KacBo commited on
Commit
67e5dae
·
verified ·
1 Parent(s): e6823c5

second Push

Browse files
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e5c5711a455ffeeea1eab11fb7a6db28889e32f66a09eaceae6a8acac795aa11
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d023740bfe7b77f4b88afb0510d123770e862564d1f0663c82227a2414949460
3
  size 650646
SnowballTarget/SnowballTarget-1599976.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91eb412ee72a02f1919d87dfc8f8a082a6e3f4497d399ec59493b0c1e933e6d6
3
+ size 650646
SnowballTarget/SnowballTarget-1599976.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76014e3872ff808745bcf7850b427c5658b44d627c2cb3d32858190111989aeb
3
+ size 3850041
SnowballTarget/SnowballTarget-1649992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d9edd73d257b49de777abadfc6ca728c21d7333ee8b2c2a43ce0e66bd327a16
3
+ size 650646
SnowballTarget/SnowballTarget-1649992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ec1765b2963ca16091bc8cca83ed76a0bf0cc16d35b2ddfe06d289ee2b53a58
3
+ size 3850041
SnowballTarget/SnowballTarget-1699936.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a524e21a39e0741e6328359f101d36dd00a86c28084bc80528fa4819f85fb8c
3
+ size 650646
SnowballTarget/SnowballTarget-1699936.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8e89b2bf8c5b4ececc8ebfe3e60622900dc073b940be3cc617b0249c99911ad
3
+ size 3850041
SnowballTarget/SnowballTarget-1749960.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:600ed0b11c7ef531b05bccc9019f1eae6cc0fb9a03b2a83dccd5b265fb22ff31
3
+ size 650646
SnowballTarget/SnowballTarget-1749960.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:173a14ee04bfab05c114de50ea361efb55cc586d9df715da276d25bcb44f5a2e
3
+ size 3850041
SnowballTarget/SnowballTarget-1799984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51e165f25c164b7431e671b56f5e2c863981d8f5f744c8d97da88b6f516441ca
3
+ size 650646
SnowballTarget/SnowballTarget-1799984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa1c0703af8e29093637335d60f437097042f18653783af1afc9581d2c4d144a
3
+ size 3850041
SnowballTarget/SnowballTarget-1849984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a2f588e05ee8fa316030fb5ec28f362db1df300d5ca1b1d602b97bfa7075f57
3
+ size 650646
SnowballTarget/SnowballTarget-1849984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:558f84e7cd0c84bd3b19115de477e04968d613981fcf28d9109b0ae49de34eff
3
+ size 3850041
SnowballTarget/SnowballTarget-1899944.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6550bfe85d431353f3783bfb7558b24dfea5b839338a498252d170ebc372a4a9
3
+ size 650646
SnowballTarget/SnowballTarget-1899944.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f498002e9787f5f8b2cc454735986c8675e673d6c6a160d04af6dbafee6f27e
3
+ size 3850041
SnowballTarget/SnowballTarget-1949968.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44eba98dc8676f7dff22809ce7c0128e58faafdf991b7b3a896acd5eda891431
3
+ size 650646
SnowballTarget/SnowballTarget-1949968.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9acd2cbc9e0ba5ff1a66770ce9200cc33e5bfe42d82995f6e483ef5e17259ba5
3
+ size 3850041
SnowballTarget/SnowballTarget-1999992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d023740bfe7b77f4b88afb0510d123770e862564d1f0663c82227a2414949460
3
+ size 650646
SnowballTarget/SnowballTarget-1999992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a90a9f850fce09dfb7d0b2d196214144780517746d570e1794a19763dfa3efd2
3
+ size 3850041
SnowballTarget/SnowballTarget-2000504.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d023740bfe7b77f4b88afb0510d123770e862564d1f0663c82227a2414949460
3
+ size 650646
SnowballTarget/SnowballTarget-2000504.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df5d7fea6809c33bbf7e3159cbcebc758c018758001a5166019aa5550faa5044
3
+ size 3850041
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:68c111e98e385713c9191ef9a91893b3a27d330969d9a5c530bdfccb65707415
3
  size 3849077
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a41fefc638a28597ddbf131645489436a30533422edeaa18f3193fd24a1f5134
3
  size 3849077
SnowballTarget/events.out.tfevents.1770593468.ea52937bc0e2.13572.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:123dba714a85e5a3fd371cfd46a2a3a6f5215086dee7f5e5024f8a67dcfa6854
3
+ size 170228
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": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
 
1
+ {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 2000000, "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": "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
@@ -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
@@ -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
 
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
+ max_steps: 2000000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: false
 
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/training-envs-executables/linux/SnowballTarget/Snowball
2
  Mono config path = '/content/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/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
10
  Forcing GfxDevice: Null
@@ -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: 0.693415 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]: 5367 frames, [16.0 KB-32.0 KB]: 90 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 36
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]: 5458 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]: 5458 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
- Peak Allocated memory 17.5 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]: 5126 frames, [64.0 KB-128.0 KB]: 332 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
- Peak Allocated memory 66.4 KB
220
  Peak Large allocation bytes 0 B
221
  [ALLOC_GFX_THREAD]
222
- Peak usage frame count: [32.0 KB-64.0 KB]: 5458 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]: 5458 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]: 5457 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]: 5458 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]: 5458 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/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/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
7
  Forcing GfxDevice: Null
 
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: 0.652816 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]: 53650 frames, [16.0 KB-32.0 KB]: 909 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 48
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]: 10477 frames, [8.0 MB-16.0 MB]: 27110 frames, [16.0 MB-32.0 MB]: 16973 frames
176
  Requested Block Size 16.0 MB
177
+ Peak Block count 2
178
+ Peak Allocated memory 24.8 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 54560 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
+ Peak Allocated memory 17.2 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]: 52889 frames, [64.0 KB-128.0 KB]: 1671 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
+ Peak Allocated memory 67.3 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
+ Peak usage frame count: [32.0 KB-64.0 KB]: 54560 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]: 54560 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]: 54559 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]: 54560 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]: 54560 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
@@ -2,213 +2,213 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 0.8550259470939636,
6
- "min": 0.8133524656295776,
7
- "max": 2.8720791339874268,
8
- "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 8126.16650390625,
12
- "min": 7801.6767578125,
13
- "max": 29318.18359375,
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": 12.782927513122559,
30
- "min": 0.3263982832431793,
31
- "max": 12.782927513122559,
32
- "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2492.6708984375,
36
- "min": 63.321266174316406,
37
- "max": 2590.16455078125,
38
- "count": 20
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
- "value": 0.06970330293167054,
42
- "min": 0.06550141833009263,
43
- "max": 0.074469765673355,
44
- "count": 20
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
- "value": 0.27881321172668216,
48
- "min": 0.2633021368311864,
49
- "max": 0.3597980855876242,
50
- "count": 20
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
- "value": 0.20233449518826663,
54
- "min": 0.09487491577416293,
55
- "max": 0.31499941828204137,
56
- "count": 20
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
- "value": 0.8093379807530665,
60
- "min": 0.37949966309665173,
61
- "max": 1.5749970914102067,
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": 25.068181818181817,
114
- "min": 2.909090909090909,
115
- "max": 25.568181818181817,
116
- "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1103.0,
120
- "min": 128.0,
121
- "max": 1396.0,
122
- "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 25.068181818181817,
126
- "min": 2.909090909090909,
127
- "max": 25.568181818181817,
128
- "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1103.0,
132
- "min": 128.0,
133
- "max": 1396.0,
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": "1770591137",
152
  "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]",
153
- "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
154
  "mlagents_version": "1.2.0.dev0",
155
  "mlagents_envs_version": "1.2.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.8.0+cu128",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1770591591"
160
  },
161
- "total": 454.594464132,
162
  "count": 1,
163
- "self": 0.4306487889998607,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.025071598000067752,
167
  "count": 1,
168
- "self": 0.025071598000067752
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 454.13874374500006,
172
  "count": 1,
173
- "self": 0.4349820710037875,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 3.0731741060000104,
177
  "count": 1,
178
- "self": 3.0731741060000104
179
  },
180
  "TrainerController.advance": {
181
- "total": 450.5506597789962,
182
- "count": 18192,
183
- "self": 0.44403236199980256,
184
  "children": {
185
  "env_step": {
186
- "total": 330.2141421119974,
187
- "count": 18192,
188
- "self": 256.753843844989,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 73.21045396701481,
192
- "count": 18192,
193
- "self": 1.350321971004405,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 71.86013199601041,
197
- "count": 18192,
198
- "self": 71.86013199601041
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.24984429999358326,
204
- "count": 18192,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 452.39253704300097,
209
- "count": 18192,
210
  "is_parallel": true,
211
- "self": 227.8513776469997,
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": 0.005380066000043371,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.003664567999862811,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0017154980001805598,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0017154980001805598
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.03655387200001314,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0005642739999984769,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.0003897689999803333,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.0003897689999803333
244
  },
245
  "communicator.exchange": {
246
- "total": 0.03370864300006815,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.03370864300006815
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0018911859999661829,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.00036901800012856256,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0015221679998376203,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0015221679998376203
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 224.54115939600126,
271
- "count": 18191,
272
  "is_parallel": true,
273
- "self": 10.287022656023396,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 5.559260232997872,
277
- "count": 18191,
278
  "is_parallel": true,
279
- "self": 5.559260232997872
280
  },
281
  "communicator.exchange": {
282
- "total": 171.48726647998205,
283
- "count": 18191,
284
  "is_parallel": true,
285
- "self": 171.48726647998205
286
  },
287
  "steps_from_proto": {
288
- "total": 37.20761002699794,
289
- "count": 18191,
290
  "is_parallel": true,
291
- "self": 6.882537870990518,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 30.325072156007423,
295
- "count": 181910,
296
  "is_parallel": true,
297
- "self": 30.325072156007423
298
  }
299
  }
300
  }
@@ -307,31 +307,31 @@
307
  }
308
  },
309
  "trainer_advance": {
310
- "total": 119.89248530499901,
311
- "count": 18192,
312
- "self": 0.552551636992689,
313
  "children": {
314
  "process_trajectory": {
315
- "total": 26.337594581005874,
316
- "count": 18192,
317
- "self": 25.906713586005935,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
- "total": 0.4308809949999386,
321
- "count": 4,
322
- "self": 0.4308809949999386
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
- "total": 93.00233908700045,
328
- "count": 90,
329
- "self": 37.82933866900703,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
- "total": 55.17300041799342,
333
- "count": 4587,
334
- "self": 55.17300041799342
335
  }
336
  }
337
  }
@@ -340,19 +340,19 @@
340
  }
341
  },
342
  "trainer_threads": {
343
- "total": 9.510001746093621e-07,
344
  "count": 1,
345
- "self": 9.510001746093621e-07
346
  },
347
  "TrainerController._save_models": {
348
- "total": 0.07992683799989209,
349
  "count": 1,
350
- "self": 0.0007949009998355905,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
- "total": 0.0791319370000565,
354
  "count": 1,
355
- "self": 0.0791319370000565
356
  }
357
  }
358
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.4640839695930481,
6
+ "min": 0.46335798501968384,
7
+ "max": 2.8744521141052246,
8
+ "count": 200
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 4778.20849609375,
12
+ "min": 4420.2529296875,
13
+ "max": 29342.408203125,
14
+ "count": 200
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 1999992.0,
18
  "min": 9952.0,
19
+ "max": 1999992.0,
20
+ "count": 200
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 1999992.0,
24
  "min": 9952.0,
25
+ "max": 1999992.0,
26
+ "count": 200
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 14.271677017211914,
30
+ "min": 0.40419891476631165,
31
+ "max": 14.420598030090332,
32
+ "count": 200
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2925.69384765625,
36
+ "min": 78.41458892822266,
37
+ "max": 2949.749755859375,
38
+ "count": 200
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
+ "value": 0.06806659528736811,
42
+ "min": 0.05760496456111343,
43
+ "max": 0.07640866107962496,
44
+ "count": 200
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
+ "value": 0.3403329764368405,
48
+ "min": 0.2304198582444537,
49
+ "max": 0.38008534068313904,
50
+ "count": 200
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
+ "value": 0.1701448224046651,
54
+ "min": 0.1142922752518572,
55
+ "max": 0.2989402155081431,
56
+ "count": 200
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
+ "value": 0.8507241120233255,
60
+ "min": 0.4571691010074288,
61
+ "max": 1.4947010775407155,
62
+ "count": 200
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
65
+ "value": 7.032997656000039e-07,
66
+ "min": 7.032997656000039e-07,
67
+ "max": 0.00029918820027059994,
68
+ "count": 200
69
  },
70
  "SnowballTarget.Policy.LearningRate.sum": {
71
+ "value": 3.5164988280000196e-06,
72
+ "min": 3.5164988280000196e-06,
73
+ "max": 0.0014885160038279998,
74
+ "count": 200
75
  },
76
  "SnowballTarget.Policy.Epsilon.mean": {
77
+ "value": 0.10023440000000002,
78
+ "min": 0.10023440000000002,
79
+ "max": 0.1997294,
80
+ "count": 200
81
  },
82
  "SnowballTarget.Policy.Epsilon.sum": {
83
+ "value": 0.5011720000000001,
84
+ "min": 0.4029176,
85
+ "max": 0.996172,
86
+ "count": 200
87
  },
88
  "SnowballTarget.Policy.Beta.mean": {
89
+ "value": 2.1696560000000067e-05,
90
+ "min": 2.1696560000000067e-05,
91
+ "max": 0.004986497059999999,
92
+ "count": 200
93
  },
94
  "SnowballTarget.Policy.Beta.sum": {
95
+ "value": 0.00010848280000000034,
96
+ "min": 0.00010848280000000034,
97
+ "max": 0.024808982800000004,
98
+ "count": 200
99
  },
100
  "SnowballTarget.Environment.EpisodeLength.mean": {
101
  "value": 199.0,
102
  "min": 199.0,
103
  "max": 199.0,
104
+ "count": 200
105
  },
106
  "SnowballTarget.Environment.EpisodeLength.sum": {
107
+ "value": 10945.0,
108
  "min": 8756.0,
109
  "max": 10945.0,
110
+ "count": 200
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 27.345454545454544,
114
+ "min": 3.4318181818181817,
115
+ "max": 28.581818181818182,
116
+ "count": 200
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1504.0,
120
+ "min": 151.0,
121
+ "max": 1572.0,
122
+ "count": 200
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 27.345454545454544,
126
+ "min": 3.4318181818181817,
127
+ "max": 28.581818181818182,
128
+ "count": 200
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1504.0,
132
+ "min": 151.0,
133
+ "max": 1572.0,
134
+ "count": 200
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
+ "count": 200
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
+ "count": 200
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1770593467",
152
  "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]",
153
+ "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --no-graphics",
154
  "mlagents_version": "1.2.0.dev0",
155
  "mlagents_envs_version": "1.2.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.8.0+cu128",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1770597861"
160
  },
161
+ "total": 4394.018748836999,
162
  "count": 1,
163
+ "self": 0.47660773399820755,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.029923408000286145,
167
  "count": 1,
168
+ "self": 0.029923408000286145
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 4393.512217695001,
172
  "count": 1,
173
+ "self": 3.7676694411093195,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 1.7913107260001198,
177
  "count": 1,
178
+ "self": 1.7913107260001198
179
  },
180
  "TrainerController.advance": {
181
+ "total": 4387.869930687892,
182
+ "count": 181864,
183
+ "self": 3.950413664205371,
184
  "children": {
185
  "env_step": {
186
+ "total": 3192.8163815699327,
187
+ "count": 181864,
188
+ "self": 2491.976419407858,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 698.536891151999,
192
+ "count": 181864,
193
+ "self": 12.877168777048155,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 685.6597223749509,
197
+ "count": 181864,
198
+ "self": 685.6597223749509
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 2.303071010075655,
204
+ "count": 181864,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 4378.054228119862,
209
+ "count": 181864,
210
  "is_parallel": true,
211
+ "self": 2193.0227901438525,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.0021330879999368335,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.000690076999944722,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0014430109999921115,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0014430109999921115
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.035167684000043664,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0005844800002705597,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0004027129998576129,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0004027129998576129
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.03236229899994214,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.03236229899994214
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.001818191999973351,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.00035864699975718395,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.001459545000216167,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.001459545000216167
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 2185.03143797601,
271
+ "count": 181863,
272
  "is_parallel": true,
273
+ "self": 101.07277186692863,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 54.456352131190215,
277
+ "count": 181863,
278
  "is_parallel": true,
279
+ "self": 54.456352131190215
280
  },
281
  "communicator.exchange": {
282
+ "total": 1666.2199322010697,
283
+ "count": 181863,
284
  "is_parallel": true,
285
+ "self": 1666.2199322010697
286
  },
287
  "steps_from_proto": {
288
+ "total": 363.28238177682124,
289
+ "count": 181863,
290
  "is_parallel": true,
291
+ "self": 67.3950197194572,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 295.88736205736404,
295
+ "count": 1818630,
296
  "is_parallel": true,
297
+ "self": 295.88736205736404
298
  }
299
  }
300
  }
 
307
  }
308
  },
309
  "trainer_advance": {
310
+ "total": 1191.1031354537536,
311
+ "count": 181864,
312
+ "self": 4.616626632641783,
313
  "children": {
314
  "process_trajectory": {
315
+ "total": 259.5865856991172,
316
+ "count": 181864,
317
+ "self": 256.1810363451191,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
+ "total": 3.40554935399814,
321
+ "count": 40,
322
+ "self": 3.40554935399814
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
+ "total": 926.8999231219946,
328
+ "count": 909,
329
+ "self": 378.49098049994836,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
+ "total": 548.4089426220462,
333
+ "count": 46356,
334
+ "self": 548.4089426220462
335
  }
336
  }
337
  }
 
340
  }
341
  },
342
  "trainer_threads": {
343
+ "total": 1.0670000847312622e-06,
344
  "count": 1,
345
+ "self": 1.0670000847312622e-06
346
  },
347
  "TrainerController._save_models": {
348
+ "total": 0.08330577299966535,
349
  "count": 1,
350
+ "self": 0.0007299330000023474,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
+ "total": 0.082575839999663,
354
  "count": 1,
355
+ "self": 0.082575839999663
356
  }
357
  }
358
  }
run_logs/training_status.json CHANGED
@@ -2,58 +2,103 @@
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
- "steps": 49936,
6
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 12.636363636363637,
8
- "creation_time": 1770591252.245259,
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": 23.09090909090909,
17
- "creation_time": 1770591364.807654,
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": 25.545454545454547,
26
- "creation_time": 1770591478.642622,
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": 26.09090909090909,
35
- "creation_time": 1770591591.1298006,
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": 26.09090909090909,
44
- "creation_time": 1770591591.2235126,
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": 26.09090909090909,
54
- "creation_time": 1770591591.2235126,
55
  "auxillary_file_paths": [
56
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },
 
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
+ "steps": 1599976,
6
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1599976.onnx",
7
+ "reward": 27.727272727272727,
8
+ "creation_time": 1770597012.1144395,
9
  "auxillary_file_paths": [
10
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-1599976.pt"
11
  ]
12
  },
13
  {
14
+ "steps": 1649992,
15
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1649992.onnx",
16
+ "reward": 28.3,
17
+ "creation_time": 1770597117.18306,
18
  "auxillary_file_paths": [
19
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-1649992.pt"
20
  ]
21
  },
22
  {
23
+ "steps": 1699936,
24
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1699936.onnx",
25
+ "reward": 28.09090909090909,
26
+ "creation_time": 1770597221.5767782,
27
  "auxillary_file_paths": [
28
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-1699936.pt"
29
  ]
30
  },
31
  {
32
+ "steps": 1749960,
33
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1749960.onnx",
34
+ "reward": 27.90909090909091,
35
+ "creation_time": 1770597326.2940793,
36
  "auxillary_file_paths": [
37
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-1749960.pt"
38
  ]
39
  },
40
  {
41
+ "steps": 1799984,
42
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1799984.onnx",
43
+ "reward": 28.0,
44
+ "creation_time": 1770597432.9348755,
45
  "auxillary_file_paths": [
46
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-1799984.pt"
47
+ ]
48
+ },
49
+ {
50
+ "steps": 1849984,
51
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1849984.onnx",
52
+ "reward": 28.363636363636363,
53
+ "creation_time": 1770597537.7290735,
54
+ "auxillary_file_paths": [
55
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-1849984.pt"
56
+ ]
57
+ },
58
+ {
59
+ "steps": 1899944,
60
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1899944.onnx",
61
+ "reward": 29.181818181818183,
62
+ "creation_time": 1770597642.8117526,
63
+ "auxillary_file_paths": [
64
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-1899944.pt"
65
+ ]
66
+ },
67
+ {
68
+ "steps": 1949968,
69
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1949968.onnx",
70
+ "reward": 28.545454545454547,
71
+ "creation_time": 1770597750.7901583,
72
+ "auxillary_file_paths": [
73
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-1949968.pt"
74
+ ]
75
+ },
76
+ {
77
+ "steps": 1999992,
78
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1999992.onnx",
79
+ "reward": 27.545454545454547,
80
+ "creation_time": 1770597860.9212458,
81
+ "auxillary_file_paths": [
82
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-1999992.pt"
83
+ ]
84
+ },
85
+ {
86
+ "steps": 2000504,
87
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-2000504.onnx",
88
+ "reward": 27.545454545454547,
89
+ "creation_time": 1770597861.0504487,
90
+ "auxillary_file_paths": [
91
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-2000504.pt"
92
  ]
93
  }
94
  ],
95
  "final_checkpoint": {
96
+ "steps": 2000504,
97
+ "file_path": "results/SnowballTarget2/SnowballTarget.onnx",
98
+ "reward": 27.545454545454547,
99
+ "creation_time": 1770597861.0504487,
100
  "auxillary_file_paths": [
101
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-2000504.pt"
102
  ]
103
  }
104
  },