget.Policy.Epsilon.mean": {
113
+ "value": 0.10104400000000002,
114
+ "min": 0.10104400000000002,
115
+ "max": 0.14834400000000003,
116
  "count": 20
117
  },
118
  "SnowballTarget.Policy.Epsilon.sum": {
119
+ "value": 0.20208800000000005,
120
+ "min": 0.20208800000000005,
121
+ "max": 0.42358199999999996,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.Beta.mean": {
125
+ "value": 6.209560000000005e-05,
126
+ "min": 6.209560000000005e-05,
127
+ "max": 0.0024223656000000003,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.Beta.sum": {
131
+ "value": 0.0001241912000000001,
132
+ "min": 0.0001241912000000001,
133
+ "max": 0.0061967418000000015,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
 
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1682001031",
152
  "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]",
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": "0.31.0.dev0",
155
  "mlagents_envs_version": "0.31.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "1.11.0+cu102",
158
  "numpy_version": "1.21.2",
159
+ "end_time_seconds": "1682001531"
160
  },
161
+ "total": 500.0744705029997,
162
  "count": 1,
163
+ "self": 0.43700920399942333,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.11587146100009704,
167
  "count": 1,
168
+ "self": 0.11587146100009704
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 499.5215898380002,
172
  "count": 1,
173
+ "self": 0.5868092699829504,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 3.652955971999745,
177
  "count": 1,
178
+ "self": 3.652955971999745
179
  },
180
  "TrainerController.advance": {
181
+ "total": 495.13635417501746,
182
+ "count": 18200,
183
+ "self": 0.2876086750275135,
184
  "children": {
185
  "env_step": {
186
+ "total": 494.84874549998995,
187
+ "count": 18200,
188
+ "self": 368.07016639899166,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 126.47954610097395,
192
+ "count": 18200,
193
+ "self": 1.8020691599854217,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 124.67747694098853,
197
+ "count": 18200,
198
+ "self": 124.67747694098853
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.2990330000243375,
204
+ "count": 18200,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 497.8670632399553,
209
+ "count": 18200,
210
  "is_parallel": true,
211
+ "self": 238.29139352099446,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.0022070060003898107,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0006732950005243765,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0015337109998654341,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0015337109998654341
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.10292192699989755,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0006266099999265862,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.000476675999834697,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.000476675999834697
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.09954849799987642,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.09954849799987642
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.00227014300025985,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.00044758400008504395,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.001822559000174806,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.001822559000174806
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 259.57566971896085,
271
+ "count": 18199,
272
  "is_parallel": true,
273
+ "self": 10.23755472897028,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 5.9126614250053535,
277
+ "count": 18199,
278
  "is_parallel": true,
279
+ "self": 5.9126614250053535
280
  },
281
  "communicator.exchange": {
282
+ "total": 208.92869690997122,
283
+ "count": 18199,
284
  "is_parallel": true,
285
+ "self": 208.92869690997122
286
  },
287
  "steps_from_proto": {
288
+ "total": 34.496756655013996,
289
+ "count": 18199,
290
  "is_parallel": true,
291
+ "self": 6.896312140013833,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 27.600444515000163,
295
+ "count": 181990,
296
  "is_parallel": true,
297
+ "self": 27.600444515000163
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 0.0001900800002658798,
313
  "count": 1,
314
+ "self": 0.0001900800002658798,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 490.0417796281804,
324
+ "count": 550680,
325
  "is_parallel": true,
326
+ "self": 13.848489997127672,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 323.80108473005475,
330
+ "count": 550680,
331
  "is_parallel": true,
332
+ "self": 322.1471898110549,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
+ "total": 1.6538949189998675,
336
  "count": 4,
337
  "is_parallel": true,
338
+ "self": 1.6538949189998675
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
+ "total": 152.39220490099797,
344
  "count": 45,
345
  "is_parallel": true,
346
+ "self": 81.16971216701359,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 71.22249273398438,
350
  "count": 3056,
351
  "is_parallel": true,
352
+ "self": 71.22249273398438
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.1452803409997614,
364
  "count": 1,
365
+ "self": 0.0012633559995265387,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.14401698500023485,
369
  "count": 1,
370
+ "self": 0.14401698500023485
371
  }
372
  }
373
  }
run_logs/training_status.json CHANGED
@@ -1,15 +1,6 @@
1
  {
2
  "SnowballTarget": {
3
  "checkpoints": [
4
- {
5
- "steps": 49936,
6
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 10.636363636363637,
8
- "creation_time": 1682000044.6985354,
9
- "auxillary_file_paths": [
10
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
11
- ]
12
- },
13
  {
14
  "steps": 99960,
15
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
@@ -45,15 +36,69 @@
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": 24.545454545454547,
54
- "creation_time": 1682000420.8059154,
55
  "auxillary_file_paths": [
56
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },
 
1
  {
2
  "SnowballTarget": {
3
  "checkpoints": [
 
 
 
 
 
 
 
 
 
4
  {
5
  "steps": 99960,
6
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
 
36
  "auxillary_file_paths": [
37
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
38
  ]
39
+ },
40
+ {
41
+ "steps": 200112,
42
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
43
+ "reward": null,
44
+ "creation_time": 1682000883.1100755,
45
+ "auxillary_file_paths": [
46
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
47
+ ]
48
+ },
49
+ {
50
+ "steps": 249984,
51
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-249984.onnx",
52
+ "reward": 26.545454545454547,
53
+ "creation_time": 1682001160.5022836,
54
+ "auxillary_file_paths": [
55
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-249984.pt"
56
+ ]
57
+ },
58
+ {
59
+ "steps": 299944,
60
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-299944.onnx",
61
+ "reward": 26.045454545454547,
62
+ "creation_time": 1682001282.3670187,
63
+ "auxillary_file_paths": [
64
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-299944.pt"
65
+ ]
66
+ },
67
+ {
68
+ "steps": 349968,
69
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-349968.onnx",
70
+ "reward": 25.0,
71
+ "creation_time": 1682001408.4883945,
72
+ "auxillary_file_paths": [
73
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-349968.pt"
74
+ ]
75
+ },
76
+ {
77
+ "steps": 399968,
78
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-399968.onnx",
79
+ "reward": 26.09090909090909,
80
+ "creation_time": 1682001531.3253553,
81
+ "auxillary_file_paths": [
82
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-399968.pt"
83
+ ]
84
+ },
85
+ {
86
+ "steps": 400224,
87
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-400224.onnx",
88
+ "reward": 26.09090909090909,
89
+ "creation_time": 1682001531.5099182,
90
+ "auxillary_file_paths": [
91
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-400224.pt"
92
+ ]
93
  }
94
  ],
95
  "final_checkpoint": {
96
+ "steps": 400224,
97
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
98
+ "reward": 26.09090909090909,
99
+ "creation_time": 1682001531.5099182,
100
  "auxillary_file_paths": [
101
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-400224.pt"
102
  ]
103
  }
104
  },