Hugging Face's logo

Tiru8055
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files Metrics Community
Tiru8055 commited on
Commit
8adac6e
•
1 Parent(s): 11bf15b

First Push

Browse files
Files changed (22) hide show
  1. SnowballTarget.onnx +1 -1
  2. SnowballTarget/SnowballTarget-249984.onnx +3 -0
  3. SnowballTarget/SnowballTarget-249984.pt +3 -0
  4. SnowballTarget/SnowballTarget-299944.onnx +3 -0
  5. SnowballTarget/SnowballTarget-299944.pt +3 -0
  6. SnowballTarget/SnowballTarget-349968.onnx +3 -0
  7. SnowballTarget/SnowballTarget-349968.pt +3 -0
  8. SnowballTarget/SnowballTarget-399968.onnx +3 -0
  9. SnowballTarget/SnowballTarget-399968.pt +3 -0
  10. SnowballTarget/SnowballTarget-449992.onnx +3 -0
  11. SnowballTarget/SnowballTarget-449992.pt +3 -0
  12. SnowballTarget/SnowballTarget-499952.onnx +3 -0
  13. SnowballTarget/SnowballTarget-499952.pt +3 -0
  14. SnowballTarget/SnowballTarget-500016.onnx +3 -0
  15. SnowballTarget/SnowballTarget-500016.pt +3 -0
  16. SnowballTarget/checkpoint.pt +1 -1
  17. SnowballTarget/events.out.tfevents.1688361359.ffe632322ea5.4780.0 +3 -0
  18. config.json +1 -1
  19. configuration.yaml +2 -2
  20. run_logs/Player-0.log +15 -18
  21. run_logs/timers.json +163 -163
  22. run_logs/training_status.json +67 -22
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b840eb91a5e6521ef017585524401ec41e24cab99e94d3e2f1be467355c348ca
3
  size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72c21525d963aab9361932cffb61b8a8767d334705406fcf9767f2df700b08a0
3
  size 646532
SnowballTarget/SnowballTarget-249984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6f0f8e5ae31a0a6595b25e8c6195d399d87569ee606724398f3517ad05d018c
3
+ size 646532
SnowballTarget/SnowballTarget-249984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f98c0084b95ae84be8da3911149cac7918910a028f27415e5eb455510a2c5ed7
3
+ size 3843968
SnowballTarget/SnowballTarget-299944.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d164e38db96fb304695415638d60910756c48dae64ad402a7e00f10d3ad1460
3
+ size 646532
SnowballTarget/SnowballTarget-299944.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:655c05349b4b6d2cda393e519d73a48a7e3be912d6dc020d97da6083cc486a58
3
+ size 3843968
SnowballTarget/SnowballTarget-349968.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af861557ca09811875b9d91dd0fdecea9b556d0cdcc1198c8ddf7ca8f47487bd
3
+ size 646532
SnowballTarget/SnowballTarget-349968.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f4b5eccc602b2f9f84e77032890cbc87b83d01de3027ceb6771df10047ce363
3
+ size 3843968
SnowballTarget/SnowballTarget-399968.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f48b50fec83dc37be9f17fa1f49aa6c9b16c210b23510857474952c79ee28fb3
3
+ size 646532
SnowballTarget/SnowballTarget-399968.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d985d556ad2844ec0bb394114ad8b91398163067bb8533309fd2d0d6df124db
3
+ size 3843968
SnowballTarget/SnowballTarget-449992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ef875b5d499683b7604cb5f2797d9de9579c51ee6695c7cca0fceb0e358cae8
3
+ size 646532
SnowballTarget/SnowballTarget-449992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6bef5845adfd0dc936c65a20315b42025bf5177e40efd354e14bcca78d2da82
3
+ size 3843968
SnowballTarget/SnowballTarget-499952.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72c21525d963aab9361932cffb61b8a8767d334705406fcf9767f2df700b08a0
3
+ size 646532
SnowballTarget/SnowballTarget-499952.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:974042f92d99a1ecfcd8df3683a461bff6b6ac465037a45734b45bc9c1972a9a
3
+ size 3843968
SnowballTarget/SnowballTarget-500016.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72c21525d963aab9361932cffb61b8a8767d334705406fcf9767f2df700b08a0
3
+ size 646532
SnowballTarget/SnowballTarget-500016.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2acd54b73a0c6d4799d4a2c3270d82771984e4ffa693b2dd453b4ac71173204
3
+ size 3843968
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e8a2c04ceb9f4f0f2f753eeac84944fe31f1afe0c03fe7536dc74bd176d2676
3
  size 3843968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2acd54b73a0c6d4799d4a2c3270d82771984e4ffa693b2dd453b4ac71173204
3
  size 3843968
SnowballTarget/events.out.tfevents.1688361359.ffe632322ea5.4780.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7adb75a5e8cc3fcfd524dac7a219a83a9e41a4eade6a857678fae3b2751392f9
3
+ size 25630
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": 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": 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": 500000, "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: 500000
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 0.092 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: 0.814693 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]: 5369 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
@@ -169,22 +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]: 5461 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
- Peak Allocated memory 6.8 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
- Peak usage frame count: [16.0 MB-32.0 MB]: 5461 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
- Peak Allocated memory 17.6 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]: 4802 frames, [64.0 KB-128.0 KB]: 659 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]: 5461 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]: 5461 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]: 5460 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]: 5461 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]: 5461 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 0.080 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: 0.723080 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]: 8046 frames, [16.0 KB-32.0 KB]: 136 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 37
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]: 8183 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
+ Peak Allocated memory 7.8 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 8183 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
+ Peak Allocated memory 17.5 MB
185
  Peak Large allocation bytes 16.0 MB
186
  [ALLOC_TEMP_JOB_1_FRAME]
187
  Initial Block Size 2.0 MB
 
210
  Used Block count 1
211
  Peak Allocated bytes 1.0 MB
212
  [ALLOC_GFX_MAIN]
213
+ Peak usage frame count: [32.0 KB-64.0 KB]: 7994 frames, [64.0 KB-128.0 KB]: 189 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
+ Peak Allocated memory 66.0 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
+ Peak usage frame count: [32.0 KB-64.0 KB]: 8183 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]: 8183 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]: 8182 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]: 8183 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]: 8183 frames
256
  Requested Block Size 2.0 MB
257
  Peak Block count 1
258
  Peak Allocated memory 1.7 KB
run_logs/timers.json CHANGED
@@ -2,213 +2,213 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 0.8457798361778259,
6
- "min": 0.8457798361778259,
7
- "max": 2.8563437461853027,
8
- "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 8094.11279296875,
12
- "min": 8094.11279296875,
13
- "max": 29251.81640625,
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": 12.897496223449707,
30
- "min": 0.4525079131126404,
31
- "max": 12.897496223449707,
32
- "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2515.01171875,
36
- "min": 87.78653717041016,
37
- "max": 2620.910888671875,
38
- "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
- "count": 20
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
- "value": 8756.0,
48
  "min": 8756.0,
49
  "max": 10945.0,
50
- "count": 20
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
- "value": 0.0660408986672444,
54
- "min": 0.06202504008458573,
55
- "max": 0.07594248190694534,
56
- "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.2641635946689776,
60
- "min": 0.24810016033834292,
61
- "max": 0.37971240953472674,
62
- "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.20833415198413763,
66
- "min": 0.11108574133672222,
67
- "max": 0.2736487640469682,
68
- "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.8333366079365505,
72
- "min": 0.4443429653468889,
73
- "max": 1.368243820234841,
74
- "count": 20
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
- "value": 8.082097306000005e-06,
78
- "min": 8.082097306000005e-06,
79
- "max": 0.000291882002706,
80
- "count": 20
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
- "value": 3.232838922400002e-05,
84
- "min": 3.232838922400002e-05,
85
- "max": 0.00138516003828,
86
- "count": 20
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
- "value": 0.10269400000000001,
90
- "min": 0.10269400000000001,
91
- "max": 0.19729400000000002,
92
- "count": 20
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
- "value": 0.41077600000000003,
96
- "min": 0.41077600000000003,
97
- "max": 0.96172,
98
- "count": 20
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
- "value": 0.0001444306000000001,
102
- "min": 0.0001444306000000001,
103
- "max": 0.0048649706,
104
- "count": 20
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
107
- "value": 0.0005777224000000004,
108
- "min": 0.0005777224000000004,
109
- "max": 0.023089828,
110
- "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 25.613636363636363,
114
- "min": 3.8181818181818183,
115
- "max": 25.727272727272727,
116
- "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1127.0,
120
- "min": 168.0,
121
- "max": 1399.0,
122
- "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 25.613636363636363,
126
- "min": 3.8181818181818183,
127
- "max": 25.727272727272727,
128
- "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1127.0,
132
- "min": 168.0,
133
- "max": 1399.0,
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": "1688360621",
152
  "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1688361122"
160
  },
161
- "total": 500.95074694299996,
162
  "count": 1,
163
- "self": 0.4364345719999392,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.042037476000018614,
167
  "count": 1,
168
- "self": 0.042037476000018614
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 500.472274895,
172
  "count": 1,
173
- "self": 0.617950017999874,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 4.689369449000026,
177
  "count": 1,
178
- "self": 4.689369449000026
179
  },
180
  "TrainerController.advance": {
181
- "total": 495.0138066100002,
182
- "count": 18202,
183
- "self": 0.31194189099733194,
184
  "children": {
185
  "env_step": {
186
- "total": 494.70186471900286,
187
- "count": 18202,
188
- "self": 359.99233726200856,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 134.41122841800131,
192
- "count": 18202,
193
- "self": 1.976198901999112,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 132.4350295160022,
197
- "count": 18202,
198
- "self": 132.4350295160022
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.2982990389929796,
204
- "count": 18202,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 498.73344575299967,
209
- "count": 18202,
210
  "is_parallel": true,
211
- "self": 231.1729418770006,
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": 0.005294972000001508,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.003601630999980898,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0016933410000206095,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0016933410000206095
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.09222192999999379,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0006798279999884471,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.0003048659999649317,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.0003048659999649317
244
  },
245
  "communicator.exchange": {
246
- "total": 0.08895729800002528,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.08895729800002528
250
  },
251
  "steps_from_proto": {
252
- "total": 0.002279938000015136,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.00038622200003146645,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0018937159999836695,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0018937159999836695
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 267.5605038759991,
271
- "count": 18201,
272
  "is_parallel": true,
273
- "self": 11.011050943994746,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 5.68991407300183,
277
- "count": 18201,
278
  "is_parallel": true,
279
- "self": 5.68991407300183
280
  },
281
  "communicator.exchange": {
282
- "total": 212.22475883100407,
283
- "count": 18201,
284
  "is_parallel": true,
285
- "self": 212.22475883100407
286
  },
287
  "steps_from_proto": {
288
- "total": 38.63478002799843,
289
- "count": 18201,
290
  "is_parallel": true,
291
- "self": 7.204467238008817,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 31.430312789989614,
295
- "count": 182010,
296
  "is_parallel": true,
297
- "self": 31.430312789989614
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 9.930499993515696e-05,
313
  "count": 1,
314
- "self": 9.930499993515696e-05,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,36 +320,36 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 491.19399326699875,
324
- "count": 468403,
325
  "is_parallel": true,
326
- "self": 10.452562230021385,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 270.97192971297744,
330
- "count": 468403,
331
  "is_parallel": true,
332
- "self": 269.57651628297737,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
- "total": 1.395413430000076,
336
- "count": 4,
337
  "is_parallel": true,
338
- "self": 1.395413430000076
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
- "total": 209.76950132399992,
344
- "count": 90,
345
  "is_parallel": true,
346
- "self": 80.41273413999949,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
- "total": 129.35676718400043,
350
- "count": 4584,
351
  "is_parallel": true,
352
- "self": 129.35676718400043
353
  }
354
  }
355
  }
@@ -360,14 +360,14 @@
360
  }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.15104951299997538,
364
  "count": 1,
365
- "self": 0.0008534070000223437,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.15019610599995303,
369
  "count": 1,
370
- "self": 0.15019610599995303
371
  }
372
  }
373
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.5554143786430359,
6
+ "min": 0.5431214570999146,
7
+ "max": 0.8691041469573975,
8
+ "count": 30
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 5351.97314453125,
12
+ "min": 5228.943359375,
13
+ "max": 8976.9765625,
14
+ "count": 30
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 499952.0,
18
+ "min": 209936.0,
19
+ "max": 499952.0,
20
+ "count": 30
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 499952.0,
24
+ "min": 209936.0,
25
+ "max": 499952.0,
26
+ "count": 30
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 13.531689643859863,
30
+ "min": 12.990665435791016,
31
+ "max": 13.649582862854004,
32
+ "count": 30
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2760.464599609375,
36
+ "min": 2494.838134765625,
37
+ "max": 2784.514892578125,
38
+ "count": 30
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
+ "count": 30
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
+ "value": 10945.0,
48
  "min": 8756.0,
49
  "max": 10945.0,
50
+ "count": 30
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.0689360275408855,
54
+ "min": 0.06196786984219216,
55
+ "max": 0.08477714681004156,
56
+ "count": 30
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.3446801377044275,
60
+ "min": 0.24787147936876863,
61
+ "max": 0.3776190985734894,
62
+ "count": 30
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.17166311223717298,
66
+ "min": 0.1591150899801184,
67
+ "max": 0.21358135138072218,
68
+ "count": 30
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.8583155611858649,
72
+ "min": 0.6364603599204736,
73
+ "max": 0.9760537848753088,
74
+ "count": 30
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
+ "value": 3.1056989647999945e-06,
78
+ "min": 3.1056989647999945e-06,
79
+ "max": 0.00017668564110480002,
80
+ "count": 30
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
+ "value": 1.5528494823999972e-05,
84
+ "min": 1.5528494823999972e-05,
85
+ "max": 0.000853728215424,
86
+ "count": 30
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
+ "value": 0.10103520000000002,
90
+ "min": 0.10103520000000002,
91
+ "max": 0.15889520000000001,
92
+ "count": 30
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
+ "value": 0.5051760000000001,
96
+ "min": 0.4120608,
97
+ "max": 0.7845760000000002,
98
+ "count": 30
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
+ "value": 6.165647999999992e-05,
102
+ "min": 6.165647999999992e-05,
103
+ "max": 0.002948870480000001,
104
+ "count": 30
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
107
+ "value": 0.0003082823999999996,
108
+ "min": 0.0003082823999999996,
109
+ "max": 0.0142503424,
110
+ "count": 30
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 26.254545454545454,
114
+ "min": 25.072727272727274,
115
+ "max": 26.818181818181817,
116
+ "count": 30
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1444.0,
120
+ "min": 1137.0,
121
+ "max": 1472.0,
122
+ "count": 30
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 26.254545454545454,
126
+ "min": 25.072727272727274,
127
+ "max": 26.818181818181817,
128
+ "count": 30
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1444.0,
132
+ "min": 1137.0,
133
+ "max": 1472.0,
134
+ "count": 30
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
+ "count": 30
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
+ "count": 30
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1688361359",
152
  "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1688362084"
160
  },
161
+ "total": 725.1287801450001,
162
  "count": 1,
163
+ "self": 0.42301487899976564,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.03936998600011066,
167
  "count": 1,
168
+ "self": 0.03936998600011066
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 724.6663952800002,
172
  "count": 1,
173
+ "self": 0.8414607440045074,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 3.9242372219998742,
177
  "count": 1,
178
+ "self": 3.9242372219998742
179
  },
180
  "TrainerController.advance": {
181
+ "total": 719.7430740599957,
182
+ "count": 27274,
183
+ "self": 0.42077153500281383,
184
  "children": {
185
  "env_step": {
186
+ "total": 719.3223025249929,
187
+ "count": 27274,
188
+ "self": 524.3226615199812,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 194.58223836600496,
192
+ "count": 27274,
193
+ "self": 2.794133769002201,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 191.78810459700276,
197
+ "count": 27274,
198
+ "self": 191.78810459700276
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.4174026390066956,
204
+ "count": 27274,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 722.2940654699773,
209
+ "count": 27274,
210
  "is_parallel": true,
211
+ "self": 337.9235702160188,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.001969485000017812,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0005988259999867296,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0013706590000310825,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0013706590000310825
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.08242344599989337,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0006884039999022207,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.00045308199992177833,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.00045308199992177833
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.07630878300005861,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.07630878300005861
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0049731770000107645,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.002791672000057588,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0021815049999531766,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0021815049999531766
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 384.37049525395855,
271
+ "count": 27273,
272
  "is_parallel": true,
273
+ "self": 15.486524079959281,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 8.425367698016771,
277
+ "count": 27273,
278
  "is_parallel": true,
279
+ "self": 8.425367698016771
280
  },
281
  "communicator.exchange": {
282
+ "total": 305.2477889279937,
283
+ "count": 27273,
284
  "is_parallel": true,
285
+ "self": 305.2477889279937
286
  },
287
  "steps_from_proto": {
288
+ "total": 55.210814547988775,
289
+ "count": 27273,
290
  "is_parallel": true,
291
+ "self": 10.211360998963528,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 44.99945354902525,
295
+ "count": 272730,
296
  "is_parallel": true,
297
+ "self": 44.99945354902525
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 3.70650000149908e-05,
313
  "count": 1,
314
+ "self": 3.70650000149908e-05,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 714.1417267301904,
324
+ "count": 684441,
325
  "is_parallel": true,
326
+ "self": 15.42709771122577,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 390.330625886965,
330
+ "count": 684441,
331
  "is_parallel": true,
332
+ "self": 388.8141920999649,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
+ "total": 1.5164337870000963,
336
+ "count": 6,
337
  "is_parallel": true,
338
+ "self": 1.5164337870000963
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
+ "total": 308.38400313199963,
344
+ "count": 136,
345
  "is_parallel": true,
346
+ "self": 119.26334611800644,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 189.1206570139932,
350
+ "count": 6933,
351
  "is_parallel": true,
352
+ "self": 189.1206570139932
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.15758618900008514,
364
  "count": 1,
365
+ "self": 0.0010900650001985923,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.15649612399988655,
369
  "count": 1,
370
+ "self": 0.15649612399988655
371
  }
372
  }
373
  }
run_logs/training_status.json CHANGED
@@ -1,24 +1,6 @@
1
  {
2
  "SnowballTarget": {
3
  "checkpoints": [
4
- {
5
- "steps": 49936,
6
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 13.272727272727273,
8
- "creation_time": 1688360750.9501905,
9
- "auxillary_file_paths": [
10
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
11
- ]
12
- },
13
- {
14
- "steps": 99960,
15
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
16
- "reward": 22.272727272727273,
17
- "creation_time": 1688360873.446901,
18
- "auxillary_file_paths": [
19
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
20
- ]
21
- },
22
  {
23
  "steps": 149984,
24
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
@@ -45,15 +27,78 @@
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": 25.454545454545453,
54
- "creation_time": 1688361122.0340798,
55
  "auxillary_file_paths": [
56
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },
 
1
  {
2
  "SnowballTarget": {
3
  "checkpoints": [
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  {
5
  "steps": 149984,
6
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
 
27
  "auxillary_file_paths": [
28
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
29
  ]
30
+ },
31
+ {
32
+ "steps": 249984,
33
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-249984.onnx",
34
+ "reward": 25.818181818181817,
35
+ "creation_time": 1688361483.6038277,
36
+ "auxillary_file_paths": [
37
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-249984.pt"
38
+ ]
39
+ },
40
+ {
41
+ "steps": 299944,
42
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-299944.onnx",
43
+ "reward": 27.545454545454547,
44
+ "creation_time": 1688361602.0786066,
45
+ "auxillary_file_paths": [
46
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-299944.pt"
47
+ ]
48
+ },
49
+ {
50
+ "steps": 349968,
51
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-349968.onnx",
52
+ "reward": 26.0,
53
+ "creation_time": 1688361724.4352,
54
+ "auxillary_file_paths": [
55
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-349968.pt"
56
+ ]
57
+ },
58
+ {
59
+ "steps": 399968,
60
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-399968.onnx",
61
+ "reward": 27.727272727272727,
62
+ "creation_time": 1688361849.5447729,
63
+ "auxillary_file_paths": [
64
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-399968.pt"
65
+ ]
66
+ },
67
+ {
68
+ "steps": 449992,
69
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-449992.onnx",
70
+ "reward": 26.363636363636363,
71
+ "creation_time": 1688361966.9275382,
72
+ "auxillary_file_paths": [
73
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-449992.pt"
74
+ ]
75
+ },
76
+ {
77
+ "steps": 499952,
78
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-499952.onnx",
79
+ "reward": 26.363636363636363,
80
+ "creation_time": 1688362083.6424947,
81
+ "auxillary_file_paths": [
82
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-499952.pt"
83
+ ]
84
+ },
85
+ {
86
+ "steps": 500016,
87
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-500016.onnx",
88
+ "reward": 26.363636363636363,
89
+ "creation_time": 1688362083.81968,
90
+ "auxillary_file_paths": [
91
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-500016.pt"
92
+ ]
93
  }
94
  ],
95
  "final_checkpoint": {
96
+ "steps": 500016,
97
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
98
+ "reward": 26.363636363636363,
99
+ "creation_time": 1688362083.81968,
100
  "auxillary_file_paths": [
101
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-500016.pt"
102
  ]
103
  }
104
  },