Hugging Face's logo

Brumocas
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
Brumocas commited on
Commit
6f0f7d7
·
verified ·
1 Parent(s): c3990be

Improved Training_1

Browse files
Files changed (28) hide show
  1. SnowballTarget.onnx +1 -1
  2. SnowballTarget/SnowballTarget-1000120.onnx +3 -0
  3. SnowballTarget/SnowballTarget-1000120.pt +3 -0
  4. SnowballTarget/SnowballTarget-599976.onnx +3 -0
  5. SnowballTarget/SnowballTarget-599976.pt +3 -0
  6. SnowballTarget/SnowballTarget-649936.onnx +3 -0
  7. SnowballTarget/SnowballTarget-649936.pt +3 -0
  8. SnowballTarget/SnowballTarget-699960.onnx +3 -0
  9. SnowballTarget/SnowballTarget-699960.pt +3 -0
  10. SnowballTarget/SnowballTarget-749960.onnx +3 -0
  11. SnowballTarget/SnowballTarget-749960.pt +3 -0
  12. SnowballTarget/SnowballTarget-799984.onnx +3 -0
  13. SnowballTarget/SnowballTarget-799984.pt +3 -0
  14. SnowballTarget/SnowballTarget-849944.onnx +3 -0
  15. SnowballTarget/SnowballTarget-849944.pt +3 -0
  16. SnowballTarget/SnowballTarget-899968.onnx +3 -0
  17. SnowballTarget/SnowballTarget-899968.pt +3 -0
  18. SnowballTarget/SnowballTarget-949968.onnx +3 -0
  19. SnowballTarget/SnowballTarget-949968.pt +3 -0
  20. SnowballTarget/SnowballTarget-999992.onnx +3 -0
  21. SnowballTarget/SnowballTarget-999992.pt +3 -0
  22. SnowballTarget/checkpoint.pt +1 -1
  23. SnowballTarget/events.out.tfevents.1730728013.6f03cf4e36ee.8633.0 +3 -0
  24. config.json +1 -1
  25. configuration.yaml +1 -1
  26. run_logs/Player-0.log +16 -16
  27. run_logs/timers.json +161 -161
  28. run_logs/training_status.json +70 -34
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:42fae1f6e866334fa9a80c9b457ced0e004b23ad03050091950c4bba0a67787b
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fbcccfe4cdcae0a7b9e717a01d5235d7c9cf55c805a6df77c04af15eca4ab80
3
  size 650646
SnowballTarget/SnowballTarget-1000120.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fbcccfe4cdcae0a7b9e717a01d5235d7c9cf55c805a6df77c04af15eca4ab80
3
+ size 650646
SnowballTarget/SnowballTarget-1000120.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73b38fa7c8da8304aa148e13c7f1bba2834233956db29927fac7750e75bdec07
3
+ size 3850214
SnowballTarget/SnowballTarget-599976.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a41317a71e7fb3566106891f6ea4a2fca3d94c474e57dfed7d5f36a9a90f5775
3
+ size 650646
SnowballTarget/SnowballTarget-599976.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a946237a45ecad45b3f4bc2522812b51cb88757c617667818944aeedf3700200
3
+ size 3850075
SnowballTarget/SnowballTarget-649936.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08dd80e921951c5e7abea93f6d9edd8023d3898449e6dad3df14bfed5700d2f4
3
+ size 650646
SnowballTarget/SnowballTarget-649936.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c17306b13c79b870359d0f9d634c466820ddc8c3c06e9cb147c330c21bedce28
3
+ size 3850075
SnowballTarget/SnowballTarget-699960.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e186365bb11cdad37251e96a4e8de644cdc15f0d2e72ee4ed5b316bc3ea904fc
3
+ size 650646
SnowballTarget/SnowballTarget-699960.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00c718b28b7e81b8806cd932a6f82746896676f22d2a1e8638092507958e9361
3
+ size 3850075
SnowballTarget/SnowballTarget-749960.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fe0258e9b7ab6f3c58e2b02d996008dad38acd6d280cf08659affe7b969033b
3
+ size 650646
SnowballTarget/SnowballTarget-749960.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36b8174f8a5cc2c479d01d53dd8ee79504393f63f9a81f9f57a1c02c84e03853
3
+ size 3850075
SnowballTarget/SnowballTarget-799984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72674c44b917031bc3856487d95fb754f38478712d7e2f3b6ce308fc6f004f9e
3
+ size 650646
SnowballTarget/SnowballTarget-799984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98c070e9365a5eb8150eed1bf11a1430135ba144a96641b10e5182f7dc328702
3
+ size 3850075
SnowballTarget/SnowballTarget-849944.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a6710738dc075e9e297866ade0794d07e000fa4d3c8a8ef71a9c6f851c3b881
3
+ size 650646
SnowballTarget/SnowballTarget-849944.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b87c670fd0cb1f5f5e459a250ff2f11e8d4fb71bd1c75b70fbc8e70ec812124a
3
+ size 3850075
SnowballTarget/SnowballTarget-899968.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5e5cfc3b7d1418f5f99fa2c667f203d1981ed82cc534d43231a3d66f5fd7901
3
+ size 650646
SnowballTarget/SnowballTarget-899968.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdf6a408e0babb83d201df09cf9ceaf416e1a091317f27f65c862c80ac613afc
3
+ size 3850075
SnowballTarget/SnowballTarget-949968.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a28fb5280bf9deaa549bf61cc29dcd959321e4f2d187b9fe165e30b8455db94
3
+ size 650646
SnowballTarget/SnowballTarget-949968.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08b2c5e0208ed4243b4a9009e783dc01c3525b8e181608eff5f368b95ded4349
3
+ size 3850075
SnowballTarget/SnowballTarget-999992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fbcccfe4cdcae0a7b9e717a01d5235d7c9cf55c805a6df77c04af15eca4ab80
3
+ size 650646
SnowballTarget/SnowballTarget-999992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6c3bde4f82252c62ad9accd9aa9f8fda3caf5a1f9a56ae46b6034fb9c760e4b
3
+ size 3850075
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:70d299e2ddba5ecfdb7b8955240e94e6a0e061b58dfdaad00ea9dcb8327300eb
3
  size 3849250
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd11ed5c4e4cff75858586f78ef228898b0fcbd1e924de048d3a7862b7f115d9
3
  size 3849250
SnowballTarget/events.out.tfevents.1730728013.6f03cf4e36ee.8633.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1c267182169c5716de9cddcc0559288a8ee6832ce1eca5831c232b7f3952007
3
+ size 67148
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": false, "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": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
 
1
+ {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 1000000, "time_horizon": 64, "summary_freq": 10000, "threaded": false, "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": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -38,7 +38,7 @@ behaviors:
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
- max_steps: 200000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: false
 
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
+ max_steps: 1000000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: false
run_logs/Player-0.log CHANGED
@@ -31,7 +31,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
31
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
32
  FMOD initialized on nosound output
33
  Begin MonoManager ReloadAssembly
34
- - Completed reload, in 0.082 seconds
35
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
36
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
37
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -42,7 +42,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
42
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
43
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
44
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
45
- UnloadTime: 0.656358 ms
46
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
47
  requesting resize 84 x 84
48
  Setting up 1 worker threads for Enlighten.
@@ -50,7 +50,7 @@ Memory Statistics:
50
  [ALLOC_TEMP_TLS] TLS Allocator
51
  StackAllocators :
52
  [ALLOC_TEMP_MAIN]
53
- Peak usage frame count: [8.0 KB-16.0 KB]: 5367 frames, [16.0 KB-32.0 KB]: 90 frames, [2.0 MB-4.0 MB]: 1 frames
54
  Initial Block Size 4.0 MB
55
  Current Block Size 4.0 MB
56
  Peak Allocated Bytes 2.0 MB
@@ -166,23 +166,23 @@ Memory Statistics:
166
  Peak Allocated Bytes 0 B
167
  Overflow Count 0
168
  [ALLOC_DEFAULT] Dual Thread Allocator
169
- Peak main deferred allocation count 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]: 5458 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
- Peak Allocated memory 6.6 MB
179
- Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
- Peak usage frame count: [16.0 MB-32.0 MB]: 5458 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
- Peak Allocated memory 17.8 MB
185
- Peak Large allocation bytes 16.0 MB
186
  [ALLOC_TEMP_JOB_1_FRAME]
187
  Initial Block Size 2.0 MB
188
  Used Block Count 1
@@ -210,13 +210,13 @@ Memory Statistics:
210
  Used Block count 1
211
  Peak Allocated bytes 1.0 MB
212
  [ALLOC_GFX_MAIN]
213
- Peak usage frame count: [32.0 KB-64.0 KB]: 4703 frames, [64.0 KB-128.0 KB]: 755 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]: 5458 frames
220
  Requested Block Size 16.0 MB
221
  Peak Block count 1
222
  Peak Allocated memory 39.6 KB
@@ -228,13 +228,13 @@ Memory Statistics:
228
  Used Block count 1
229
  Peak Allocated bytes 1.0 MB
230
  [ALLOC_CACHEOBJECTS_MAIN]
231
- Peak usage frame count: [0.5 MB-1.0 MB]: 5458 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]: 5457 frames, [2.0 MB-4.0 MB]: 1 frames
238
  Requested Block Size 4.0 MB
239
  Peak Block count 1
240
  Peak Allocated memory 2.2 MB
@@ -246,13 +246,13 @@ Memory Statistics:
246
  Used Block count 1
247
  Peak Allocated bytes 1.0 MB
248
  [ALLOC_TYPETREE_MAIN]
249
- Peak usage frame count: [0-1.0 KB]: 5458 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]: 5458 frames
256
  Requested Block Size 2.0 MB
257
  Peak Block count 1
258
  Peak Allocated memory 1.7 KB
 
31
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
32
  FMOD initialized on nosound output
33
  Begin MonoManager ReloadAssembly
34
+ - Completed reload, in 0.130 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: 0.868923 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]: 21455 frames, [16.0 KB-32.0 KB]: 363 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 33
170
  [ALLOC_BUCKET]
171
  Large Block size 4.0 MB
172
  Used Block count 1
173
  Peak Allocated bytes 1.0 MB
174
  [ALLOC_DEFAULT_MAIN]
175
+ Peak usage frame count: [16.0 MB-32.0 MB]: 21819 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
+ Peak Allocated memory 28.3 MB
179
+ Peak Large allocation bytes 16.0 MB
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [1.0 MB-2.0 MB]: 21819 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
+ Peak Allocated memory 1.4 MB
185
+ Peak Large allocation bytes 0 B
186
  [ALLOC_TEMP_JOB_1_FRAME]
187
  Initial Block Size 2.0 MB
188
  Used Block Count 1
 
210
  Used Block count 1
211
  Peak Allocated bytes 1.0 MB
212
  [ALLOC_GFX_MAIN]
213
+ Peak usage frame count: [32.0 KB-64.0 KB]: 21300 frames, [64.0 KB-128.0 KB]: 519 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]: 21819 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]: 21819 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]: 21818 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]: 21819 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]: 21819 frames
256
  Requested Block Size 2.0 MB
257
  Peak Block count 1
258
  Peak Allocated memory 1.7 KB
run_logs/timers.json CHANGED
@@ -2,153 +2,153 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 0.8375208377838135,
6
- "min": 0.8375208377838135,
7
- "max": 2.862612724304199,
8
- "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 7959.7978515625,
12
- "min": 7959.7978515625,
13
- "max": 29221.55078125,
14
- "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
17
- "value": 199984.0,
18
- "min": 9952.0,
19
- "max": 199984.0,
20
- "count": 20
21
  },
22
  "SnowballTarget.Step.sum": {
23
- "value": 199984.0,
24
- "min": 9952.0,
25
- "max": 199984.0,
26
- "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 12.981234550476074,
30
- "min": 0.40167486667633057,
31
- "max": 12.981234550476074,
32
- "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2531.3408203125,
36
- "min": 77.9249267578125,
37
- "max": 2637.80810546875,
38
- "count": 20
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
- "value": 0.06575937363788184,
42
- "min": 0.06296241341145052,
43
- "max": 0.07252992254647075,
44
- "count": 20
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
- "value": 0.26303749455152736,
48
- "min": 0.25378506844543725,
49
- "max": 0.36264961273235374,
50
- "count": 20
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
- "value": 0.19090985813561606,
54
- "min": 0.11745862592258217,
55
- "max": 0.2897929125556759,
56
- "count": 20
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
- "value": 0.7636394325424642,
60
- "min": 0.4698345036903287,
61
- "max": 1.4489645627783796,
62
- "count": 20
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
65
- "value": 8.082097306000005e-06,
66
- "min": 8.082097306000005e-06,
67
- "max": 0.000291882002706,
68
- "count": 20
69
  },
70
  "SnowballTarget.Policy.LearningRate.sum": {
71
- "value": 3.232838922400002e-05,
72
- "min": 3.232838922400002e-05,
73
- "max": 0.00138516003828,
74
- "count": 20
75
  },
76
  "SnowballTarget.Policy.Epsilon.mean": {
77
- "value": 0.10269400000000001,
78
- "min": 0.10269400000000001,
79
- "max": 0.19729400000000002,
80
- "count": 20
81
  },
82
  "SnowballTarget.Policy.Epsilon.sum": {
83
- "value": 0.41077600000000003,
84
- "min": 0.41077600000000003,
85
- "max": 0.96172,
86
- "count": 20
87
  },
88
  "SnowballTarget.Policy.Beta.mean": {
89
- "value": 0.0001444306000000001,
90
- "min": 0.0001444306000000001,
91
- "max": 0.0048649706,
92
- "count": 20
93
  },
94
  "SnowballTarget.Policy.Beta.sum": {
95
- "value": 0.0005777224000000004,
96
- "min": 0.0005777224000000004,
97
- "max": 0.023089828,
98
- "count": 20
99
  },
100
  "SnowballTarget.Environment.EpisodeLength.mean": {
101
  "value": 199.0,
102
  "min": 199.0,
103
  "max": 199.0,
104
- "count": 20
105
  },
106
  "SnowballTarget.Environment.EpisodeLength.sum": {
107
  "value": 8756.0,
108
  "min": 8756.0,
109
  "max": 10945.0,
110
- "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 25.613636363636363,
114
- "min": 3.5,
115
- "max": 25.613636363636363,
116
- "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1127.0,
120
- "min": 154.0,
121
- "max": 1399.0,
122
- "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 25.613636363636363,
126
- "min": 3.5,
127
- "max": 25.613636363636363,
128
- "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1127.0,
132
- "min": 154.0,
133
- "max": 1399.0,
134
- "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
- "count": 20
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
- "count": 20
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1730727226",
152
  "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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 --resume",
154
  "mlagents_version": "1.2.0.dev0",
@@ -156,59 +156,59 @@
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.5.0+cu121",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1730727669"
160
  },
161
- "total": 442.45249143699994,
162
  "count": 1,
163
- "self": 0.4818635369997537,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.05374190800012002,
167
  "count": 1,
168
- "self": 0.05374190800012002
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 441.91688599200006,
172
  "count": 1,
173
- "self": 0.3984946130080971,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 1.935235170000169,
177
  "count": 1,
178
- "self": 1.935235170000169
179
  },
180
  "TrainerController.advance": {
181
- "total": 439.48296594299177,
182
- "count": 18192,
183
- "self": 0.41437885697223464,
184
  "children": {
185
  "env_step": {
186
- "total": 313.0500756400004,
187
- "count": 18192,
188
- "self": 238.836308489987,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 73.98206785300044,
192
- "count": 18192,
193
- "self": 1.3151810179917902,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 72.66688683500865,
197
- "count": 18192,
198
- "self": 72.66688683500865
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.23169929701293768,
204
- "count": 18192,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 440.22789513798966,
209
- "count": 18192,
210
  "is_parallel": true,
211
- "self": 231.39362931498817,
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": 0.00217295000015838,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.0006859820002773631,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.001486967999881017,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.001486967999881017
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.039462678999825584,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0007359619996805122,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.00037742200015600247,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.00037742200015600247
244
  },
245
  "communicator.exchange": {
246
- "total": 0.036360305000016524,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.036360305000016524
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0019889899999725458,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.00036312499992163794,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0016258650000509078,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0016258650000509078
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 208.8342658230015,
271
- "count": 18191,
272
  "is_parallel": true,
273
- "self": 10.211585903037076,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 5.588718342992706,
277
- "count": 18191,
278
  "is_parallel": true,
279
- "self": 5.588718342992706
280
  },
281
  "communicator.exchange": {
282
- "total": 160.19006862798574,
283
- "count": 18191,
284
  "is_parallel": true,
285
- "self": 160.19006862798574
286
  },
287
  "steps_from_proto": {
288
- "total": 32.84389294898597,
289
- "count": 18191,
290
  "is_parallel": true,
291
- "self": 6.05930704400248,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 26.784585904983487,
295
- "count": 181910,
296
  "is_parallel": true,
297
- "self": 26.784585904983487
298
  }
299
  }
300
  }
@@ -307,31 +307,31 @@
307
  }
308
  },
309
  "trainer_advance": {
310
- "total": 126.01851144601915,
311
- "count": 18192,
312
- "self": 0.47961246900968035,
313
  "children": {
314
  "process_trajectory": {
315
- "total": 28.622726011009945,
316
- "count": 18192,
317
- "self": 28.154369539010077,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
- "total": 0.4683564719998685,
321
- "count": 4,
322
- "self": 0.4683564719998685
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
- "total": 96.91617296599952,
328
- "count": 90,
329
- "self": 39.348050224004055,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
- "total": 57.56812274199547,
333
- "count": 4587,
334
- "self": 57.56812274199547
335
  }
336
  }
337
  }
@@ -340,19 +340,19 @@
340
  }
341
  },
342
  "trainer_threads": {
343
- "total": 1.4140000530460384e-06,
344
  "count": 1,
345
- "self": 1.4140000530460384e-06
346
  },
347
  "TrainerController._save_models": {
348
- "total": 0.10018885199997385,
349
  "count": 1,
350
- "self": 0.0011800769998444594,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
- "total": 0.09900877500012939,
354
  "count": 1,
355
- "self": 0.09900877500012939
356
  }
357
  }
358
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.601077139377594,
6
+ "min": 0.5837947726249695,
7
+ "max": 0.9881709814071655,
8
+ "count": 80
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 5712.63720703125,
12
+ "min": 5643.8955078125,
13
+ "max": 10030.509765625,
14
+ "count": 80
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 999992.0,
18
+ "min": 209936.0,
19
+ "max": 999992.0,
20
+ "count": 80
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 999992.0,
24
+ "min": 209936.0,
25
+ "max": 999992.0,
26
+ "count": 80
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 14.166631698608398,
30
+ "min": 12.94360065460205,
31
+ "max": 14.166631698608398,
32
+ "count": 80
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2762.4931640625,
36
+ "min": 2485.17138671875,
37
+ "max": 2896.8720703125,
38
+ "count": 80
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
+ "value": 0.0720234285188638,
42
+ "min": 0.060970312462635706,
43
+ "max": 0.07712253872637566,
44
+ "count": 80
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
+ "value": 0.2880937140754552,
48
+ "min": 0.24388124985054283,
49
+ "max": 0.369829463961936,
50
+ "count": 80
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
+ "value": 0.17329983738269292,
54
+ "min": 0.14300536825960758,
55
+ "max": 0.23871639186479882,
56
+ "count": 80
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
+ "value": 0.6931993495307717,
60
+ "min": 0.6001153049223563,
61
+ "max": 1.0542938566091014,
62
+ "count": 80
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
65
+ "value": 1.402899532400004e-06,
66
+ "min": 1.402899532400004e-06,
67
+ "max": 0.0002383428205524,
68
+ "count": 80
69
  },
70
  "SnowballTarget.Policy.LearningRate.sum": {
71
+ "value": 5.611598129600016e-06,
72
+ "min": 5.611598129600016e-06,
73
+ "max": 0.001176864107712,
74
+ "count": 80
75
  },
76
  "SnowballTarget.Policy.Epsilon.mean": {
77
+ "value": 0.1004676,
78
+ "min": 0.1004676,
79
+ "max": 0.1794476,
80
+ "count": 80
81
  },
82
  "SnowballTarget.Policy.Epsilon.sum": {
83
+ "value": 0.4018704,
84
+ "min": 0.4018704,
85
+ "max": 0.892288,
86
+ "count": 80
87
  },
88
  "SnowballTarget.Policy.Beta.mean": {
89
+ "value": 3.3333240000000065e-05,
90
+ "min": 3.3333240000000065e-05,
91
+ "max": 0.00397443524,
92
+ "count": 80
93
  },
94
  "SnowballTarget.Policy.Beta.sum": {
95
+ "value": 0.00013333296000000026,
96
+ "min": 0.00013333296000000026,
97
+ "max": 0.0196251712,
98
+ "count": 80
99
  },
100
  "SnowballTarget.Environment.EpisodeLength.mean": {
101
  "value": 199.0,
102
  "min": 199.0,
103
  "max": 199.0,
104
+ "count": 80
105
  },
106
  "SnowballTarget.Environment.EpisodeLength.sum": {
107
  "value": 8756.0,
108
  "min": 8756.0,
109
  "max": 10945.0,
110
+ "count": 80
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 27.545454545454547,
114
+ "min": 25.163636363636364,
115
+ "max": 27.854545454545455,
116
+ "count": 80
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1212.0,
120
+ "min": 1116.0,
121
+ "max": 1532.0,
122
+ "count": 80
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 27.545454545454547,
126
+ "min": 25.163636363636364,
127
+ "max": 27.854545454545455,
128
+ "count": 80
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1212.0,
132
+ "min": 1116.0,
133
+ "max": 1532.0,
134
+ "count": 80
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
+ "count": 80
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
+ "count": 80
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1730728012",
152
  "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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 --resume",
154
  "mlagents_version": "1.2.0.dev0",
 
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.5.0+cu121",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1730729744"
160
  },
161
+ "total": 1732.12271626,
162
  "count": 1,
163
+ "self": 0.5099708959999134,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.08511985199993433,
167
  "count": 1,
168
+ "self": 0.08511985199993433
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 1731.5276255120002,
172
  "count": 1,
173
+ "self": 1.4218081270296352,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 2.5309698369999296,
177
  "count": 1,
178
+ "self": 2.5309698369999296
179
  },
180
  "TrainerController.advance": {
181
+ "total": 1727.4860122999705,
182
+ "count": 72728,
183
+ "self": 1.4741836119442269,
184
  "children": {
185
  "env_step": {
186
+ "total": 1224.1766177549985,
187
+ "count": 72728,
188
+ "self": 931.4992000770171,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 291.7915417349475,
192
+ "count": 72728,
193
+ "self": 5.0668181610044485,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 286.72472357394304,
197
+ "count": 72728,
198
+ "self": 286.72472357394304
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.8858759430338523,
204
+ "count": 72728,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 1726.5713134429836,
209
+ "count": 72728,
210
  "is_parallel": true,
211
+ "self": 910.7163590749676,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.002908205000039743,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0007877580001149909,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.002120446999924752,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.002120446999924752
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.04131846600012068,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0008152610000706773,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0003790219998336397,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0003790219998336397
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.03820512500010409,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.03820512500010409
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0019190580001122726,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.00044222899987289566,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.001476829000239377,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.001476829000239377
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 815.854954368016,
271
+ "count": 72727,
272
  "is_parallel": true,
273
+ "self": 40.134165063941964,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 21.711173289010503,
277
+ "count": 72727,
278
  "is_parallel": true,
279
+ "self": 21.711173289010503
280
  },
281
  "communicator.exchange": {
282
+ "total": 624.4117628640613,
283
+ "count": 72727,
284
  "is_parallel": true,
285
+ "self": 624.4117628640613
286
  },
287
  "steps_from_proto": {
288
+ "total": 129.59785315100225,
289
+ "count": 72727,
290
  "is_parallel": true,
291
+ "self": 23.52818316418302,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 106.06966998681924,
295
+ "count": 727270,
296
  "is_parallel": true,
297
+ "self": 106.06966998681924
298
  }
299
  }
300
  }
 
307
  }
308
  },
309
  "trainer_advance": {
310
+ "total": 501.83521093302784,
311
+ "count": 72728,
312
+ "self": 1.719571437992272,
313
  "children": {
314
  "process_trajectory": {
315
+ "total": 112.45800108804315,
316
+ "count": 72728,
317
+ "self": 110.7157728100442,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
+ "total": 1.7422282779989473,
321
+ "count": 16,
322
+ "self": 1.7422282779989473
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
+ "total": 387.6576384069924,
328
+ "count": 363,
329
+ "self": 159.84262632701825,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
+ "total": 227.81501207997417,
333
+ "count": 18510,
334
+ "self": 227.81501207997417
335
  }
336
  }
337
  }
 
340
  }
341
  },
342
  "trainer_threads": {
343
+ "total": 9.680002222012263e-07,
344
  "count": 1,
345
+ "self": 9.680002222012263e-07
346
  },
347
  "TrainerController._save_models": {
348
+ "total": 0.0888342799999009,
349
  "count": 1,
350
+ "self": 0.0011844049995488604,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
+ "total": 0.08764987500035204,
354
  "count": 1,
355
+ "self": 0.08764987500035204
356
  }
357
  }
358
  }
run_logs/training_status.json CHANGED
@@ -7,67 +7,103 @@
7
  "SnowballTarget": {
8
  "checkpoints": [
9
  {
10
- "steps": 0,
11
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-0.onnx",
12
- "reward": null,
13
- "creation_time": 1730726958.991576,
14
  "auxillary_file_paths": [
15
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-0.pt"
16
  ]
17
  },
18
  {
19
- "steps": 49936,
20
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
21
- "reward": 14.363636363636363,
22
- "creation_time": 1730727337.7310948,
23
  "auxillary_file_paths": [
24
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
25
  ]
26
  },
27
  {
28
- "steps": 99960,
29
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
30
- "reward": 22.09090909090909,
31
- "creation_time": 1730727448.8917255,
32
  "auxillary_file_paths": [
33
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
34
  ]
35
  },
36
  {
37
- "steps": 149984,
38
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
39
- "reward": 25.181818181818183,
40
- "creation_time": 1730727559.2517269,
41
  "auxillary_file_paths": [
42
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
43
  ]
44
  },
45
  {
46
- "steps": 199984,
47
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
48
- "reward": 25.272727272727273,
49
- "creation_time": 1730727668.482267,
50
  "auxillary_file_paths": [
51
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
52
  ]
53
  },
54
  {
55
- "steps": 200112,
56
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
57
- "reward": 25.272727272727273,
58
- "creation_time": 1730727668.5984137,
59
  "auxillary_file_paths": [
60
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
61
  ]
62
  }
63
  ],
64
  "final_checkpoint": {
65
- "steps": 200112,
66
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
67
- "reward": 25.272727272727273,
68
- "creation_time": 1730727668.5984137,
69
  "auxillary_file_paths": [
70
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
71
  ]
72
  }
73
  }
 
7
  "SnowballTarget": {
8
  "checkpoints": [
9
  {
10
+ "steps": 599976,
11
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-599976.onnx",
12
+ "reward": 27.181818181818183,
13
+ "creation_time": 1730728876.7846673,
14
  "auxillary_file_paths": [
15
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-599976.pt"
16
  ]
17
  },
18
  {
19
+ "steps": 649936,
20
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-649936.onnx",
21
+ "reward": 27.09090909090909,
22
+ "creation_time": 1730728983.7344217,
23
  "auxillary_file_paths": [
24
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-649936.pt"
25
  ]
26
  },
27
  {
28
+ "steps": 699960,
29
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-699960.onnx",
30
+ "reward": 28.181818181818183,
31
+ "creation_time": 1730729089.5967672,
32
  "auxillary_file_paths": [
33
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-699960.pt"
34
  ]
35
  },
36
  {
37
+ "steps": 749960,
38
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-749960.onnx",
39
+ "reward": 27.09090909090909,
40
+ "creation_time": 1730729197.2924042,
41
  "auxillary_file_paths": [
42
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-749960.pt"
43
  ]
44
  },
45
  {
46
+ "steps": 799984,
47
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-799984.onnx",
48
+ "reward": 26.545454545454547,
49
+ "creation_time": 1730729310.9403522,
50
  "auxillary_file_paths": [
51
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-799984.pt"
52
  ]
53
  },
54
  {
55
+ "steps": 849944,
56
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-849944.onnx",
57
+ "reward": 27.363636363636363,
58
+ "creation_time": 1730729419.6657178,
59
  "auxillary_file_paths": [
60
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-849944.pt"
61
+ ]
62
+ },
63
+ {
64
+ "steps": 899968,
65
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-899968.onnx",
66
+ "reward": 27.545454545454547,
67
+ "creation_time": 1730729528.0058172,
68
+ "auxillary_file_paths": [
69
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-899968.pt"
70
+ ]
71
+ },
72
+ {
73
+ "steps": 949968,
74
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-949968.onnx",
75
+ "reward": 27.545454545454547,
76
+ "creation_time": 1730729635.525651,
77
+ "auxillary_file_paths": [
78
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-949968.pt"
79
+ ]
80
+ },
81
+ {
82
+ "steps": 999992,
83
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-999992.onnx",
84
+ "reward": 26.818181818181817,
85
+ "creation_time": 1730729744.0084317,
86
+ "auxillary_file_paths": [
87
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-999992.pt"
88
+ ]
89
+ },
90
+ {
91
+ "steps": 1000120,
92
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1000120.onnx",
93
+ "reward": 26.818181818181817,
94
+ "creation_time": 1730729744.1085699,
95
+ "auxillary_file_paths": [
96
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-1000120.pt"
97
  ]
98
  }
99
  ],
100
  "final_checkpoint": {
101
+ "steps": 1000120,
102
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
103
+ "reward": 26.818181818181817,
104
+ "creation_time": 1730729744.1085699,
105
  "auxillary_file_paths": [
106
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-1000120.pt"
107
  ]
108
  }
109
  }