Hugging Face's logo

feysahin
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
 Metrics Community
feysahin commited on
Commit
3b33bb7
·
verified ·
1 Parent(s): e596150

32-batchsize

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-49968.onnx +3 -0
  9. SnowballTarget/SnowballTarget-49968.pt +3 -0
  10. SnowballTarget/SnowballTarget-99992.onnx +3 -0
  11. SnowballTarget/SnowballTarget-99992.pt +3 -0
  12. SnowballTarget/checkpoint.pt +1 -1
  13. SnowballTarget/events.out.tfevents.1717234093.94b086f696dc.13359.0 +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 +125 -125
  18. run_logs/training_status.json +26 -26
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:36708457d1f0fbf5da3c64567005a700e649aa5e1f4dbc482d53ef238b9a4542
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f188d034d0921691e8112cc4e232946b5fd090933cd03b030bb2973d0d671ff9
3
  size 650646
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:66bf1783d6e3d8d8d2247666c75d3ee17943338b6197507d19017b0f2e8b13a0
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:961a30d1f8ffd9a5b663dbd60d319826cc46f2f3f938fc107868c63e2363226f
3
  size 650646
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:74eacce87c141e496974c9f44d622613bc3cf11a6e749df2d3bde3bbb0d51f22
3
  size 3850075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70d89ee98a7a995c06955ae3a29903c1ae992ca7405a7fe68328f3fc5f2b80d4
3
  size 3850075
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:36708457d1f0fbf5da3c64567005a700e649aa5e1f4dbc482d53ef238b9a4542
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f188d034d0921691e8112cc4e232946b5fd090933cd03b030bb2973d0d671ff9
3
  size 650646
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c6a75e6bfbdf2932a9f81a9f5e8edde114fa25baa6f73eb03efe73fc29eca733
3
  size 3850075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8bdd3b603e95fc272f9ee94cd2b18ef9d8e5560746d5344d692d41ab6719df0
3
  size 3850075
SnowballTarget/SnowballTarget-200112.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:36708457d1f0fbf5da3c64567005a700e649aa5e1f4dbc482d53ef238b9a4542
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f188d034d0921691e8112cc4e232946b5fd090933cd03b030bb2973d0d671ff9
3
  size 650646
SnowballTarget/SnowballTarget-200112.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e7981bcfc1e5a8f089e4efc0637258dd109ee54537e32206ecb8d84eb6afd90
3
  size 3850075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77c842bc4bd48f3dd7aa36b7079691c5f6b600aeb69681510f14d7bf7135c7bf
3
  size 3850075
SnowballTarget/SnowballTarget-49968.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68f14900b8e9a8dd91fdfbb9152f639e28e8e53949953145ab7193c8c6f2814c
3
+ size 650646
SnowballTarget/SnowballTarget-49968.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9eae1c391cbd53ab482bd146304f4f0c46f57ebe67a2def0883009ffee1b4444
3
+ size 3850000
SnowballTarget/SnowballTarget-99992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92ccb497f9ed5b1805dcf1bf183b924b482ab898e70e705a16b9e36a34dc2cd4
3
+ size 650646
SnowballTarget/SnowballTarget-99992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bed1d2780fe969bf537b92bc4722d964e76b427335e47bc7811c5537af45582
3
+ size 3850000
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9aecb38cf1debd590a07117bb504036aab3789f126c5720b06a3c86bcdcdcfc
3
  size 3849250
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d55d479beb347c88d2fb0ed339d4905109dfca5221f14e186d7afceac11b729a
3
  size 3849250
SnowballTarget/events.out.tfevents.1717234093.94b086f696dc.13359.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ecb09ba347bf16bbd94d3bbb01f91530690f3a3f86c1e73584e5c0d74a26771
3
+ size 23249
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": 64, "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": 32, "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
@@ -3,7 +3,7 @@ behaviors:
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
@@ -39,7 +39,7 @@ behaviors:
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
  max_steps: 200000
42
- time_horizon: 64
43
  summary_freq: 10000
44
  threaded: true
45
  self_play: null
@@ -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
 
3
  SnowballTarget:
4
  trainer_type: ppo
5
  hyperparameters:
6
+ batch_size: 64
7
  buffer_size: 2048
8
  learning_rate: 0.0003
9
  beta: 0.005
 
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
  max_steps: 200000
42
+ time_horizon: 32
43
  summary_freq: 10000
44
  threaded: true
45
  self_play: null
 
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: 0.731455 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]: 5370 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 38
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]: 5462 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
- Peak Allocated memory 6.9 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
- Peak usage frame count: [16.0 MB-32.0 MB]: 5462 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
- Peak Allocated memory 17.6 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]: 3934 frames, [64.0 KB-128.0 KB]: 1528 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
- Peak Allocated memory 66.8 KB
220
  Peak Large allocation bytes 0 B
221
  [ALLOC_GFX_THREAD]
222
- Peak usage frame count: [32.0 KB-64.0 KB]: 5462 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]: 5462 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]: 5461 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]: 5462 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]: 5462 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 0.086 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: 0.662950 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]: 5368 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]: 5460 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]: 5460 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]: 5124 frames, [64.0 KB-128.0 KB]: 336 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
+ Peak Allocated memory 66.3 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
+ Peak usage frame count: [32.0 KB-64.0 KB]: 5460 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]: 5460 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]: 5459 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]: 5460 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]: 5460 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
@@ -2,39 +2,39 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 1.07244873046875,
6
- "min": 1.07244873046875,
7
- "max": 2.8645427227020264,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 10239.740234375,
12
- "min": 10239.740234375,
13
- "max": 29335.78125,
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": 12.17463207244873,
30
- "min": 0.3278978168964386,
31
- "max": 12.17463207244873,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2374.05322265625,
36
- "min": 63.612178802490234,
37
- "max": 2451.98876953125,
38
  "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
@@ -50,87 +50,87 @@
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
- "value": 0.07091637908781515,
54
- "min": 0.062193297305687636,
55
- "max": 0.07754508002803692,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.2836655163512606,
60
- "min": 0.24877318922275055,
61
- "max": 0.36851019851233374,
62
  "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.22349769936180583,
66
- "min": 0.11979061460428342,
67
- "max": 0.2911507780061049,
68
  "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.8939907974472233,
72
- "min": 0.4791624584171337,
73
- "max": 1.4557538900305245,
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": 23.818181818181817,
114
- "min": 3.1818181818181817,
115
- "max": 23.818181818181817,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1048.0,
120
- "min": 140.0,
121
- "max": 1292.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 23.818181818181817,
126
- "min": 3.1818181818181817,
127
- "max": 23.818181818181817,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1048.0,
132
- "min": 140.0,
133
- "max": 1292.0,
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": "1717231800",
152
  "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.3.0+cu121",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1717232256"
160
  },
161
- "total": 455.61271882999995,
162
  "count": 1,
163
- "self": 0.7898104119999516,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.06150707200004035,
167
  "count": 1,
168
- "self": 0.06150707200004035
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 454.76140134599996,
172
  "count": 1,
173
- "self": 0.6055867879831567,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 3.0354525019999983,
177
  "count": 1,
178
- "self": 3.0354525019999983
179
  },
180
  "TrainerController.advance": {
181
- "total": 450.9890701690167,
182
- "count": 18206,
183
- "self": 0.3043024290146832,
184
  "children": {
185
  "env_step": {
186
- "total": 450.68476774000203,
187
- "count": 18206,
188
- "self": 294.0798735890129,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 156.3018288999882,
192
- "count": 18206,
193
- "self": 1.5056017579738636,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 154.79622714201435,
197
- "count": 18206,
198
- "self": 154.79622714201435
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.3030652510009304,
204
- "count": 18206,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 453.53385827200395,
209
- "count": 18206,
210
  "is_parallel": true,
211
- "self": 227.49165350400256,
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": 0.006099903000063023,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.004118176999895695,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0019817260001673276,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0019817260001673276
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.04958722100002433,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0006783909999512616,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.0003986830000712871,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.0003986830000712871
244
  },
245
  "communicator.exchange": {
246
- "total": 0.04650474599998233,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.04650474599998233
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0020054010000194467,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.00038618199982920487,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0016192190001902418,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0016192190001902418
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 226.0422047680014,
271
- "count": 18205,
272
  "is_parallel": true,
273
- "self": 10.33606383599124,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 5.295276873996272,
277
- "count": 18205,
278
  "is_parallel": true,
279
- "self": 5.295276873996272
280
  },
281
  "communicator.exchange": {
282
- "total": 177.33526870000082,
283
- "count": 18205,
284
  "is_parallel": true,
285
- "self": 177.33526870000082
286
  },
287
  "steps_from_proto": {
288
- "total": 33.07559535801306,
289
- "count": 18205,
290
  "is_parallel": true,
291
- "self": 6.224162872039983,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 26.851432485973078,
295
- "count": 182050,
296
  "is_parallel": true,
297
- "self": 26.851432485973078
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 0.00014276399997470435,
313
  "count": 1,
314
- "self": 0.00014276399997470435,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,36 +320,36 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 445.5943874239572,
324
- "count": 670412,
325
  "is_parallel": true,
326
- "self": 13.866130806961792,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 247.241100587995,
330
- "count": 670412,
331
  "is_parallel": true,
332
- "self": 246.36349901599488,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
- "total": 0.8776015720001169,
336
  "count": 4,
337
  "is_parallel": true,
338
- "self": 0.8776015720001169
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
- "total": 184.4871560290004,
344
  "count": 90,
345
  "is_parallel": true,
346
- "self": 57.58180979398958,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
- "total": 126.90534623501082,
350
- "count": 4587,
351
  "is_parallel": true,
352
- "self": 126.90534623501082
353
  }
354
  }
355
  }
@@ -360,14 +360,14 @@
360
  }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.13114912300011383,
364
  "count": 1,
365
- "self": 0.001118724000207294,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.13003039899990654,
369
  "count": 1,
370
- "self": 0.13003039899990654
371
  }
372
  }
373
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.9838725328445435,
6
+ "min": 0.965241551399231,
7
+ "max": 2.866785764694214,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 9729.515625,
12
+ "min": 9625.013671875,
13
+ "max": 29295.68359375,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
17
  "value": 199984.0,
18
+ "min": 9984.0,
19
  "max": 199984.0,
20
  "count": 20
21
  },
22
  "SnowballTarget.Step.sum": {
23
  "value": 199984.0,
24
+ "min": 9984.0,
25
  "max": 199984.0,
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 13.067357063293457,
30
+ "min": 0.30062130093574524,
31
+ "max": 13.067357063293457,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 4521.3056640625,
36
+ "min": 103.71434783935547,
37
+ "max": 4587.3818359375,
38
  "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
 
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.09833402143611274,
54
+ "min": 0.08959242349465414,
55
+ "max": 0.10495804121142012,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.39333608574445095,
60
+ "min": 0.3649836925311213,
61
+ "max": 0.5207478383452543,
62
  "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.175560578356917,
66
+ "min": 0.11516721773476507,
67
+ "max": 0.23881364748904518,
68
  "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.702242313427668,
72
+ "min": 0.4606688709390603,
73
+ "max": 1.1811038187029315,
74
  "count": 20
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
+ "value": 8.082097306000007e-06,
78
+ "min": 8.082097306000007e-06,
79
  "max": 0.000291882002706,
80
  "count": 20
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
+ "value": 3.232838922400003e-05,
84
+ "min": 3.232838922400003e-05,
85
  "max": 0.00138516003828,
86
  "count": 20
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
+ "value": 0.10269399999999997,
90
+ "min": 0.10269399999999997,
91
  "max": 0.19729400000000002,
92
  "count": 20
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
+ "value": 0.41077599999999986,
96
+ "min": 0.41077599999999986,
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": {
107
  "value": 0.0005777224000000004,
108
  "min": 0.0005777224000000004,
109
+ "max": 0.023089828000000003,
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 25.84090909090909,
114
+ "min": 3.75,
115
+ "max": 26.0,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1137.0,
120
+ "min": 165.0,
121
+ "max": 1430.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 25.84090909090909,
126
+ "min": 3.75,
127
+ "max": 26.0,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1137.0,
132
+ "min": 165.0,
133
+ "max": 1430.0,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
 
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1717234092",
152
  "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.3.0+cu121",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1717234604"
160
  },
161
+ "total": 512.127364681,
162
  "count": 1,
163
+ "self": 0.4260075149995828,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.05430630900036704,
167
  "count": 1,
168
+ "self": 0.05430630900036704
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 511.64705085700007,
172
  "count": 1,
173
+ "self": 0.619859824996638,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 2.5237525529996674,
177
  "count": 1,
178
+ "self": 2.5237525529996674
179
  },
180
  "TrainerController.advance": {
181
+ "total": 508.4140232240038,
182
+ "count": 18200,
183
+ "self": 0.28823994402273456,
184
  "children": {
185
  "env_step": {
186
+ "total": 508.1257832799811,
187
+ "count": 18200,
188
+ "self": 373.0337538399799,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 134.7856456429663,
192
+ "count": 18200,
193
+ "self": 1.7443572609772673,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 133.04128838198903,
197
+ "count": 18200,
198
+ "self": 133.04128838198903
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.3063837970348686,
204
+ "count": 18200,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 510.2053330989693,
209
+ "count": 18200,
210
  "is_parallel": true,
211
+ "self": 283.7239173809576,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.0022093829998084402,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.000627141000222764,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0015822419995856762,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0015822419995856762
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.07990689799999018,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0006111320003583387,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0003600850000111677,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0003600850000111677
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.07718432899991967,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.07718432899991967
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0017513519997010008,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.00033043599978554994,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0014209159999154508,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0014209159999154508
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 226.4814157180117,
271
+ "count": 18199,
272
  "is_parallel": true,
273
+ "self": 10.214919567026755,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 5.34711932500295,
277
+ "count": 18199,
278
  "is_parallel": true,
279
+ "self": 5.34711932500295
280
  },
281
  "communicator.exchange": {
282
+ "total": 177.7891860109803,
283
+ "count": 18199,
284
  "is_parallel": true,
285
+ "self": 177.7891860109803
286
  },
287
  "steps_from_proto": {
288
+ "total": 33.1301908150017,
289
+ "count": 18199,
290
  "is_parallel": true,
291
+ "self": 6.313989595913881,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 26.816201219087816,
295
+ "count": 181990,
296
  "is_parallel": true,
297
+ "self": 26.816201219087816
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 0.00018463100013832445,
313
  "count": 1,
314
+ "self": 0.00018463100013832445,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 501.67785952741633,
324
+ "count": 804214,
325
  "is_parallel": true,
326
+ "self": 16.4597098723998,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 300.43437867401826,
330
+ "count": 804214,
331
  "is_parallel": true,
332
+ "self": 299.6356772560184,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
+ "total": 0.7987014179998368,
336
  "count": 4,
337
  "is_parallel": true,
338
+ "self": 0.7987014179998368
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
+ "total": 184.78377098099827,
344
  "count": 90,
345
  "is_parallel": true,
346
+ "self": 51.24470552498542,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 133.53906545601285,
350
+ "count": 9177,
351
  "is_parallel": true,
352
+ "self": 133.53906545601285
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.08923062399981063,
364
  "count": 1,
365
+ "self": 0.00097448099995745,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.08825614299985318,
369
  "count": 1,
370
+ "self": 0.08825614299985318
371
  }
372
  }
373
  }
run_logs/training_status.json CHANGED
@@ -2,58 +2,58 @@
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
- "steps": 49936,
6
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 12.0,
8
- "creation_time": 1717231920.674545,
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": 20.09090909090909,
17
- "creation_time": 1717232033.7092426,
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": 23.272727272727273,
26
- "creation_time": 1717232145.7095153,
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": 23.454545454545453,
35
- "creation_time": 1717232255.528378,
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": 23.454545454545453,
44
- "creation_time": 1717232255.706235,
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": 23.454545454545453,
54
- "creation_time": 1717232255.706235,
55
  "auxillary_file_paths": [
56
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },
 
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
+ "steps": 49968,
6
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-49968.onnx",
7
+ "reward": 15.545454545454545,
8
+ "creation_time": 1717234224.4865446,
9
  "auxillary_file_paths": [
10
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-49968.pt"
11
  ]
12
  },
13
  {
14
+ "steps": 99992,
15
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-99992.onnx",
16
+ "reward": 23.181818181818183,
17
+ "creation_time": 1717234350.5836809,
18
  "auxillary_file_paths": [
19
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-99992.pt"
20
  ]
21
  },
22
  {
23
  "steps": 149984,
24
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.onnx",
25
+ "reward": 26.818181818181817,
26
+ "creation_time": 1717234478.811437,
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": 25.818181818181817,
35
+ "creation_time": 1717234604.2709239,
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": 25.818181818181817,
44
+ "creation_time": 1717234604.386032,
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": 25.818181818181817,
54
+ "creation_time": 1717234604.386032,
55
  "auxillary_file_paths": [
56
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },