Hugging Face's logo

briannnyee
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
briannnyee commited on
Commit
6c9153c
·
verified ·
1 Parent(s): 57fef76

First Push

Browse files
Files changed (18) hide show
  1. SnowballTarget.onnx +2 -2
  2. SnowballTarget/SnowballTarget-149984.onnx +2 -2
  3. SnowballTarget/SnowballTarget-149984.pt +2 -2
  4. SnowballTarget/SnowballTarget-199984.onnx +2 -2
  5. SnowballTarget/SnowballTarget-199984.pt +2 -2
  6. SnowballTarget/SnowballTarget-200112.onnx +2 -2
  7. SnowballTarget/SnowballTarget-200112.pt +2 -2
  8. SnowballTarget/SnowballTarget-49936.onnx +2 -2
  9. SnowballTarget/SnowballTarget-49936.pt +2 -2
  10. SnowballTarget/SnowballTarget-99960.onnx +2 -2
  11. SnowballTarget/SnowballTarget-99960.pt +2 -2
  12. SnowballTarget/checkpoint.pt +2 -2
  13. SnowballTarget/events.out.tfevents.1724333857.8deba02a6242.9592.0 +3 -0
  14. config.json +1 -1
  15. configuration.yaml +3 -3
  16. run_logs/Player-0.log +15 -18
  17. run_logs/timers.json +124 -124
  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:ef4035e2de2a32fac3ecac1e4e9bfe735e15eb3225723ee68b2a103b6adf984b
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66f9bd902567a4b44d563cae3f739409ebe8cd59f4048bfcf205e44bc3940fa5
3
+ size 914755
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:87871b6b1b3361bb4ab3d961e59e589f768672e9da164c5e715f090b4b341dbf
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f339c4a859a3e98218a4e292178447af08e722bd5bb264e379c6ba40a91ec132
3
+ size 914755
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b6d4cc4c424be84d349ffce61be812947356e454acfee93a6cbbb9589516e56b
3
- size 3850075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16ee45af83c611780b35a91fc2a54ed712db1f3fa6aa76159cf9fb49e90e2c2a
3
+ size 5434379
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef4035e2de2a32fac3ecac1e4e9bfe735e15eb3225723ee68b2a103b6adf984b
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66f9bd902567a4b44d563cae3f739409ebe8cd59f4048bfcf205e44bc3940fa5
3
+ size 914755
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ee97b112c2550e4831376dab5a9aa205eea6ec140cc6299623fb93515b05a89
3
- size 3850075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38f52007b11e3a0db933b7c56ea9b49c33ad2b5a49f0e80cddca3fc91fd7b290
3
+ size 5434379
SnowballTarget/SnowballTarget-200112.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef4035e2de2a32fac3ecac1e4e9bfe735e15eb3225723ee68b2a103b6adf984b
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66f9bd902567a4b44d563cae3f739409ebe8cd59f4048bfcf205e44bc3940fa5
3
+ size 914755
SnowballTarget/SnowballTarget-200112.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b5b0deb31948d715376bcd52a3d5900917ab8af2ee68a55c067d35d9c5dd39a4
3
- size 3850075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a34c2a0162097a7f42f557b5784726a48b4920761b7c23041791b3de39f341a
3
+ size 5434379
SnowballTarget/SnowballTarget-49936.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e7c6ecebc1f2a9e1d00d55617365af44a8229e7efa59e21ee6b237990cde888
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e8dc38cf8d84e9cb03142b936c9b5fa5b812d749c772e64f8f4bac8ecd4a391
3
+ size 914755
SnowballTarget/SnowballTarget-49936.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ce63c298fb055803cb5daae4ebf41904b924f95eba38bfe2913720467ae09e8
3
- size 3850000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f981800b938c6aaefbc848a022c85823861515518e007a9e7ba65adcae626e40
3
+ size 5434288
SnowballTarget/SnowballTarget-99960.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0697808ed7db502662c03395c54770bb26007a327c0b92a266e67984a02e07c3
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f1d0fbe85902674efcfc38f4ae15b1422496f9e57212a0ec2c52cee517be1fb
3
+ size 914755
SnowballTarget/SnowballTarget-99960.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:236423255e41751836cd3d8da0335d9bc1b2f9166ae3614f18a78c8f08a71f77
3
- size 3850000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22b66fec72f72aff7f02c780e31856f32ee16293f9ae58b25f86c0026be1697f
3
+ size 5434288
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:88cc42311583919b9c3eca2070a72dc4fb87bc6b74fabb3553d3757ee3110938
3
- size 3849250
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac3aa816dc0321d08ea9ac380a965263f4f5bfd707857a26c63dca93c9220868
3
+ size 5433378
SnowballTarget/events.out.tfevents.1724333857.8deba02a6242.9592.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f784b75b8fedc57a75da0c131674241c23f475437b6b5b64ba7eae4a03c461f
3
+ size 23350
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "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, "no_graphics_monitor": false}, "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": 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": 3, "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, "no_graphics_monitor": false}, "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
@@ -9,7 +9,7 @@ behaviors:
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
@@ -18,7 +18,7 @@ behaviors:
18
  network_settings:
19
  normalize: false
20
  hidden_units: 256
21
- num_layers: 2
22
  vis_encode_type: simple
23
  memory: null
24
  goal_conditioning_type: hyper
@@ -66,7 +66,7 @@ engine_settings:
66
  no_graphics_monitor: false
67
  environment_parameters: null
68
  checkpoint_settings:
69
- run_id: SnowballTarget1
70
  initialize_from: null
71
  load_model: false
72
  resume: false
 
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
 
18
  network_settings:
19
  normalize: false
20
  hidden_units: 256
21
+ num_layers: 3
22
  vis_encode_type: simple
23
  memory: null
24
  goal_conditioning_type: hyper
 
66
  no_graphics_monitor: false
67
  environment_parameters: null
68
  checkpoint_settings:
69
+ run_id: SnowballTarget2
70
  initialize_from: null
71
  load_model: false
72
  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 0.087 seconds
38
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
39
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
40
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -45,7 +42,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
45
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
46
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
47
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
48
- UnloadTime: 0.630282 ms
49
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
50
  requesting resize 84 x 84
51
  Setting up 1 worker threads for Enlighten.
@@ -53,7 +50,7 @@ Memory Statistics:
53
  [ALLOC_TEMP_TLS] TLS Allocator
54
  StackAllocators :
55
  [ALLOC_TEMP_MAIN]
56
- Peak usage frame count: [8.0 KB-16.0 KB]: 5369 frames, [16.0 KB-32.0 KB]: 91 frames, [2.0 MB-4.0 MB]: 1 frames
57
  Initial Block Size 4.0 MB
58
  Current Block Size 4.0 MB
59
  Peak Allocated Bytes 2.0 MB
@@ -169,22 +166,22 @@ Memory Statistics:
169
  Peak Allocated Bytes 0 B
170
  Overflow Count 0
171
  [ALLOC_DEFAULT] Dual Thread Allocator
172
- Peak main deferred allocation count 46
173
  [ALLOC_BUCKET]
174
  Large Block size 4.0 MB
175
  Used Block count 1
176
  Peak Allocated bytes 1.0 MB
177
  [ALLOC_DEFAULT_MAIN]
178
- Peak usage frame count: [4.0 MB-8.0 MB]: 5461 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
- Peak Allocated memory 6.8 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
- Peak usage frame count: [16.0 MB-32.0 MB]: 5461 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
- Peak Allocated memory 17.7 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]: 4028 frames, [64.0 KB-128.0 KB]: 1433 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
- Peak Allocated memory 67.7 KB
220
  Peak Large allocation bytes 0 B
221
  [ALLOC_GFX_THREAD]
222
- Peak usage frame count: [32.0 KB-64.0 KB]: 5461 frames
223
  Requested Block Size 16.0 MB
224
  Peak Block count 1
225
  Peak Allocated memory 39.6 KB
@@ -231,13 +228,13 @@ Memory Statistics:
231
  Used Block count 1
232
  Peak Allocated bytes 1.0 MB
233
  [ALLOC_CACHEOBJECTS_MAIN]
234
- Peak usage frame count: [0.5 MB-1.0 MB]: 5461 frames
235
  Requested Block Size 4.0 MB
236
  Peak Block count 1
237
  Peak Allocated memory 0.6 MB
238
  Peak Large allocation bytes 0 B
239
  [ALLOC_CACHEOBJECTS_THREAD]
240
- Peak usage frame count: [0.5 MB-1.0 MB]: 5460 frames, [2.0 MB-4.0 MB]: 1 frames
241
  Requested Block Size 4.0 MB
242
  Peak Block count 1
243
  Peak Allocated memory 2.2 MB
@@ -249,13 +246,13 @@ Memory Statistics:
249
  Used Block count 1
250
  Peak Allocated bytes 1.0 MB
251
  [ALLOC_TYPETREE_MAIN]
252
- Peak usage frame count: [0-1.0 KB]: 5461 frames
253
  Requested Block Size 2.0 MB
254
  Peak Block count 1
255
  Peak Allocated memory 1.0 KB
256
  Peak Large allocation bytes 0 B
257
  [ALLOC_TYPETREE_THREAD]
258
- Peak usage frame count: [1.0 KB-2.0 KB]: 5461 frames
259
  Requested Block Size 2.0 MB
260
  Peak Block count 1
261
  Peak Allocated memory 1.7 KB
 
2
  Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
3
  Preloaded 'lib_burst_generated.so'
4
  Preloaded 'libgrpc_csharp_ext.x64.so'
 
 
 
5
  Initialize engine version: 2021.3.14f1 (eee1884e7226)
6
  [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
7
  Forcing GfxDevice: Null
 
31
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
32
  FMOD initialized on nosound output
33
  Begin MonoManager ReloadAssembly
34
+ - Completed reload, in 0.085 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: 0.674727 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]: 5371 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 44
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]: 5463 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]: 5463 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
 
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]: 5024 frames, [64.0 KB-128.0 KB]: 439 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
+ Peak Allocated memory 67.2 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
+ Peak usage frame count: [32.0 KB-64.0 KB]: 5463 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]: 5463 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]: 5462 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]: 5463 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]: 5463 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": 1.0384373664855957,
6
- "min": 1.0384373664855957,
7
- "max": 2.8559584617614746,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 9915.0,
12
- "min": 9915.0,
13
- "max": 29247.87109375,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
@@ -26,15 +26,15 @@
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 12.189550399780273,
30
- "min": 0.4255053400993347,
31
- "max": 12.189550399780273,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2376.96240234375,
36
- "min": 82.54803466796875,
37
- "max": 2462.41064453125,
38
  "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
@@ -44,63 +44,63 @@
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": 0.07356240453387443,
54
- "min": 0.05799809854990787,
55
- "max": 0.07501606463498035,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.2942496181354977,
60
- "min": 0.23199239419963147,
61
- "max": 0.3724369349148736,
62
  "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.20118075623816134,
66
- "min": 0.1201416079489076,
67
- "max": 0.2702872181055592,
68
  "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.8047230249526454,
72
- "min": 0.4805664317956304,
73
- "max": 1.3514360905277962,
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": {
@@ -110,27 +110,27 @@
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 24.15909090909091,
114
- "min": 3.227272727272727,
115
- "max": 24.15909090909091,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1063.0,
120
- "min": 142.0,
121
- "max": 1305.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 24.15909090909091,
126
- "min": 3.227272727272727,
127
- "max": 24.15909090909091,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1063.0,
132
- "min": 142.0,
133
- "max": 1305.0,
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": "1724331813",
152
  "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "2.3.1+cu121",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1724332244"
160
  },
161
- "total": 431.1629563629999,
162
  "count": 1,
163
- "self": 0.43149411699988605,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.060371717999998964,
167
  "count": 1,
168
- "self": 0.060371717999998964
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 430.67109052800004,
172
  "count": 1,
173
- "self": 0.5330210149974164,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 2.919699554999994,
177
  "count": 1,
178
- "self": 2.919699554999994
179
  },
180
  "TrainerController.advance": {
181
- "total": 427.1275536780026,
182
- "count": 18201,
183
- "self": 0.26221873899834236,
184
  "children": {
185
  "env_step": {
186
- "total": 426.86533493900424,
187
- "count": 18201,
188
- "self": 273.9763929870122,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 152.61930772300005,
192
- "count": 18201,
193
- "self": 1.4266421900051967,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 151.19266553299485,
197
- "count": 18201,
198
- "self": 151.19266553299485
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.26963422899200395,
204
- "count": 18201,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 429.4961787850019,
209
- "count": 18201,
210
  "is_parallel": true,
211
- "self": 217.98473687199746,
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": 0.005386122000004434,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.0038400240000271424,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0015460979999772917,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0015460979999772917
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.03681795800000032,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.000724001999998336,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.00040230100000826496,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.00040230100000826496
244
  },
245
  "communicator.exchange": {
246
- "total": 0.033562860000017736,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.033562860000017736
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0021287949999759803,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.0005832719999716574,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.001545523000004323,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.001545523000004323
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 211.51144191300446,
271
- "count": 18200,
272
  "is_parallel": true,
273
- "self": 9.799379372001141,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 5.008672770999681,
277
- "count": 18200,
278
  "is_parallel": true,
279
- "self": 5.008672770999681
280
  },
281
  "communicator.exchange": {
282
- "total": 164.71318103400046,
283
- "count": 18200,
284
  "is_parallel": true,
285
- "self": 164.71318103400046
286
  },
287
  "steps_from_proto": {
288
- "total": 31.990208736003183,
289
- "count": 18200,
290
  "is_parallel": true,
291
- "self": 5.9835831110025595,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 26.006625625000623,
295
- "count": 182000,
296
  "is_parallel": true,
297
- "self": 26.006625625000623
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 0.00012205600000925187,
313
  "count": 1,
314
- "self": 0.00012205600000925187,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,36 +320,36 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 421.75778035101,
324
- "count": 655406,
325
  "is_parallel": true,
326
- "self": 13.355723570954297,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 232.79396341205518,
330
- "count": 655406,
331
  "is_parallel": true,
332
- "self": 232.16192724705508,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
- "total": 0.6320361650001018,
336
  "count": 4,
337
  "is_parallel": true,
338
- "self": 0.6320361650001018
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
- "total": 175.60809336800054,
344
  "count": 90,
345
  "is_parallel": true,
346
- "self": 54.41475727700225,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
- "total": 121.19333609099829,
350
- "count": 4587,
351
  "is_parallel": true,
352
- "self": 121.19333609099829
353
  }
354
  }
355
  }
@@ -360,14 +360,14 @@
360
  }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.09069422400000349,
364
  "count": 1,
365
- "self": 0.0009345669999447637,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.08975965700005872,
369
  "count": 1,
370
- "self": 0.08975965700005872
371
  }
372
  }
373
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.8833903670310974,
6
+ "min": 0.8833903670310974,
7
+ "max": 2.844938278198242,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 8473.48046875,
12
+ "min": 8473.48046875,
13
+ "max": 29135.01171875,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
 
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 13.284790992736816,
30
+ "min": 0.4931192398071289,
31
+ "max": 13.349401473999023,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2590.5341796875,
36
+ "min": 95.66513061523438,
37
+ "max": 2723.27783203125,
38
  "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
 
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": 0.06640885960796902,
54
+ "min": 0.06242731894027469,
55
+ "max": 0.07238078322492691,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.2656354384318761,
60
+ "min": 0.2503646752778235,
61
+ "max": 0.36054516274786746,
62
  "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.20126332829103752,
66
+ "min": 0.12896142220946358,
67
+ "max": 0.29486485418151404,
68
  "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.8050533131641501,
72
+ "min": 0.5158456888378543,
73
+ "max": 1.4743242709075701,
74
  "count": 20
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
+ "value": 8.082097306000009e-06,
78
+ "min": 8.082097306000009e-06,
79
  "max": 0.000291882002706,
80
  "count": 20
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
+ "value": 3.2328389224000035e-05,
84
+ "min": 3.2328389224000035e-05,
85
  "max": 0.00138516003828,
86
  "count": 20
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
+ "value": 0.10269399999999998,
90
+ "min": 0.10269399999999998,
91
+ "max": 0.197294,
92
  "count": 20
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
+ "value": 0.4107759999999999,
96
+ "min": 0.4107759999999999,
97
+ "max": 0.9617200000000001,
98
  "count": 20
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
  "value": 0.0001444306000000001,
102
  "min": 0.0001444306000000001,
103
+ "max": 0.004864970599999999,
104
  "count": 20
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
 
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 26.113636363636363,
114
+ "min": 4.0,
115
+ "max": 26.431818181818183,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1149.0,
120
+ "min": 176.0,
121
+ "max": 1453.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 26.113636363636363,
126
+ "min": 4.0,
127
+ "max": 26.431818181818183,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1149.0,
132
+ "min": 176.0,
133
+ "max": 1453.0,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
 
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1724333857",
152
  "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "2.3.1+cu121",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1724334346"
160
  },
161
+ "total": 489.53835439700015,
162
  "count": 1,
163
+ "self": 0.426320270999895,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.05348195800024769,
167
  "count": 1,
168
+ "self": 0.05348195800024769
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 489.058552168,
172
  "count": 1,
173
+ "self": 0.5278732290225889,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 2.044195228999797,
177
  "count": 1,
178
+ "self": 2.044195228999797
179
  },
180
  "TrainerController.advance": {
181
+ "total": 486.3820269959774,
182
+ "count": 18207,
183
+ "self": 0.24879356395740615,
184
  "children": {
185
  "env_step": {
186
+ "total": 486.13323343202,
187
+ "count": 18207,
188
+ "self": 332.603935729986,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 153.27051585499703,
192
+ "count": 18207,
193
+ "self": 1.3964455650248055,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 151.87407028997222,
197
+ "count": 18207,
198
+ "self": 151.87407028997222
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.25878184703697116,
204
+ "count": 18207,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 487.9227121609715,
209
+ "count": 18207,
210
  "is_parallel": true,
211
+ "self": 280.5865455109865,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.002134323000063887,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0006300740001279337,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0015042489999359532,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0015042489999359532
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.037524909999774536,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0006427270000131102,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.00040964099980556057,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.00040964099980556057
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.03454224500001146,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.03454224500001146
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.001930296999944403,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0003812010004367039,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0015490959995076992,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0015490959995076992
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 207.336166649985,
271
+ "count": 18206,
272
  "is_parallel": true,
273
+ "self": 9.727830612991966,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 5.160190115035675,
277
+ "count": 18206,
278
  "is_parallel": true,
279
+ "self": 5.160190115035675
280
  },
281
  "communicator.exchange": {
282
+ "total": 160.59311277697907,
283
+ "count": 18206,
284
  "is_parallel": true,
285
+ "self": 160.59311277697907
286
  },
287
  "steps_from_proto": {
288
+ "total": 31.85503314497828,
289
+ "count": 18206,
290
  "is_parallel": true,
291
+ "self": 5.938592139966659,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 25.91644100501162,
295
+ "count": 182060,
296
  "is_parallel": true,
297
+ "self": 25.91644100501162
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 0.0001603770001565863,
313
  "count": 1,
314
+ "self": 0.0001603770001565863,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 480.955770004085,
324
+ "count": 644090,
325
  "is_parallel": true,
326
+ "self": 13.637962203492862,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 231.8968412825916,
330
+ "count": 644090,
331
  "is_parallel": true,
332
+ "self": 230.95321552759196,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
+ "total": 0.9436257549996299,
336
  "count": 4,
337
  "is_parallel": true,
338
+ "self": 0.9436257549996299
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
+ "total": 235.42096651800057,
344
  "count": 90,
345
  "is_parallel": true,
346
+ "self": 80.71888793399694,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 154.70207858400363,
350
+ "count": 7645,
351
  "is_parallel": true,
352
+ "self": 154.70207858400363
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.1042963370000507,
364
  "count": 1,
365
+ "self": 0.0010795800003506884,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.10321675699970001,
369
  "count": 1,
370
+ "self": 0.10321675699970001
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": 12.818181818181818,
8
- "creation_time": 1724331923.2383513,
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": 19.454545454545453,
17
- "creation_time": 1724332028.7104037,
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": 22.363636363636363,
26
- "creation_time": 1724332135.0059924,
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": 24.818181818181817,
35
- "creation_time": 1724332243.8135328,
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": 24.818181818181817,
44
- "creation_time": 1724332243.931337,
45
  "auxillary_file_paths": [
46
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
47
  ]
48
  }
49
  ],
50
  "final_checkpoint": {
51
  "steps": 200112,
52
- "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
53
- "reward": 24.818181818181817,
54
- "creation_time": 1724332243.931337,
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": 18.727272727272727,
8
+ "creation_time": 1724333981.4948874,
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": 25.0,
17
+ "creation_time": 1724334103.533036,
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": 25.636363636363637,
26
+ "creation_time": 1724334225.965563,
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": 26.09090909090909,
35
+ "creation_time": 1724334346.1580193,
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": 26.09090909090909,
44
+ "creation_time": 1724334346.2783587,
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": 26.09090909090909,
54
+ "creation_time": 1724334346.2783587,
55
  "auxillary_file_paths": [
56
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },