Hugging Face's logo

Juliacnc
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
Juliacnc commited on
Commit
b46487b
·
1 Parent(s): e3e0aa8

Second Push

Browse files
Files changed (18) hide show
  1. SnowballTarget.onnx +1 -1
  2. SnowballTarget/SnowballTarget-149984.onnx +1 -1
  3. SnowballTarget/SnowballTarget-149984.pt +1 -1
  4. SnowballTarget/SnowballTarget-199984.onnx +1 -1
  5. SnowballTarget/SnowballTarget-199984.pt +1 -1
  6. SnowballTarget/SnowballTarget-200112.onnx +1 -1
  7. SnowballTarget/SnowballTarget-200112.pt +1 -1
  8. SnowballTarget/SnowballTarget-49936.onnx +1 -1
  9. SnowballTarget/SnowballTarget-49936.pt +1 -1
  10. SnowballTarget/SnowballTarget-99960.onnx +1 -1
  11. SnowballTarget/SnowballTarget-99960.pt +1 -1
  12. SnowballTarget/checkpoint.pt +1 -1
  13. SnowballTarget/events.out.tfevents.1700213868.29dd739d5cd8.2841.0 +3 -0
  14. config.json +1 -1
  15. configuration.yaml +4 -4
  16. run_logs/Player-0.log +14 -17
  17. run_logs/timers.json +126 -126
  18. run_logs/training_status.json +24 -24
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f2b88827b0b473bcaf528957c44e38324acac29f3bdf61dbe70565ed8324e16
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e8b7a16867ff9a84a6a74d0b7f96005ecf74072c0d7dad9c9316f6a21ab8208
3
  size 650646
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37bedf9b8df5a88ce35843026d249d087306fe68e2b216a4765feae7c6d9b9c4
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1000807ad99daa4778fa1c8ef862d33121efc98732d0d8983622674bb165a668
3
  size 650646
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:042fce04394f5a70f8f789ed4c7960973f206043ac865fc7d45d6e220ff6a20f
3
  size 3849115
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e52d92a9a3d5b6a70641b90cb505e44421e5d9135182b24e81eef70cef29ff2
3
  size 3849115
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f2b88827b0b473bcaf528957c44e38324acac29f3bdf61dbe70565ed8324e16
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e8b7a16867ff9a84a6a74d0b7f96005ecf74072c0d7dad9c9316f6a21ab8208
3
  size 650646
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:578ab55ccb1efa04b2ee43331810ef10cd81142bd4880efde6ac28937bc7241f
3
  size 3849115
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a00ea325e6bd367d9e39b38a1555f52bfe97564a2eb94aa76c1087ad17a8954
3
  size 3849115
SnowballTarget/SnowballTarget-200112.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f2b88827b0b473bcaf528957c44e38324acac29f3bdf61dbe70565ed8324e16
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e8b7a16867ff9a84a6a74d0b7f96005ecf74072c0d7dad9c9316f6a21ab8208
3
  size 650646
SnowballTarget/SnowballTarget-200112.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:00aa0fc36b2b672b2ec31372336d5a3612ed59e7c7a62cdd755315e09a787390
3
  size 3849115
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f90c0518ce079d0324f011ca835fa55dd349bab7db7fe5399034cc6ef563a3f5
3
  size 3849115
SnowballTarget/SnowballTarget-49936.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:429dbe82132ccc04bcdcc66d56a740a17522ca76fe191cb9a6e88e254e19890e
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8aead83dd73979514410ff2f8b83c8f43ab067067df2f54d3cd24a824c74835
3
  size 650646
SnowballTarget/SnowballTarget-49936.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:130a39c5beda152e591fb2601a0550f24171a530d520ece5b78fb01e43cf1fd0
3
  size 3849040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fb8902d29aee962a2edce53af8841bc57b0f21d5e1950bf3294c7997f0e1151
3
  size 3849040
SnowballTarget/SnowballTarget-99960.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b0c1a5e0525420c01cd2aa4185730e0a42ceef354cebdefe716f28b2c0756db1
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c332fa6df0610fe8fc21f88c7adbc90dfeb5133e08013a58bc34d6a33f89d6ee
3
  size 650646
SnowballTarget/SnowballTarget-99960.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e0b1ea5a6994b515878a9466a58d117d660a32b71d6440c4e0c3e64b87bdea2
3
  size 3849040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b2c573771c785c613adfafcef10cb471f2c655a1f2db5784f76dacaf9d74794
3
  size 3849040
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1a03cc7517ba55887a3e3fe28bc6e61a621c3b9f50236bb2f48cd01b71c5326a
3
  size 3848290
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27050d0b82b54244872e0b52ebce42502195553a7db329bcb32ca0f870d58031
3
  size 3848290
SnowballTarget/events.out.tfevents.1700213868.29dd739d5cd8.2841.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb82f20912cbc971ba9092f81cbdc5980293e970398c354c77288acbb34fa200
3
+ size 23620
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 512, "buffer_size": 2048, "learning_rate": 0.0001, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 5, "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, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "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": 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, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget2", "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
@@ -3,13 +3,13 @@ behaviors:
3
  SnowballTarget:
4
  trainer_type: ppo
5
  hyperparameters:
6
- batch_size: 512
7
  buffer_size: 2048
8
- learning_rate: 0.0001
9
  beta: 0.005
10
  epsilon: 0.2
11
  lambd: 0.95
12
- num_epoch: 5
13
  shared_critic: false
14
  learning_rate_schedule: linear
15
  beta_schedule: linear
@@ -65,7 +65,7 @@ engine_settings:
65
  no_graphics: true
66
  environment_parameters: null
67
  checkpoint_settings:
68
- run_id: SnowballTarget1
69
  initialize_from: null
70
  load_model: false
71
  resume: false
 
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
12
+ num_epoch: 3
13
  shared_critic: false
14
  learning_rate_schedule: linear
15
  beta_schedule: linear
 
65
  no_graphics: true
66
  environment_parameters: null
67
  checkpoint_settings:
68
+ run_id: SnowballTarget2
69
  initialize_from: null
70
  load_model: false
71
  resume: 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:2664:(snd_pcm_open_noupdate) Unknown PCM default
34
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
35
  FMOD initialized on nosound output
36
  Begin MonoManager ReloadAssembly
37
- - Completed reload, in 0.179 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: 1.417504 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]: 5373 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 45
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]: 5465 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
  Peak Allocated memory 6.7 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
- Peak usage frame count: [16.0 MB-32.0 MB]: 5465 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
- Peak Allocated memory 17.8 MB
188
  Peak Large allocation bytes 16.0 MB
189
  [ALLOC_TEMP_JOB_1_FRAME]
190
  Initial Block Size 2.0 MB
@@ -213,13 +210,13 @@ Memory Statistics:
213
  Used Block count 1
214
  Peak Allocated bytes 1.0 MB
215
  [ALLOC_GFX_MAIN]
216
- Peak usage frame count: [32.0 KB-64.0 KB]: 2772 frames, [64.0 KB-128.0 KB]: 2693 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
- Peak Allocated memory 68.6 KB
220
  Peak Large allocation bytes 0 B
221
  [ALLOC_GFX_THREAD]
222
- Peak usage frame count: [32.0 KB-64.0 KB]: 5465 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]: 5465 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]: 5464 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]: 5465 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]: 5465 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 0.119 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: 0.895052 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]: 5369 frames, [16.0 KB-32.0 KB]: 91 frames, [2.0 MB-4.0 MB]: 1 frames
54
  Initial Block Size 4.0 MB
55
  Current Block Size 4.0 MB
56
  Peak Allocated Bytes 2.0 MB
 
166
  Peak Allocated Bytes 0 B
167
  Overflow Count 0
168
  [ALLOC_DEFAULT] Dual Thread Allocator
169
+ Peak main deferred allocation count 40
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]: 5461 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
  Peak Allocated memory 6.7 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 5461 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
+ Peak Allocated memory 17.9 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]: 4553 frames, [64.0 KB-128.0 KB]: 908 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
+ Peak Allocated memory 66.8 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
+ Peak usage frame count: [32.0 KB-64.0 KB]: 5461 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]: 5461 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]: 5460 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]: 5461 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]: 5461 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
@@ -2,15 +2,15 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 1.4464707374572754,
6
- "min": 1.4464707374572754,
7
- "max": 2.8888542652130127,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 13890.4580078125,
12
- "min": 13890.4580078125,
13
- "max": 29711.8671875,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
@@ -26,15 +26,15 @@
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 7.000206470489502,
30
- "min": 0.3014809191226959,
31
- "max": 7.000206470489502,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 1365.040283203125,
36
- "min": 58.48729705810547,
37
- "max": 1417.77978515625,
38
  "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
@@ -44,93 +44,93 @@
44
  "count": 20
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
- "value": 10945.0,
48
  "min": 8756.0,
49
  "max": 10945.0,
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
- "value": 0.03251143182860687,
54
- "min": 0.02755875799892238,
55
- "max": 0.03639754710166017,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.13004572731442748,
60
- "min": 0.11620291110593826,
61
- "max": 0.16542555451742372,
62
  "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.3021865148097277,
66
- "min": 0.11356627373024822,
67
- "max": 0.3027107071131468,
68
  "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 1.2087460592389108,
72
- "min": 0.4542650949209929,
73
- "max": 1.493053851276636,
74
  "count": 20
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
- "value": 2.694097306000002e-06,
78
- "min": 2.694097306000002e-06,
79
- "max": 9.729400270599998e-05,
80
  "count": 20
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
- "value": 1.0776389224000008e-05,
84
- "min": 1.0776389224000008e-05,
85
- "max": 0.00046172003827999993,
86
  "count": 20
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
  "value": 0.10269400000000001,
90
  "min": 0.10269400000000001,
91
- "max": 0.197294,
92
  "count": 20
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
  "value": 0.41077600000000003,
96
  "min": 0.41077600000000003,
97
- "max": 0.9617200000000001,
98
  "count": 20
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
- "value": 0.00014443060000000015,
102
- "min": 0.00014443060000000015,
103
- "max": 0.004864970600000001,
104
  "count": 20
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
107
- "value": 0.0005777224000000006,
108
- "min": 0.0005777224000000006,
109
  "max": 0.023089828,
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 14.886363636363637,
114
- "min": 2.8181818181818183,
115
- "max": 14.886363636363637,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 655.0,
120
- "min": 124.0,
121
- "max": 780.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 14.886363636363637,
126
- "min": 2.8181818181818183,
127
- "max": 14.886363636363637,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 655.0,
132
- "min": 124.0,
133
- "max": 780.0,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
@@ -148,67 +148,67 @@
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1700210926",
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=SnowballTarget1 --no-graphics",
154
  "mlagents_version": "1.1.0.dev0",
155
  "mlagents_envs_version": "1.1.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.1.0+cu118",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1700211728"
160
  },
161
- "total": 802.2276677859999,
162
  "count": 1,
163
- "self": 1.2696698610000112,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.10868017299992516,
167
  "count": 1,
168
- "self": 0.10868017299992516
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 800.8493177519999,
172
  "count": 1,
173
- "self": 1.2985041249902451,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 2.6257434830000648,
177
  "count": 1,
178
- "self": 2.6257434830000648
179
  },
180
  "TrainerController.advance": {
181
- "total": 796.7516731080095,
182
- "count": 18215,
183
- "self": 0.5866176710211448,
184
  "children": {
185
  "env_step": {
186
- "total": 796.1650554369884,
187
- "count": 18215,
188
- "self": 620.9162266489875,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 174.6884779429962,
192
- "count": 18215,
193
- "self": 3.829018461991268,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 170.85945948100493,
197
- "count": 18215,
198
- "self": 170.85945948100493
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.5603508450046775,
204
- "count": 18215,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 797.3759559770115,
209
- "count": 18215,
210
  "is_parallel": true,
211
- "self": 371.7840203960253,
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": 0.011452198000029057,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.0062883150000061505,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.005163883000022906,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.005163883000022906
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.17074821799997153,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0009598409999398427,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.0005482760000177223,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.0005482760000177223
244
  },
245
  "communicator.exchange": {
246
- "total": 0.15225441699999465,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.15225441699999465
250
  },
251
  "steps_from_proto": {
252
- "total": 0.01698568400001932,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.005378727999868715,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.011606956000150603,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.011606956000150603
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 425.59193558098616,
271
- "count": 18214,
272
  "is_parallel": true,
273
- "self": 18.150302016005753,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 9.239884920003306,
277
- "count": 18214,
278
  "is_parallel": true,
279
- "self": 9.239884920003306
280
  },
281
  "communicator.exchange": {
282
- "total": 340.41024761198423,
283
- "count": 18214,
284
  "is_parallel": true,
285
- "self": 340.41024761198423
286
  },
287
  "steps_from_proto": {
288
- "total": 57.79150103299287,
289
- "count": 18214,
290
  "is_parallel": true,
291
- "self": 12.23856682297469,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 45.55293421001818,
295
- "count": 182140,
296
  "is_parallel": true,
297
- "self": 45.55293421001818
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 0.00030723300005774945,
313
  "count": 1,
314
- "self": 0.00030723300005774945,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,36 +320,36 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 787.9005640910663,
324
- "count": 853789,
325
  "is_parallel": true,
326
- "self": 23.710662900065586,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 423.8173472680014,
330
- "count": 853789,
331
  "is_parallel": true,
332
- "self": 422.39809815500143,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
- "total": 1.419249112999978,
336
  "count": 4,
337
  "is_parallel": true,
338
- "self": 1.419249112999978
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
- "total": 340.37255392299926,
344
  "count": 90,
345
  "is_parallel": true,
346
- "self": 149.6832335000023,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
- "total": 190.68932042299696,
350
- "count": 1800,
351
  "is_parallel": true,
352
- "self": 190.68932042299696
353
  }
354
  }
355
  }
@@ -360,14 +360,14 @@
360
  }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.17308980300003896,
364
  "count": 1,
365
- "self": 0.001899909000030675,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.17118989400000828,
369
  "count": 1,
370
- "self": 0.17118989400000828
371
  }
372
  }
373
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.8960713744163513,
6
+ "min": 0.8949620127677917,
7
+ "max": 2.8713607788085938,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 8585.259765625,
12
+ "min": 8585.259765625,
13
+ "max": 29531.9453125,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
 
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 12.795312881469727,
30
+ "min": 0.3766804337501526,
31
+ "max": 12.795312881469727,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2495.0859375,
36
+ "min": 73.07600402832031,
37
+ "max": 2592.4775390625,
38
  "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
 
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": 0.06441009030922763,
54
+ "min": 0.06441009030922763,
55
+ "max": 0.07703820894034032,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.25764036123691053,
60
+ "min": 0.25764036123691053,
61
+ "max": 0.38519104470170157,
62
  "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.19399183897265032,
66
+ "min": 0.12134793356823388,
67
+ "max": 0.2927957919882793,
68
  "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.7759673558906013,
72
+ "min": 0.4853917342729355,
73
+ "max": 1.4639789599413966,
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": 25.318181818181817,
114
+ "min": 3.5681818181818183,
115
+ "max": 25.318181818181817,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1114.0,
120
+ "min": 157.0,
121
+ "max": 1386.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 25.318181818181817,
126
+ "min": 3.5681818181818183,
127
+ "max": 25.318181818181817,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1114.0,
132
+ "min": 157.0,
133
+ "max": 1386.0,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
 
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1700213867",
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",
154
  "mlagents_version": "1.1.0.dev0",
155
  "mlagents_envs_version": "1.1.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.1.0+cu118",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1700214535"
160
  },
161
+ "total": 668.125257329,
162
  "count": 1,
163
+ "self": 0.5373887519999698,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.057306616000005306,
167
  "count": 1,
168
+ "self": 0.057306616000005306
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 667.530561961,
172
  "count": 1,
173
+ "self": 0.909551870981204,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 1.2729417499999727,
177
  "count": 1,
178
+ "self": 1.2729417499999727
179
  },
180
  "TrainerController.advance": {
181
+ "total": 665.249798838019,
182
+ "count": 18203,
183
+ "self": 0.4716272300128139,
184
  "children": {
185
  "env_step": {
186
+ "total": 664.7781716080062,
187
+ "count": 18203,
188
+ "self": 526.6191069429877,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 137.7183071200119,
192
+ "count": 18203,
193
+ "self": 2.68766987602487,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 135.03063724398703,
197
+ "count": 18203,
198
+ "self": 135.03063724398703
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.4407575450065906,
204
+ "count": 18203,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 664.8972165579979,
209
+ "count": 18203,
210
  "is_parallel": true,
211
+ "self": 306.0108396689984,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.002385325000091143,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0007248729999673742,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0016604520001237688,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0016604520001237688
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.06406840700003613,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0007396140000537343,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0005326780000132203,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0005326780000132203
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.060427391999951396,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.060427391999951396
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0023687230000177806,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.00044277799997871625,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0019259450000390643,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0019259450000390643
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 358.8863768889995,
271
+ "count": 18202,
272
  "is_parallel": true,
273
+ "self": 15.30407611797773,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 7.812224881031284,
277
+ "count": 18202,
278
  "is_parallel": true,
279
+ "self": 7.812224881031284
280
  },
281
  "communicator.exchange": {
282
+ "total": 286.00907331899975,
283
+ "count": 18202,
284
  "is_parallel": true,
285
+ "self": 286.00907331899975
286
  },
287
  "steps_from_proto": {
288
+ "total": 49.76100257099074,
289
+ "count": 18202,
290
  "is_parallel": true,
291
+ "self": 10.03324021204537,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 39.72776235894537,
295
+ "count": 182020,
296
  "is_parallel": true,
297
+ "self": 39.72776235894537
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 9.149699985755433e-05,
313
  "count": 1,
314
+ "self": 9.149699985755433e-05,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 658.1599903669684,
324
+ "count": 695969,
325
  "is_parallel": true,
326
+ "self": 18.15263410012392,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 354.0358871278445,
330
+ "count": 695969,
331
  "is_parallel": true,
332
+ "self": 353.4998522998442,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
+ "total": 0.5360348280003109,
336
  "count": 4,
337
  "is_parallel": true,
338
+ "self": 0.5360348280003109
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
+ "total": 285.97146913899996,
344
  "count": 90,
345
  "is_parallel": true,
346
+ "self": 89.78553824600579,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 196.18593089299418,
350
+ "count": 4587,
351
  "is_parallel": true,
352
+ "self": 196.18593089299418
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.09817800499990881,
364
  "count": 1,
365
+ "self": 0.0012312719998135435,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.09694673300009526,
369
  "count": 1,
370
+ "self": 0.09694673300009526
371
  }
372
  }
373
  }
run_logs/training_status.json CHANGED
@@ -3,57 +3,57 @@
3
  "checkpoints": [
4
  {
5
  "steps": 49936,
6
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 7.636363636363637,
8
- "creation_time": 1700211130.4776564,
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": 11.636363636363637,
17
- "creation_time": 1700211328.738513,
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",
25
- "reward": 13.909090909090908,
26
- "creation_time": 1700211525.7389174,
27
  "auxillary_file_paths": [
28
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
30
  },
31
  {
32
  "steps": 199984,
33
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
34
- "reward": 15.727272727272727,
35
- "creation_time": 1700211727.1575043,
36
  "auxillary_file_paths": [
37
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
39
  },
40
  {
41
  "steps": 200112,
42
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
43
- "reward": 15.727272727272727,
44
- "creation_time": 1700211727.3812227,
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": 15.727272727272727,
54
- "creation_time": 1700211727.3812227,
55
  "auxillary_file_paths": [
56
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },
 
3
  "checkpoints": [
4
  {
5
  "steps": 49936,
6
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-49936.onnx",
7
+ "reward": 13.0,
8
+ "creation_time": 1700214035.8472915,
9
  "auxillary_file_paths": [
10
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-49936.pt"
11
  ]
12
  },
13
  {
14
  "steps": 99960,
15
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-99960.onnx",
16
+ "reward": 20.454545454545453,
17
+ "creation_time": 1700214200.654603,
18
  "auxillary_file_paths": [
19
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
21
  },
22
  {
23
  "steps": 149984,
24
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.onnx",
25
+ "reward": 23.818181818181817,
26
+ "creation_time": 1700214369.3254986,
27
  "auxillary_file_paths": [
28
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
30
  },
31
  {
32
  "steps": 199984,
33
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.onnx",
34
+ "reward": 26.0,
35
+ "creation_time": 1700214535.234496,
36
  "auxillary_file_paths": [
37
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
39
  },
40
  {
41
  "steps": 200112,
42
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.onnx",
43
+ "reward": 26.0,
44
+ "creation_time": 1700214535.365021,
45
  "auxillary_file_paths": [
46
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.pt"
47
  ]
48
  }
49
  ],
50
  "final_checkpoint": {
51
  "steps": 200112,
52
+ "file_path": "results/SnowballTarget2/SnowballTarget.onnx",
53
+ "reward": 26.0,
54
+ "creation_time": 1700214535.365021,
55
  "auxillary_file_paths": [
56
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },