EduardoCGarridoMerchan commited on
Commit
6fb190e
·
1 Parent(s): 624cfa2

Holaaaaaaaaaaaaa

Browse files
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b0d3ecceb0954a19a5a1a56fb447bd8baff6c961ee37d613ef6adb4a44ce2ab
3
  size 645119
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26bb0376a0ba4bd3e3e266b2afc9dbedfa292d7782a06f398b91e40c19684762
3
  size 645119
SnowballTarget/{SnowballTarget-149984.onnx → SnowballTarget-10208.onnx} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ba1f29cc8b2d0a63e195154b6573f82df565ab7e5c775175289460b2e7c6f5e4
3
  size 645119
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26bb0376a0ba4bd3e3e266b2afc9dbedfa292d7782a06f398b91e40c19684762
3
  size 645119
SnowballTarget/{SnowballTarget-149984.pt → SnowballTarget-10208.pt} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cad2ca4ede647f3bb85a80cb27fefbecc4e9792527e7f648430e0c6204b9768a
3
- size 3845312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c99ec8d03a2dd2fc44214d00cb47d6343f575538f1c2b0ce81e39da0e838592
3
+ size 3845586
SnowballTarget/SnowballTarget-249944.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b570aa180fe78b11b03992965a6cd9f9bf939bcdbb31f205299bc5e6ac293c53
3
- size 3845312
 
 
 
 
SnowballTarget/SnowballTarget-299968.onnx DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:18aa28ecb4effc3786289c02f7cf6770d5b1351b6b5bfa44f909070e3aaea91e
3
- size 645119
 
 
 
 
SnowballTarget/SnowballTarget-299968.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:fd2424a854f42bf633587312f83164a18bfd4b7ce30ae8856c7117c8bd50f762
3
- size 3845312
 
 
 
 
SnowballTarget/SnowballTarget-349992.onnx DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9c02b41efcf558cf9cc3e42fde89c681dd149891db4b7468bf10737b3695e87
3
- size 645119
 
 
 
 
SnowballTarget/SnowballTarget-349992.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6730b28912cf1cec7f920a4a55298b63d1600d2bd7d5ecb357e0d88148dfc7b5
3
- size 3845312
 
 
 
 
SnowballTarget/SnowballTarget-399992.onnx DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:281aa5551859d8d2564c454c7b7b8f7181f4d16ac2648e5d2faa07af992bdd29
3
- size 645119
 
 
 
 
SnowballTarget/SnowballTarget-399992.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c4d327c5228b81f1231af745f8a1e92d81c707c4a787ae497c4d1d70e1dda821
3
- size 3845312
 
 
 
 
SnowballTarget/SnowballTarget-449952.onnx DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:77a62401f72f57461dddb3208dba21a79d36d9cda3fdec85222d1a3fd3a4ac72
3
- size 645119
 
 
 
 
SnowballTarget/SnowballTarget-449952.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4bd3723c8294374de59aaf261c9abd093ae25a5732566bb8e242e499db2cc415
3
- size 3845312
 
 
 
 
SnowballTarget/{SnowballTarget-249944.onnx → SnowballTarget-4976.onnx} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4fed795d46295957b5ba252ba727e2ad13530f6e57abffc2c022cbfc719d3027
3
  size 645119
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e9ccf1de3656c0d36262015ae27804b356a467e4e5e7e2ce86071e898c35a31
3
  size 645119
SnowballTarget/{SnowballTarget-199984.pt → SnowballTarget-4976.pt} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ffdfad13bbbf4dfda47ca2f299fe186c759d13417ee3accaf9704a005bfb901
3
- size 3845312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94c56d0087850b5a06925b96f17df482563338bd16e8757f9f01ed8002cea92b
3
+ size 3845586
SnowballTarget/SnowballTarget-499976.onnx DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b0d3ecceb0954a19a5a1a56fb447bd8baff6c961ee37d613ef6adb4a44ce2ab
3
- size 645119
 
 
 
 
SnowballTarget/SnowballTarget-499976.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3369121792b21b542014315718f29229592927e1449791f89bf070e6ac55c714
3
- size 3845312
 
 
 
 
SnowballTarget/SnowballTarget-500104.onnx DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b0d3ecceb0954a19a5a1a56fb447bd8baff6c961ee37d613ef6adb4a44ce2ab
3
- size 645119
 
 
 
 
SnowballTarget/SnowballTarget-500104.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f8785139b2fbabe7dcba3efee565b1a6f01deba207d109946247b54da3f8e14
3
- size 3845312
 
 
 
 
SnowballTarget/{SnowballTarget-199984.onnx → SnowballTarget-9952.onnx} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a3aee0e367a3630ca962c3d576a0a39d4775d3131ee0f91e5476995fd99638e
3
  size 645119
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26bb0376a0ba4bd3e3e266b2afc9dbedfa292d7782a06f398b91e40c19684762
3
  size 645119
SnowballTarget/SnowballTarget-9952.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edaa4b5f2365ff382f31aeacb9c9c2fa4fb00e990a9d2f5b53e286b8d10777cf
3
+ size 3845586
SnowballTarget/SnowballTarget-99960.onnx DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6b725d65fbb5b7e0f2a35acb5c987222b96db6b9c20af552df27d921406b61a
3
- size 645119
 
 
 
 
SnowballTarget/SnowballTarget-99960.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:924684e45aaa33e9ee23663b1088f26be67de4a0916e20ed2b16bbe27523b751
3
- size 3845312
 
 
 
 
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f8785139b2fbabe7dcba3efee565b1a6f01deba207d109946247b54da3f8e14
3
- size 3845312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c99ec8d03a2dd2fc44214d00cb47d6343f575538f1c2b0ce81e39da0e838592
3
+ size 3845586
SnowballTarget/{events.out.tfevents.1674039374.efb5849a5f26.6069.0 → events.out.tfevents.1677844412.cfdc967d52cc.1859.0} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:88851eee3cdbb7e79f44cda2d953ed09dd70827a68c49938e76ba86c02102ff3
3
- size 14703
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a67ccaf32338fcd83324ccdfc52caef950bbc2030b4aa2910e859199a5fec529
3
+ size 6731
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 64, "buffer_size": 2048, "learning_rate": 0.0001, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "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, "checkpoint_interval": 50000, "max_steps": 500000, "time_horizon": 64, "summary_freq": 50000, "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, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "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, "checkpoint_interval": 5000, "max_steps": 10000, "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}
configuration.yaml CHANGED
@@ -3,9 +3,9 @@ behaviors:
3
  SnowballTarget:
4
  trainer_type: ppo
5
  hyperparameters:
6
- batch_size: 64
7
  buffer_size: 2048
8
- learning_rate: 0.0001
9
  beta: 0.005
10
  epsilon: 0.2
11
  lambd: 0.95
@@ -35,10 +35,10 @@ behaviors:
35
  deterministic: false
36
  init_path: null
37
  keep_checkpoints: 10
38
- checkpoint_interval: 50000
39
- max_steps: 500000
40
  time_horizon: 64
41
- summary_freq: 50000
42
  threaded: true
43
  self_play: null
44
  behavioral_cloning: null
 
3
  SnowballTarget:
4
  trainer_type: ppo
5
  hyperparameters:
6
+ batch_size: 128
7
  buffer_size: 2048
8
+ learning_rate: 0.0003
9
  beta: 0.005
10
  epsilon: 0.2
11
  lambd: 0.95
 
35
  deterministic: false
36
  init_path: null
37
  keep_checkpoints: 10
38
+ checkpoint_interval: 5000
39
+ max_steps: 10000
40
  time_horizon: 64
41
+ summary_freq: 10000
42
  threaded: true
43
  self_play: null
44
  behavioral_cloning: null
run_logs/Player-0.log CHANGED
@@ -34,7 +34,7 @@ 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 0.077 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 +45,7 @@ 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: 0.745031 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 +53,7 @@ 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]: 13416 frames, [16.0 KB-32.0 KB]: 227 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 +169,22 @@ Memory Statistics:
169
  Peak Allocated Bytes 0 B
170
  Overflow Count 0
171
  [ALLOC_DEFAULT] Dual Thread Allocator
172
- Peak main deferred allocation count 44
173
  [ALLOC_BUCKET]
174
  Large Block size 4.0 MB
175
  Used Block count 1
176
- Peak Allocated bytes 0.9 MB
177
  [ALLOC_DEFAULT_MAIN]
178
- Peak usage frame count: [4.0 MB-8.0 MB]: 11413 frames, [8.0 MB-16.0 MB]: 2231 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
- Peak Allocated memory 9.6 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
- Peak usage frame count: [16.0 MB-32.0 MB]: 13644 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
- Peak Allocated memory 17.8 MB
188
  Peak Large allocation bytes 16.0 MB
189
  [ALLOC_TEMP_JOB_1_FRAME]
190
  Initial Block Size 2.0 MB
@@ -211,15 +211,15 @@ Memory Statistics:
211
  [ALLOC_BUCKET]
212
  Large Block size 4.0 MB
213
  Used Block count 1
214
- Peak Allocated bytes 0.9 MB
215
  [ALLOC_GFX_MAIN]
216
- Peak usage frame count: [32.0 KB-64.0 KB]: 12331 frames, [64.0 KB-128.0 KB]: 1313 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
- Peak Allocated memory 66.8 KB
220
  Peak Large allocation bytes 0 B
221
  [ALLOC_GFX_THREAD]
222
- Peak usage frame count: [32.0 KB-64.0 KB]: 13644 frames
223
  Requested Block Size 16.0 MB
224
  Peak Block count 1
225
  Peak Allocated memory 39.6 KB
@@ -229,15 +229,15 @@ Memory Statistics:
229
  [ALLOC_BUCKET]
230
  Large Block size 4.0 MB
231
  Used Block count 1
232
- Peak Allocated bytes 0.9 MB
233
  [ALLOC_CACHEOBJECTS_MAIN]
234
- Peak usage frame count: [0.5 MB-1.0 MB]: 13644 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]: 13643 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
@@ -247,15 +247,15 @@ Memory Statistics:
247
  [ALLOC_BUCKET]
248
  Large Block size 4.0 MB
249
  Used Block count 1
250
- Peak Allocated bytes 0.9 MB
251
  [ALLOC_TYPETREE_MAIN]
252
- Peak usage frame count: [0-1.0 KB]: 13644 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]: 13644 frames
259
  Requested Block Size 2.0 MB
260
  Peak Block count 1
261
  Peak Allocated memory 1.7 KB
 
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 0.080 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
  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: 0.688987 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
  [ALLOC_TEMP_TLS] TLS Allocator
54
  StackAllocators :
55
  [ALLOC_TEMP_MAIN]
56
+ Peak usage frame count: [8.0 KB-16.0 KB]: 277 frames, [16.0 KB-32.0 KB]: 4 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
  Peak Allocated Bytes 0 B
170
  Overflow Count 0
171
  [ALLOC_DEFAULT] Dual Thread Allocator
172
+ Peak main deferred allocation count 37
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]: 282 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
+ Peak Allocated memory 5.8 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
+ Peak usage frame count: [16.0 MB-32.0 MB]: 282 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
+ Peak Allocated memory 17.3 MB
188
  Peak Large allocation bytes 16.0 MB
189
  [ALLOC_TEMP_JOB_1_FRAME]
190
  Initial Block Size 2.0 MB
 
211
  [ALLOC_BUCKET]
212
  Large Block size 4.0 MB
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]: 248 frames, [64.0 KB-128.0 KB]: 34 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]: 282 frames
223
  Requested Block Size 16.0 MB
224
  Peak Block count 1
225
  Peak Allocated memory 39.6 KB
 
229
  [ALLOC_BUCKET]
230
  Large Block size 4.0 MB
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]: 282 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]: 281 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
 
247
  [ALLOC_BUCKET]
248
  Large Block size 4.0 MB
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]: 282 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]: 282 frames
259
  Requested Block Size 2.0 MB
260
  Peak Block count 1
261
  Peak Allocated memory 1.7 KB
run_logs/timers.json CHANGED
@@ -2,220 +2,220 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 0.7169133424758911,
6
- "min": 0.7169133424758911,
7
- "max": 2.5835161209106445,
8
- "count": 10
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 35810.5390625,
12
- "min": 35810.5390625,
13
- "max": 130526.984375,
14
- "count": 10
15
  },
16
  "SnowballTarget.Step.mean": {
17
- "value": 499976.0,
18
- "min": 49936.0,
19
- "max": 499976.0,
20
- "count": 10
21
  },
22
  "SnowballTarget.Step.sum": {
23
- "value": 499976.0,
24
- "min": 49936.0,
25
- "max": 499976.0,
26
- "count": 10
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 13.537559509277344,
30
- "min": 2.3262007236480713,
31
- "max": 13.537559509277344,
32
- "count": 10
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 13578.171875,
36
- "min": 2307.591064453125,
37
- "max": 13578.171875,
38
- "count": 10
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
- "count": 10
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
- "value": 50347.0,
48
- "min": 48158.0,
49
- "max": 50347.0,
50
- "count": 10
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
- "value": 0.09952346138659715,
54
- "min": 0.09466299025930625,
55
- "max": 0.10087861357168838,
56
- "count": 10
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 2.2890396118917344,
60
- "min": 2.1755999400326496,
61
- "max": 2.320208112148833,
62
- "count": 10
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.18897049657790865,
66
- "min": 0.18560784062067362,
67
- "max": 0.255028156342917,
68
- "count": 10
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 4.346321421291899,
72
- "min": 4.1164782167795835,
73
- "max": 5.865647595887091,
74
- "count": 10
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
- "value": 4.977695022400002e-06,
78
- "min": 4.977695022400002e-06,
79
- "max": 9.495760504239999e-05,
80
- "count": 10
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
- "value": 0.00011448698551520003,
84
- "min": 0.00011448698551520003,
85
- "max": 0.0020890673109328,
86
- "count": 10
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
- "value": 0.10497759999999998,
90
- "min": 0.10497759999999998,
91
- "max": 0.19495760000000004,
92
- "count": 10
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
- "value": 2.4144847999999994,
96
- "min": 2.4144847999999994,
97
- "max": 4.289067200000001,
98
- "count": 10
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
- "value": 0.00025838224000000005,
102
- "min": 0.00025838224000000005,
103
- "max": 0.0047483842399999995,
104
- "count": 10
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
107
- "value": 0.005942791520000001,
108
- "min": 0.005942791520000001,
109
- "max": 0.10446445328,
110
- "count": 10
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 26.49407114624506,
114
- "min": 7.433884297520661,
115
- "max": 26.49407114624506,
116
- "count": 10
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 6703.0,
120
- "min": 1799.0,
121
- "max": 6703.0,
122
- "count": 10
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 26.49407114624506,
126
- "min": 7.433884297520661,
127
- "max": 26.49407114624506,
128
- "count": 10
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 6703.0,
132
- "min": 1799.0,
133
- "max": 6703.0,
134
- "count": 10
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
- "count": 10
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
- "count": 10
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1674039368",
152
  "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.dev0",
155
  "mlagents_envs_version": "0.29.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "1.8.1+cu102",
158
- "numpy_version": "1.21.6",
159
- "end_time_seconds": "1674040491"
160
  },
161
- "total": 1122.6467492589998,
162
  "count": 1,
163
- "self": 0.3830281609996291,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.11190371199995752,
167
  "count": 1,
168
- "self": 0.11190371199995752
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 1122.1518173860002,
172
  "count": 1,
173
- "self": 1.3495537490184688,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 9.088162218999969,
177
  "count": 1,
178
- "self": 9.088162218999969
179
  },
180
  "TrainerController.advance": {
181
- "total": 1111.5961136439812,
182
- "count": 45477,
183
- "self": 0.7089983889948144,
184
  "children": {
185
  "env_step": {
186
- "total": 1110.8871152549864,
187
- "count": 45477,
188
- "self": 782.5423483469895,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 327.68075491198056,
192
- "count": 45477,
193
- "self": 3.3905774380211824,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 324.2901774739594,
197
- "count": 45477,
198
- "self": 72.44579044294528,
199
  "children": {
200
  "TorchPolicy.sample_actions": {
201
- "total": 251.8443870310141,
202
- "count": 45477,
203
- "self": 251.8443870310141
204
  }
205
  }
206
  }
207
  }
208
  },
209
  "workers": {
210
- "total": 0.6640119960163702,
211
- "count": 45477,
212
  "self": 0.0,
213
  "children": {
214
  "worker_root": {
215
- "total": 1119.2070092759475,
216
- "count": 45477,
217
  "is_parallel": true,
218
- "self": 575.9232987029563,
219
  "children": {
220
  "run_training.setup": {
221
  "total": 0.0,
@@ -224,48 +224,48 @@
224
  "self": 0.0,
225
  "children": {
226
  "steps_from_proto": {
227
- "total": 0.005660044000023845,
228
  "count": 1,
229
  "is_parallel": true,
230
- "self": 0.003462286000058157,
231
  "children": {
232
  "_process_rank_one_or_two_observation": {
233
- "total": 0.002197757999965688,
234
  "count": 10,
235
  "is_parallel": true,
236
- "self": 0.002197757999965688
237
  }
238
  }
239
  },
240
  "UnityEnvironment.step": {
241
- "total": 0.042526369999905,
242
  "count": 1,
243
  "is_parallel": true,
244
- "self": 0.0006222729998626164,
245
  "children": {
246
  "UnityEnvironment._generate_step_input": {
247
- "total": 0.00027388500006964023,
248
  "count": 1,
249
  "is_parallel": true,
250
- "self": 0.00027388500006964023
251
  },
252
  "communicator.exchange": {
253
- "total": 0.03969701200003328,
254
  "count": 1,
255
  "is_parallel": true,
256
- "self": 0.03969701200003328
257
  },
258
  "steps_from_proto": {
259
- "total": 0.0019331999999394611,
260
  "count": 1,
261
  "is_parallel": true,
262
- "self": 0.0004443279997303762,
263
  "children": {
264
  "_process_rank_one_or_two_observation": {
265
- "total": 0.001488872000209085,
266
  "count": 10,
267
  "is_parallel": true,
268
- "self": 0.001488872000209085
269
  }
270
  }
271
  }
@@ -274,34 +274,34 @@
274
  }
275
  },
276
  "UnityEnvironment.step": {
277
- "total": 543.2837105729911,
278
- "count": 45476,
279
  "is_parallel": true,
280
- "self": 20.542142130923366,
281
  "children": {
282
  "UnityEnvironment._generate_step_input": {
283
- "total": 11.932183702015209,
284
- "count": 45476,
285
  "is_parallel": true,
286
- "self": 11.932183702015209
287
  },
288
  "communicator.exchange": {
289
- "total": 438.3587254880065,
290
- "count": 45476,
291
  "is_parallel": true,
292
- "self": 438.3587254880065
293
  },
294
  "steps_from_proto": {
295
- "total": 72.45065925204608,
296
- "count": 45476,
297
  "is_parallel": true,
298
- "self": 15.787640815154873,
299
  "children": {
300
  "_process_rank_one_or_two_observation": {
301
- "total": 56.66301843689121,
302
- "count": 454760,
303
  "is_parallel": true,
304
- "self": 56.66301843689121
305
  }
306
  }
307
  }
@@ -316,9 +316,9 @@
316
  }
317
  },
318
  "trainer_threads": {
319
- "total": 3.444400044827489e-05,
320
  "count": 1,
321
- "self": 3.444400044827489e-05,
322
  "children": {
323
  "thread_root": {
324
  "total": 0.0,
@@ -327,36 +327,36 @@
327
  "self": 0.0,
328
  "children": {
329
  "trainer_advance": {
330
- "total": 1104.0753907361634,
331
- "count": 874880,
332
  "is_parallel": true,
333
- "self": 22.69800708795856,
334
  "children": {
335
  "process_trajectory": {
336
- "total": 582.5718808692036,
337
- "count": 874880,
338
  "is_parallel": true,
339
- "self": 580.5311300472033,
340
  "children": {
341
  "RLTrainer._checkpoint": {
342
- "total": 2.040750822000291,
343
- "count": 10,
344
  "is_parallel": true,
345
- "self": 2.040750822000291
346
  }
347
  }
348
  },
349
  "_update_policy": {
350
- "total": 498.80550277900124,
351
- "count": 227,
352
  "is_parallel": true,
353
- "self": 102.70710151600565,
354
  "children": {
355
  "TorchPPOOptimizer.update": {
356
- "total": 396.0984012629956,
357
- "count": 23151,
358
  "is_parallel": true,
359
- "self": 396.0984012629956
360
  }
361
  }
362
  }
@@ -367,14 +367,14 @@
367
  }
368
  },
369
  "TrainerController._save_models": {
370
- "total": 0.11795333000009123,
371
  "count": 1,
372
- "self": 0.0010511870000300405,
373
  "children": {
374
  "RLTrainer._checkpoint": {
375
- "total": 0.11690214300006119,
376
  "count": 1,
377
- "self": 0.11690214300006119
378
  }
379
  }
380
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 2.876863956451416,
6
+ "min": 2.876863956451416,
7
+ "max": 2.876863956451416,
8
+ "count": 1
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 29461.96484375,
12
+ "min": 29461.96484375,
13
+ "max": 29461.96484375,
14
+ "count": 1
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 9952.0,
18
+ "min": 9952.0,
19
+ "max": 9952.0,
20
+ "count": 1
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 9952.0,
24
+ "min": 9952.0,
25
+ "max": 9952.0,
26
+ "count": 1
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 0.33867913484573364,
30
+ "min": 0.33867913484573364,
31
+ "max": 0.33867913484573364,
32
+ "count": 1
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 65.70375061035156,
36
+ "min": 65.70375061035156,
37
+ "max": 65.70375061035156,
38
+ "count": 1
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
+ "count": 1
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
+ "value": 8756.0,
48
+ "min": 8756.0,
49
+ "max": 8756.0,
50
+ "count": 1
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.06874559047066535,
54
+ "min": 0.06874559047066535,
55
+ "max": 0.06874559047066535,
56
+ "count": 1
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.2749823618826614,
60
+ "min": 0.2749823618826614,
61
+ "max": 0.2749823618826614,
62
+ "count": 1
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.11873810157389836,
66
+ "min": 0.11873810157389836,
67
+ "max": 0.11873810157389836,
68
+ "count": 1
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.47495240629559343,
72
+ "min": 0.47495240629559343,
73
+ "max": 0.47495240629559343,
74
+ "count": 1
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
+ "value": 0.00013764005412,
78
+ "min": 0.00013764005412,
79
+ "max": 0.00013764005412,
80
+ "count": 1
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
+ "value": 0.00055056021648,
84
+ "min": 0.00055056021648,
85
+ "max": 0.00055056021648,
86
+ "count": 1
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
+ "value": 0.14588,
90
+ "min": 0.14588,
91
+ "max": 0.14588,
92
+ "count": 1
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
+ "value": 0.58352,
96
+ "min": 0.58352,
97
+ "max": 0.58352,
98
+ "count": 1
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
+ "value": 0.002299412,
102
+ "min": 0.002299412,
103
+ "max": 0.002299412,
104
+ "count": 1
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
107
+ "value": 0.009197648,
108
+ "min": 0.009197648,
109
+ "max": 0.009197648,
110
+ "count": 1
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 3.159090909090909,
114
+ "min": 3.159090909090909,
115
+ "max": 3.159090909090909,
116
+ "count": 1
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 139.0,
120
+ "min": 139.0,
121
+ "max": 139.0,
122
+ "count": 1
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 3.159090909090909,
126
+ "min": 3.159090909090909,
127
+ "max": 3.159090909090909,
128
+ "count": 1
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 139.0,
132
+ "min": 139.0,
133
+ "max": 139.0,
134
+ "count": 1
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
+ "count": 1
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
+ "count": 1
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1677844407",
152
  "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.dev0",
155
  "mlagents_envs_version": "0.29.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "1.8.1+cu102",
158
+ "numpy_version": "1.22.4",
159
+ "end_time_seconds": "1677844442"
160
  },
161
+ "total": 35.03159936999998,
162
  "count": 1,
163
+ "self": 0.4360851120000575,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.10681694699997024,
167
  "count": 1,
168
+ "self": 0.10681694699997024
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 34.48869731099995,
172
  "count": 1,
173
+ "self": 0.04713503999943214,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 8.882059615000003,
177
  "count": 1,
178
+ "self": 8.882059615000003
179
  },
180
  "TrainerController.advance": {
181
+ "total": 25.425225923000482,
182
+ "count": 937,
183
+ "self": 0.016131978998714658,
184
  "children": {
185
  "env_step": {
186
+ "total": 25.409093944001768,
187
+ "count": 937,
188
+ "self": 17.730428522001432,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 7.6619752459995425,
192
+ "count": 937,
193
+ "self": 0.08449144799993746,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 7.577483797999605,
197
+ "count": 937,
198
+ "self": 1.9353788369987228,
199
  "children": {
200
  "TorchPolicy.sample_actions": {
201
+ "total": 5.642104961000882,
202
+ "count": 937,
203
+ "self": 5.642104961000882
204
  }
205
  }
206
  }
207
  }
208
  },
209
  "workers": {
210
+ "total": 0.016690176000793144,
211
+ "count": 937,
212
  "self": 0.0,
213
  "children": {
214
  "worker_root": {
215
+ "total": 34.36413838800047,
216
+ "count": 937,
217
  "is_parallel": true,
218
+ "self": 20.757842949000235,
219
  "children": {
220
  "run_training.setup": {
221
  "total": 0.0,
 
224
  "self": 0.0,
225
  "children": {
226
  "steps_from_proto": {
227
+ "total": 0.006261745000017527,
228
  "count": 1,
229
  "is_parallel": true,
230
+ "self": 0.0042581569999242674,
231
  "children": {
232
  "_process_rank_one_or_two_observation": {
233
+ "total": 0.0020035880000932593,
234
  "count": 10,
235
  "is_parallel": true,
236
+ "self": 0.0020035880000932593
237
  }
238
  }
239
  },
240
  "UnityEnvironment.step": {
241
+ "total": 0.03745905400000993,
242
  "count": 1,
243
  "is_parallel": true,
244
+ "self": 0.0004591179999806627,
245
  "children": {
246
  "UnityEnvironment._generate_step_input": {
247
+ "total": 0.00031786200003125487,
248
  "count": 1,
249
  "is_parallel": true,
250
+ "self": 0.00031786200003125487
251
  },
252
  "communicator.exchange": {
253
+ "total": 0.034681594999995013,
254
  "count": 1,
255
  "is_parallel": true,
256
+ "self": 0.034681594999995013
257
  },
258
  "steps_from_proto": {
259
+ "total": 0.002000479000002997,
260
  "count": 1,
261
  "is_parallel": true,
262
+ "self": 0.00042925400009607984,
263
  "children": {
264
  "_process_rank_one_or_two_observation": {
265
+ "total": 0.0015712249999069172,
266
  "count": 10,
267
  "is_parallel": true,
268
+ "self": 0.0015712249999069172
269
  }
270
  }
271
  }
 
274
  }
275
  },
276
  "UnityEnvironment.step": {
277
+ "total": 13.606295439000235,
278
+ "count": 936,
279
  "is_parallel": true,
280
+ "self": 0.5185446180007602,
281
  "children": {
282
  "UnityEnvironment._generate_step_input": {
283
+ "total": 0.30188923899947895,
284
+ "count": 936,
285
  "is_parallel": true,
286
+ "self": 0.30188923899947895
287
  },
288
  "communicator.exchange": {
289
+ "total": 11.035731466999835,
290
+ "count": 936,
291
  "is_parallel": true,
292
+ "self": 11.035731466999835
293
  },
294
  "steps_from_proto": {
295
+ "total": 1.750130115000161,
296
+ "count": 936,
297
  "is_parallel": true,
298
+ "self": 0.39313945999555244,
299
  "children": {
300
  "_process_rank_one_or_two_observation": {
301
+ "total": 1.3569906550046085,
302
+ "count": 9360,
303
  "is_parallel": true,
304
+ "self": 1.3569906550046085
305
  }
306
  }
307
  }
 
316
  }
317
  },
318
  "trainer_threads": {
319
+ "total": 0.0002281310000284975,
320
  "count": 1,
321
+ "self": 0.0002281310000284975,
322
  "children": {
323
  "thread_root": {
324
  "total": 0.0,
 
327
  "self": 0.0,
328
  "children": {
329
  "trainer_advance": {
330
+ "total": 25.2196370670012,
331
+ "count": 24931,
332
  "is_parallel": true,
333
+ "self": 0.6154899739971711,
334
  "children": {
335
  "process_trajectory": {
336
+ "total": 15.802811131004034,
337
+ "count": 24931,
338
  "is_parallel": true,
339
+ "self": 15.406221554004048,
340
  "children": {
341
  "RLTrainer._checkpoint": {
342
+ "total": 0.3965895769999861,
343
+ "count": 2,
344
  "is_parallel": true,
345
+ "self": 0.3965895769999861
346
  }
347
  }
348
  },
349
  "_update_policy": {
350
+ "total": 8.801335961999996,
351
+ "count": 4,
352
  "is_parallel": true,
353
+ "self": 3.3292205230000604,
354
  "children": {
355
  "TorchPPOOptimizer.update": {
356
+ "total": 5.472115438999936,
357
+ "count": 201,
358
  "is_parallel": true,
359
+ "self": 5.472115438999936
360
  }
361
  }
362
  }
 
367
  }
368
  },
369
  "TrainerController._save_models": {
370
+ "total": 0.13404860200000712,
371
  "count": 1,
372
+ "self": 0.0009381350000126076,
373
  "children": {
374
  "RLTrainer._checkpoint": {
375
+ "total": 0.13311046699999451,
376
  "count": 1,
377
+ "self": 0.13311046699999451
378
  }
379
  }
380
  }
run_logs/training_status.json CHANGED
@@ -2,103 +2,40 @@
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
- "steps": 99960,
6
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
7
- "reward": 18.272727272727273,
8
- "creation_time": 1674039596.460914,
9
  "auxillary_file_paths": [
10
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
11
  ]
12
  },
13
  {
14
- "steps": 149984,
15
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
16
- "reward": 22.272727272727273,
17
- "creation_time": 1674039708.0522,
18
  "auxillary_file_paths": [
19
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
20
  ]
21
  },
22
  {
23
- "steps": 199984,
24
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
25
- "reward": 25.272727272727273,
26
- "creation_time": 1674039819.3134322,
27
  "auxillary_file_paths": [
28
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
29
- ]
30
- },
31
- {
32
- "steps": 249944,
33
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-249944.onnx",
34
- "reward": 26.0,
35
- "creation_time": 1674039932.375243,
36
- "auxillary_file_paths": [
37
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-249944.pt"
38
- ]
39
- },
40
- {
41
- "steps": 299968,
42
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.onnx",
43
- "reward": 26.0,
44
- "creation_time": 1674040047.2077258,
45
- "auxillary_file_paths": [
46
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.pt"
47
- ]
48
- },
49
- {
50
- "steps": 349992,
51
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-349992.onnx",
52
- "reward": 26.09090909090909,
53
- "creation_time": 1674040158.590551,
54
- "auxillary_file_paths": [
55
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-349992.pt"
56
- ]
57
- },
58
- {
59
- "steps": 399992,
60
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-399992.onnx",
61
- "reward": 25.0,
62
- "creation_time": 1674040270.7453825,
63
- "auxillary_file_paths": [
64
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-399992.pt"
65
- ]
66
- },
67
- {
68
- "steps": 449952,
69
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-449952.onnx",
70
- "reward": 26.90909090909091,
71
- "creation_time": 1674040381.7889433,
72
- "auxillary_file_paths": [
73
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-449952.pt"
74
- ]
75
- },
76
- {
77
- "steps": 499976,
78
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-499976.onnx",
79
- "reward": 26.363636363636363,
80
- "creation_time": 1674040490.9901326,
81
- "auxillary_file_paths": [
82
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-499976.pt"
83
- ]
84
- },
85
- {
86
- "steps": 500104,
87
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-500104.onnx",
88
- "reward": 26.363636363636363,
89
- "creation_time": 1674040491.1353183,
90
- "auxillary_file_paths": [
91
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-500104.pt"
92
  ]
93
  }
94
  ],
95
  "final_checkpoint": {
96
- "steps": 500104,
97
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
98
- "reward": 26.363636363636363,
99
- "creation_time": 1674040491.1353183,
100
  "auxillary_file_paths": [
101
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-500104.pt"
102
  ]
103
  }
104
  },
 
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
+ "steps": 4976,
6
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-4976.onnx",
7
+ "reward": 3.272727272727273,
8
+ "creation_time": 1677844429.0165222,
9
  "auxillary_file_paths": [
10
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-4976.pt"
11
  ]
12
  },
13
  {
14
+ "steps": 9952,
15
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-9952.onnx",
16
+ "reward": 3.1818181818181817,
17
+ "creation_time": 1677844441.6319678,
18
  "auxillary_file_paths": [
19
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-9952.pt"
20
  ]
21
  },
22
  {
23
+ "steps": 10208,
24
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-10208.onnx",
25
+ "reward": 3.1818181818181817,
26
+ "creation_time": 1677844441.8209934,
27
  "auxillary_file_paths": [
28
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-10208.pt"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
29
  ]
30
  }
31
  ],
32
  "final_checkpoint": {
33
+ "steps": 10208,
34
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
35
+ "reward": 3.1818181818181817,
36
+ "creation_time": 1677844441.8209934,
37
  "auxillary_file_paths": [
38
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-10208.pt"
39
  ]
40
  }
41
  },