Hugging Face's logo

FredericProtat
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files Metrics Community
FredericProtat commited on
Commit
bec2880
•
1 Parent(s): 2135de1

Second Push

Browse files
Files changed (28) hide show
  1. SnowballTarget.onnx +1 -1
  2. SnowballTarget/SnowballTarget-1599992.onnx +3 -0
  3. SnowballTarget/SnowballTarget-1599992.pt +3 -0
  4. SnowballTarget/SnowballTarget-1649952.onnx +3 -0
  5. SnowballTarget/SnowballTarget-1649952.pt +3 -0
  6. SnowballTarget/SnowballTarget-1699952.onnx +3 -0
  7. SnowballTarget/SnowballTarget-1699952.pt +3 -0
  8. SnowballTarget/SnowballTarget-1749976.onnx +3 -0
  9. SnowballTarget/SnowballTarget-1749976.pt +3 -0
  10. SnowballTarget/SnowballTarget-1799936.onnx +3 -0
  11. SnowballTarget/SnowballTarget-1799936.pt +3 -0
  12. SnowballTarget/SnowballTarget-1849992.onnx +3 -0
  13. SnowballTarget/SnowballTarget-1849992.pt +3 -0
  14. SnowballTarget/SnowballTarget-1899960.onnx +3 -0
  15. SnowballTarget/SnowballTarget-1899960.pt +3 -0
  16. SnowballTarget/SnowballTarget-1949984.onnx +3 -0
  17. SnowballTarget/SnowballTarget-1949984.pt +3 -0
  18. SnowballTarget/SnowballTarget-1999944.onnx +3 -0
  19. SnowballTarget/SnowballTarget-1999944.pt +3 -0
  20. SnowballTarget/SnowballTarget-2000200.onnx +3 -0
  21. SnowballTarget/SnowballTarget-2000200.pt +3 -0
  22. SnowballTarget/checkpoint.pt +1 -1
  23. SnowballTarget/events.out.tfevents.1692965777.eebf89c569ba.28258.0 +3 -0
  24. config.json +1 -1
  25. configuration.yaml +1 -1
  26. run_logs/Player-0.log +18 -18
  27. run_logs/timers.json +162 -162
  28. run_logs/training_status.json +54 -54
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:acbac7dca0ecba239492ce964c1fca19f5724d70c6ed9b0098d7c1898ce60844
3
  size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b8fa3abc5e1ebeebeeb5fc95d454e1a75916cd1af2e6db4e68f195c663dcc53
3
  size 646532
SnowballTarget/SnowballTarget-1599992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fcce1f1a1e62799722b02be2c010eccd2886f7966f3beb3b5f0694b20a81fc1
3
+ size 646532
SnowballTarget/SnowballTarget-1599992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f26bcdb150da6742120b85a3f729f769073bc1f5d809b87014479bf8d6fbeda
3
+ size 3843968
SnowballTarget/SnowballTarget-1649952.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1e51116ce0dbfd9b477275605a37fe401fe9f98a1f82dc365c4568e3922fb6f
3
+ size 646532
SnowballTarget/SnowballTarget-1649952.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6c285677857a166676791bb33d17dfa6dfc709fd759f3dc794571b5abe6b537
3
+ size 3843968
SnowballTarget/SnowballTarget-1699952.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf31bb5b9fd8efc8cead6965d93aac6e1de64b1e39764ba329b3ca8c4772973c
3
+ size 646532
SnowballTarget/SnowballTarget-1699952.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cae02d46b639b02b28b3f413fe66dd036f67865cbbf2c92f62a94139c2688609
3
+ size 3843968
SnowballTarget/SnowballTarget-1749976.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:168c382a8f0d626cab6384f650d6d140206b548805d0d1dafe5002600dc7bcbc
3
+ size 646532
SnowballTarget/SnowballTarget-1749976.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4d64122285a827414deec7e3f37ee1ba6188393596d8917a3601348eabb06d4
3
+ size 3843968
SnowballTarget/SnowballTarget-1799936.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bfb3c7151c137018b9c75114bc5aacf124469db7ded513451ef879f2494878c
3
+ size 646532
SnowballTarget/SnowballTarget-1799936.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ee019cfb2ef2fd418f9ab763fd1d725e02facda2b074e95e7b5fcfae1889ecd
3
+ size 3843968
SnowballTarget/SnowballTarget-1849992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d94f3f9ab1218e6ae0a2323c603c9959f3cd62da38a8a4235d9b522b10bc528d
3
+ size 646532
SnowballTarget/SnowballTarget-1849992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e42d2b25717ee65da0ffdc0f35538a5a0fa93504886b58ea882ac96357f9995
3
+ size 3843968
SnowballTarget/SnowballTarget-1899960.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d44b2a503023a9a2de23f66ec1b06b59ba99ab3f605c97535746de1938744a97
3
+ size 646532
SnowballTarget/SnowballTarget-1899960.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b51aa3619cc32562df87f3eed470b3054a7f25991c9225ed992c10378978af2c
3
+ size 3843968
SnowballTarget/SnowballTarget-1949984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d2c86237b6dbe8afe7d63b2d96291c130c442067405a1111501af555a819d3f
3
+ size 646532
SnowballTarget/SnowballTarget-1949984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49eac8981624a8841e7956d183eaa56a6f9547eb3664eba210d2a97a006e3dd5
3
+ size 3843968
SnowballTarget/SnowballTarget-1999944.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b8fa3abc5e1ebeebeeb5fc95d454e1a75916cd1af2e6db4e68f195c663dcc53
3
+ size 646532
SnowballTarget/SnowballTarget-1999944.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab8fae3b2188322e126ae1dede645c6887ad1a5d308a831097ad9523429c998a
3
+ size 3843968
SnowballTarget/SnowballTarget-2000200.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b8fa3abc5e1ebeebeeb5fc95d454e1a75916cd1af2e6db4e68f195c663dcc53
3
+ size 646532
SnowballTarget/SnowballTarget-2000200.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f90bd2de2340fba01aa400be7f9f0dadf1502d399bce924d77afd69681dedd6d
3
+ size 3843968
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a9de89d0237c813c8af328c3d926ed78d1c2f7264313293d695beeec072f303e
3
  size 3843968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f90bd2de2340fba01aa400be7f9f0dadf1502d399bce924d77afd69681dedd6d
3
  size 3843968
SnowballTarget/events.out.tfevents.1692965777.eebf89c569ba.28258.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:778be0e2a1f4c032aa27ada3dcd1780fcb5d0132b7f4434536e0b1e0858d1918
3
+ size 41680
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": 1500000, "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": "SnowballTarget2", "initialize_from": null, "load_model": false, "resume": true, "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": 2000000, "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": "SnowballTarget2", "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: 1500000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: true
 
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
+ max_steps: 2000000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: true
run_logs/Player-0.log CHANGED
@@ -31,7 +31,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
31
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
32
  FMOD initialized on nosound output
33
  Begin MonoManager ReloadAssembly
34
- - Completed reload, in 0.146 seconds
35
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
36
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
37
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -42,7 +42,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
42
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
43
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
44
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
45
- UnloadTime: 0.965593 ms
46
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
47
  requesting resize 84 x 84
48
  Setting up 1 worker threads for Enlighten.
@@ -50,7 +50,7 @@ Memory Statistics:
50
  [ALLOC_TEMP_TLS] TLS Allocator
51
  StackAllocators :
52
  [ALLOC_TEMP_MAIN]
53
- Peak usage frame count: [8.0 KB-16.0 KB]: 26826 frames, [16.0 KB-32.0 KB]: 454 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
@@ -166,23 +166,23 @@ Memory Statistics:
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]: 12032 frames, [8.0 MB-16.0 MB]: 15249 frames
176
  Requested Block Size 16.0 MB
177
- Peak Block count 2
178
- Peak Allocated memory 14.4 MB
179
- Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
- Peak usage frame count: [16.0 MB-32.0 MB]: 27281 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
- Peak Allocated memory 17.8 MB
185
- Peak Large allocation bytes 16.0 MB
186
  [ALLOC_TEMP_JOB_1_FRAME]
187
  Initial Block Size 2.0 MB
188
  Used Block Count 1
@@ -210,13 +210,13 @@ Memory Statistics:
210
  Used Block count 1
211
  Peak Allocated bytes 1.0 MB
212
  [ALLOC_GFX_MAIN]
213
- Peak usage frame count: [32.0 KB-64.0 KB]: 26734 frames, [64.0 KB-128.0 KB]: 547 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]: 27281 frames
220
  Requested Block Size 16.0 MB
221
  Peak Block count 1
222
  Peak Allocated memory 39.6 KB
@@ -228,13 +228,13 @@ Memory Statistics:
228
  Used Block count 1
229
  Peak Allocated bytes 1.0 MB
230
  [ALLOC_CACHEOBJECTS_MAIN]
231
- Peak usage frame count: [0.5 MB-1.0 MB]: 27281 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]: 27280 frames, [2.0 MB-4.0 MB]: 1 frames
238
  Requested Block Size 4.0 MB
239
  Peak Block count 1
240
  Peak Allocated memory 2.2 MB
@@ -246,13 +246,13 @@ Memory Statistics:
246
  Used Block count 1
247
  Peak Allocated bytes 1.0 MB
248
  [ALLOC_TYPETREE_MAIN]
249
- Peak usage frame count: [0-1.0 KB]: 27281 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]: 27281 frames
256
  Requested Block Size 2.0 MB
257
  Peak Block count 1
258
  Peak Allocated memory 1.7 KB
 
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 0.089 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: 0.715132 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]: 13416 frames, [16.0 KB-32.0 KB]: 227 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: [16.0 MB-32.0 MB]: 13644 frames
176
  Requested Block Size 16.0 MB
177
+ Peak Block count 1
178
+ Peak Allocated memory 25.6 MB
179
+ Peak Large allocation bytes 16.0 MB
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [1.0 MB-2.0 MB]: 13644 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
+ Peak Allocated memory 1.7 MB
185
+ Peak Large allocation bytes 0 B
186
  [ALLOC_TEMP_JOB_1_FRAME]
187
  Initial Block Size 2.0 MB
188
  Used Block Count 1
 
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]: 13421 frames, [64.0 KB-128.0 KB]: 223 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]: 13644 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]: 13644 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]: 13643 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]: 13644 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]: 13644 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
@@ -2,153 +2,153 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 0.53799968957901,
6
- "min": 0.53799968957901,
7
- "max": 0.7564886808395386,
8
- "count": 100
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 5119.06689453125,
12
- "min": 5119.06689453125,
13
- "max": 7755.52197265625,
14
- "count": 100
15
  },
16
  "SnowballTarget.Step.mean": {
17
- "value": 1499968.0,
18
- "min": 509968.0,
19
- "max": 1499968.0,
20
- "count": 100
21
  },
22
  "SnowballTarget.Step.sum": {
23
- "value": 1499968.0,
24
- "min": 509968.0,
25
- "max": 1499968.0,
26
- "count": 100
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 14.214460372924805,
30
- "min": 13.348098754882812,
31
- "max": 14.227214813232422,
32
- "count": 100
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2800.248779296875,
36
- "min": 2610.87353515625,
37
- "max": 2912.97412109375,
38
- "count": 100
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
- "count": 100
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
- "value": 8756.0,
48
  "min": 8756.0,
49
  "max": 10945.0,
50
- "count": 100
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
- "value": 0.06820257050105069,
54
- "min": 0.060251745833175295,
55
- "max": 0.07947645083816798,
56
- "count": 100
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.27281028200420276,
60
- "min": 0.24238255767604822,
61
- "max": 0.39738225419083995,
62
- "count": 100
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.14256108318473776,
66
- "min": 0.1319370623604924,
67
- "max": 0.22878244577669632,
68
- "count": 100
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.570244332738951,
72
- "min": 0.567250649134318,
73
- "max": 0.944139890518843,
74
- "count": 100
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
- "value": 9.144996951999985e-07,
78
- "min": 9.144996951999985e-07,
79
- "max": 0.0001989144336952,
80
- "count": 100
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
- "value": 3.657998780799994e-06,
84
- "min": 3.657998780799994e-06,
85
- "max": 0.0009846721717760001,
86
- "count": 100
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
- "value": 0.10030480000000001,
90
- "min": 0.10030480000000001,
91
- "max": 0.16630480000000003,
92
- "count": 100
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
- "value": 0.40121920000000005,
96
- "min": 0.40121920000000005,
97
- "max": 0.8282240000000001,
98
- "count": 100
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
- "value": 2.5209519999999977e-05,
102
- "min": 2.5209519999999977e-05,
103
- "max": 0.0033186095200000002,
104
- "count": 100
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
107
- "value": 0.00010083807999999991,
108
- "min": 0.00010083807999999991,
109
- "max": 0.016428377600000002,
110
- "count": 100
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 27.872340425531913,
114
- "min": 25.954545454545453,
115
- "max": 28.227272727272727,
116
- "count": 100
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1310.0,
120
- "min": 1142.0,
121
- "max": 1540.0,
122
- "count": 100
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 27.872340425531913,
126
- "min": 25.954545454545453,
127
- "max": 28.227272727272727,
128
- "count": 100
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1310.0,
132
- "min": 1142.0,
133
- "max": 1540.0,
134
- "count": 100
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
- "count": 100
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
- "count": 100
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1692962393",
152
  "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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=SnowballTarget2 --no-graphics --resume",
154
  "mlagents_version": "0.31.0.dev0",
@@ -156,59 +156,59 @@
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "1.11.0+cu102",
158
  "numpy_version": "1.21.2",
159
- "end_time_seconds": "1692964894"
160
  },
161
- "total": 2500.6627455750004,
162
  "count": 1,
163
- "self": 0.44154720699998506,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.07522503400014102,
167
  "count": 1,
168
- "self": 0.07522503400014102
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 2500.1459733340002,
172
  "count": 1,
173
- "self": 2.8104127370179413,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 4.462005488999694,
177
  "count": 1,
178
- "self": 4.462005488999694
179
  },
180
  "TrainerController.advance": {
181
- "total": 2492.721634398982,
182
- "count": 90936,
183
- "self": 1.439072695132836,
184
  "children": {
185
  "env_step": {
186
- "total": 2491.2825617038493,
187
- "count": 90936,
188
- "self": 1817.928624887776,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 671.9135965620321,
192
- "count": 90936,
193
- "self": 9.22253509812208,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 662.69106146391,
197
- "count": 90936,
198
- "self": 662.69106146391
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 1.4403402540410752,
204
- "count": 90936,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 2492.006246379005,
209
- "count": 90936,
210
  "is_parallel": true,
211
- "self": 1163.5157451381565,
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": 0.0021117299997968075,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.000618000999565993,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0014937290002308146,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0014937290002308146
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.0384858330003226,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0005794200001218996,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.00048016700020525604,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.00048016700020525604
244
  },
245
  "communicator.exchange": {
246
- "total": 0.035512124999968364,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.035512124999968364
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0019141210000270803,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.0004901489996882447,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0014239720003388356,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0014239720003388356
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 1328.4905012408485,
271
- "count": 90935,
272
  "is_parallel": true,
273
- "self": 55.29365731678399,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 27.60718476707052,
277
- "count": 90935,
278
  "is_parallel": true,
279
- "self": 27.60718476707052
280
  },
281
  "communicator.exchange": {
282
- "total": 1053.3361043439882,
283
- "count": 90935,
284
  "is_parallel": true,
285
- "self": 1053.3361043439882
286
  },
287
  "steps_from_proto": {
288
- "total": 192.25355481300585,
289
- "count": 90935,
290
  "is_parallel": true,
291
- "self": 35.007807823652,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 157.24574698935385,
295
- "count": 909350,
296
  "is_parallel": true,
297
- "self": 157.24574698935385
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 0.00029096500020386884,
313
  "count": 1,
314
- "self": 0.00029096500020386884,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,36 +320,36 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 2471.4963887372874,
324
- "count": 2314657,
325
  "is_parallel": true,
326
- "self": 54.422157136818896,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 1338.7720334094543,
330
- "count": 2314657,
331
  "is_parallel": true,
332
- "self": 1332.0034128774528,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
- "total": 6.768620532001478,
336
- "count": 20,
337
  "is_parallel": true,
338
- "self": 6.768620532001478
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
- "total": 1078.3021981910142,
344
- "count": 454,
345
  "is_parallel": true,
346
- "self": 437.2446732899907,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
- "total": 641.0575249010235,
350
- "count": 23148,
351
  "is_parallel": true,
352
- "self": 641.0575249010235
353
  }
354
  }
355
  }
@@ -360,14 +360,14 @@
360
  }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.1516297440002745,
364
  "count": 1,
365
- "self": 0.0012008220010102377,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.15042892199926428,
369
  "count": 1,
370
- "self": 0.15042892199926428
371
  }
372
  }
373
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.46688005328178406,
6
+ "min": 0.46145811676979065,
7
+ "max": 0.548062801361084,
8
+ "count": 50
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 4791.58984375,
12
+ "min": 4390.77392578125,
13
+ "max": 5577.51953125,
14
+ "count": 50
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 1999944.0,
18
+ "min": 1509984.0,
19
+ "max": 1999944.0,
20
+ "count": 50
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 1999944.0,
24
+ "min": 1509984.0,
25
+ "max": 1999944.0,
26
+ "count": 50
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 14.30431079864502,
30
+ "min": 13.924019813537598,
31
+ "max": 14.351710319519043,
32
+ "count": 50
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2918.079345703125,
36
+ "min": 2711.312744140625,
37
+ "max": 2942.005615234375,
38
+ "count": 50
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
+ "count": 50
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
+ "value": 10945.0,
48
  "min": 8756.0,
49
  "max": 10945.0,
50
+ "count": 50
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.06890000453008813,
54
+ "min": 0.06153105939784105,
55
+ "max": 0.07687349683150316,
56
+ "count": 50
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.34450002265044066,
60
+ "min": 0.25084291392019675,
61
+ "max": 0.364112547010996,
62
+ "count": 50
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.14710586433317147,
66
+ "min": 0.13593446288038702,
67
+ "max": 0.18358633409975572,
68
+ "count": 50
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.7355293216658574,
72
+ "min": 0.5437378515215481,
73
+ "max": 0.835933457548712,
74
+ "count": 50
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
+ "value": 7.296997567999969e-07,
78
+ "min": 7.296997567999969e-07,
79
+ "max": 7.415467528179998e-05,
80
+ "count": 50
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
+ "value": 3.648498783999985e-06,
84
+ "min": 3.648498783999985e-06,
85
+ "max": 0.00036334837888399996,
86
+ "count": 50
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
+ "value": 0.10024320000000002,
90
+ "min": 0.10024320000000002,
91
+ "max": 0.1247182,
92
+ "count": 50
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
+ "value": 0.5012160000000001,
96
+ "min": 0.40295280000000006,
97
+ "max": 0.621116,
98
+ "count": 50
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
+ "value": 2.213567999999995e-05,
102
+ "min": 2.213567999999995e-05,
103
+ "max": 0.00124343818,
104
+ "count": 50
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
107
+ "value": 0.00011067839999999976,
108
+ "min": 0.00011067839999999976,
109
+ "max": 0.006093688400000002,
110
+ "count": 50
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 28.327272727272728,
114
+ "min": 27.020833333333332,
115
+ "max": 28.477272727272727,
116
+ "count": 50
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1558.0,
120
+ "min": 1198.0,
121
+ "max": 1559.0,
122
+ "count": 50
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 28.327272727272728,
126
+ "min": 27.020833333333332,
127
+ "max": 28.477272727272727,
128
+ "count": 50
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1558.0,
132
+ "min": 1198.0,
133
+ "max": 1559.0,
134
+ "count": 50
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
+ "count": 50
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
+ "count": 50
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1692965776",
152
  "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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=SnowballTarget2 --no-graphics --resume",
154
  "mlagents_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": "1692967032"
160
  },
161
+ "total": 1256.3228092959998,
162
  "count": 1,
163
+ "self": 0.47509459699995205,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.0447613159994944,
167
  "count": 1,
168
+ "self": 0.0447613159994944
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 1255.8029533830004,
172
  "count": 1,
173
+ "self": 1.442056101005619,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 4.730609146000461,
177
  "count": 1,
178
+ "self": 4.730609146000461
179
  },
180
  "TrainerController.advance": {
181
+ "total": 1249.4823890559937,
182
+ "count": 45477,
183
+ "self": 0.7374466800038135,
184
  "children": {
185
  "env_step": {
186
+ "total": 1248.74494237599,
187
+ "count": 45477,
188
+ "self": 911.1786683529326,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 336.8326590630595,
192
+ "count": 45477,
193
+ "self": 4.573453362008877,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 332.25920570105063,
197
+ "count": 45477,
198
+ "self": 332.25920570105063
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.7336149599977944,
204
+ "count": 45477,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 1251.7938582959005,
209
+ "count": 45477,
210
  "is_parallel": true,
211
+ "self": 585.271636632955,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.0019754929999180604,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0005514640006367699,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0014240289992812905,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0014240289992812905
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.07299540999974852,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0006748169989805319,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0004447620003702468,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0004447620003702468
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.06937806499990984,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.06937806499990984
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0024977660004879,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0006389070013028686,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0018588589991850313,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0018588589991850313
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 666.5222216629454,
271
+ "count": 45476,
272
  "is_parallel": true,
273
+ "self": 27.84803703185571,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 13.8533773930194,
277
+ "count": 45476,
278
  "is_parallel": true,
279
+ "self": 13.8533773930194
280
  },
281
  "communicator.exchange": {
282
+ "total": 527.5904366399864,
283
+ "count": 45476,
284
  "is_parallel": true,
285
+ "self": 527.5904366399864
286
  },
287
  "steps_from_proto": {
288
+ "total": 97.23037059808394,
289
+ "count": 45476,
290
  "is_parallel": true,
291
+ "self": 17.93557078792037,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 79.29479981016357,
295
+ "count": 454760,
296
  "is_parallel": true,
297
+ "self": 79.29479981016357
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 0.00020477300040511182,
313
  "count": 1,
314
+ "self": 0.00020477300040511182,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 1238.3293930730097,
324
+ "count": 1159049,
325
  "is_parallel": true,
326
+ "self": 27.88234454603662,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 673.0375864319767,
330
+ "count": 1159049,
331
  "is_parallel": true,
332
+ "self": 669.9807408189754,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
+ "total": 3.0568456130013146,
336
+ "count": 10,
337
  "is_parallel": true,
338
+ "self": 3.0568456130013146
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
+ "total": 537.4094620949963,
344
+ "count": 227,
345
  "is_parallel": true,
346
+ "self": 216.54626846698739,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 320.86319362800896,
350
+ "count": 11574,
351
  "is_parallel": true,
352
+ "self": 320.86319362800896
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.14769430700016528,
364
  "count": 1,
365
+ "self": 0.0011035859997718944,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.1465907210003934,
369
  "count": 1,
370
+ "self": 0.1465907210003934
371
  }
372
  }
373
  }
run_logs/training_status.json CHANGED
@@ -2,103 +2,103 @@
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
- "steps": 1099952,
6
- "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1099952.onnx",
7
- "reward": 27.90909090909091,
8
- "creation_time": 1692963944.2917123,
9
  "auxillary_file_paths": [
10
- "results/SnowballTarget2/SnowballTarget/SnowballTarget-1099952.pt"
11
  ]
12
  },
13
  {
14
- "steps": 1149976,
15
- "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1149976.onnx",
16
- "reward": 27.727272727272727,
17
- "creation_time": 1692964062.8930812,
18
  "auxillary_file_paths": [
19
- "results/SnowballTarget2/SnowballTarget/SnowballTarget-1149976.pt"
20
  ]
21
  },
22
  {
23
- "steps": 1199936,
24
- "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1199936.onnx",
25
- "reward": 26.818181818181817,
26
- "creation_time": 1692964179.947914,
27
  "auxillary_file_paths": [
28
- "results/SnowballTarget2/SnowballTarget/SnowballTarget-1199936.pt"
29
  ]
30
  },
31
  {
32
- "steps": 1249936,
33
- "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1249936.onnx",
34
- "reward": 27.545454545454547,
35
- "creation_time": 1692964295.1733549,
36
  "auxillary_file_paths": [
37
- "results/SnowballTarget2/SnowballTarget/SnowballTarget-1249936.pt"
38
  ]
39
  },
40
  {
41
- "steps": 1299960,
42
- "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1299960.onnx",
43
- "reward": 27.363636363636363,
44
- "creation_time": 1692964411.928051,
45
  "auxillary_file_paths": [
46
- "results/SnowballTarget2/SnowballTarget/SnowballTarget-1299960.pt"
47
  ]
48
  },
49
  {
50
- "steps": 1349984,
51
- "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1349984.onnx",
52
- "reward": 26.636363636363637,
53
- "creation_time": 1692964530.7918591,
54
  "auxillary_file_paths": [
55
- "results/SnowballTarget2/SnowballTarget/SnowballTarget-1349984.pt"
56
  ]
57
  },
58
  {
59
- "steps": 1399944,
60
- "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1399944.onnx",
61
- "reward": 27.727272727272727,
62
- "creation_time": 1692964645.8908463,
63
  "auxillary_file_paths": [
64
- "results/SnowballTarget2/SnowballTarget/SnowballTarget-1399944.pt"
65
  ]
66
  },
67
  {
68
- "steps": 1449944,
69
- "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1449944.onnx",
70
- "reward": 27.454545454545453,
71
- "creation_time": 1692964768.3015232,
72
  "auxillary_file_paths": [
73
- "results/SnowballTarget2/SnowballTarget/SnowballTarget-1449944.pt"
74
  ]
75
  },
76
  {
77
- "steps": 1499968,
78
- "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1499968.onnx",
79
- "reward": 27.363636363636363,
80
- "creation_time": 1692964893.75044,
81
  "auxillary_file_paths": [
82
- "results/SnowballTarget2/SnowballTarget/SnowballTarget-1499968.pt"
83
  ]
84
  },
85
  {
86
- "steps": 1500224,
87
- "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1500224.onnx",
88
- "reward": 27.363636363636363,
89
- "creation_time": 1692964893.9408672,
90
  "auxillary_file_paths": [
91
- "results/SnowballTarget2/SnowballTarget/SnowballTarget-1500224.pt"
92
  ]
93
  }
94
  ],
95
  "final_checkpoint": {
96
- "steps": 1500224,
97
  "file_path": "results/SnowballTarget2/SnowballTarget.onnx",
98
- "reward": 27.363636363636363,
99
- "creation_time": 1692964893.9408672,
100
  "auxillary_file_paths": [
101
- "results/SnowballTarget2/SnowballTarget/SnowballTarget-1500224.pt"
102
  ]
103
  }
104
  },
 
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
+ "steps": 1599992,
6
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1599992.onnx",
7
+ "reward": 27.454545454545453,
8
+ "creation_time": 1692966032.6757853,
9
  "auxillary_file_paths": [
10
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-1599992.pt"
11
  ]
12
  },
13
  {
14
+ "steps": 1649952,
15
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1649952.onnx",
16
+ "reward": 27.545454545454547,
17
+ "creation_time": 1692966160.0008776,
18
  "auxillary_file_paths": [
19
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-1649952.pt"
20
  ]
21
  },
22
  {
23
+ "steps": 1699952,
24
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1699952.onnx",
25
+ "reward": 27.727272727272727,
26
+ "creation_time": 1692966281.8239093,
27
  "auxillary_file_paths": [
28
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-1699952.pt"
29
  ]
30
  },
31
  {
32
+ "steps": 1749976,
33
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1749976.onnx",
34
+ "reward": 27.90909090909091,
35
+ "creation_time": 1692966405.519714,
36
  "auxillary_file_paths": [
37
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-1749976.pt"
38
  ]
39
  },
40
  {
41
+ "steps": 1799936,
42
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1799936.onnx",
43
+ "reward": 28.454545454545453,
44
+ "creation_time": 1692966530.9553137,
45
  "auxillary_file_paths": [
46
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-1799936.pt"
47
  ]
48
  },
49
  {
50
+ "steps": 1849992,
51
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1849992.onnx",
52
+ "reward": 27.428571428571427,
53
+ "creation_time": 1692966658.7945466,
54
  "auxillary_file_paths": [
55
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-1849992.pt"
56
  ]
57
  },
58
  {
59
+ "steps": 1899960,
60
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1899960.onnx",
61
+ "reward": 28.09090909090909,
62
+ "creation_time": 1692966782.081134,
63
  "auxillary_file_paths": [
64
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-1899960.pt"
65
  ]
66
  },
67
  {
68
+ "steps": 1949984,
69
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1949984.onnx",
70
+ "reward": 28.09090909090909,
71
+ "creation_time": 1692966905.7248962,
72
  "auxillary_file_paths": [
73
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-1949984.pt"
74
  ]
75
  },
76
  {
77
+ "steps": 1999944,
78
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1999944.onnx",
79
+ "reward": 28.272727272727273,
80
+ "creation_time": 1692967031.9898722,
81
  "auxillary_file_paths": [
82
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-1999944.pt"
83
  ]
84
  },
85
  {
86
+ "steps": 2000200,
87
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-2000200.onnx",
88
+ "reward": 28.272727272727273,
89
+ "creation_time": 1692967032.1787574,
90
  "auxillary_file_paths": [
91
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-2000200.pt"
92
  ]
93
  }
94
  ],
95
  "final_checkpoint": {
96
+ "steps": 2000200,
97
  "file_path": "results/SnowballTarget2/SnowballTarget.onnx",
98
+ "reward": 28.272727272727273,
99
+ "creation_time": 1692967032.1787574,
100
  "auxillary_file_paths": [
101
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-2000200.pt"
102
  ]
103
  }
104
  },