amit-huggingface2 commited on
Commit
e1dc1d2
·
verified ·
1 Parent(s): 8180a8f

First Push

Browse files
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a5c2bd37752bb9b75a7fd3aaa8b3abbba79eab850019e4603c63813333ba9567
3
  size 1178864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b9db2c7cc0588bda93caa8c9c3d3d21ea7b29a39743e95dd276b62e6b852ff3
3
  size 1178864
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:95f4d7ff2b6e0ebf15eab045d002cc3cad32622f85d1e2caf15eaf8889536a69
3
  size 1178864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9260c6da515abf6095e2ca0c3e588e667fbd8448babb2c5c20215c787f292cce
3
  size 1178864
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f0fe88f6c40e5ec2cdb42493bfccc4f9eedc44428072a2ef747e7679355e512
3
  size 7019111
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c2dd3403515d203525a4f67697a1010c8c709b0687c7281255400997c6e3fd8
3
  size 7019111
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a5c2bd37752bb9b75a7fd3aaa8b3abbba79eab850019e4603c63813333ba9567
3
  size 1178864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db4e45da7daaeab3cfd10bcfb7649d80067b1d5c8c774c8ce306b2cef9f24a56
3
  size 1178864
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:808fb271e3b43b2fe79f0a5f18dc57f0593f5e18d21916f13f51cba0ec8f0c29
3
  size 7019111
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe3a774596177d8b2221d07bf1e09b0bfb3cb713f9b3a5c5011e3b35532457c0
3
  size 7019111
SnowballTarget/SnowballTarget-249880.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a409a92929c08a36b585c3d9c6330e58abaf10dca917a05d24d4b2d413aa4ee3
3
+ size 1178864
SnowballTarget/SnowballTarget-249880.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc3bbdb38245c0485218c645823abd9ddfac706788d2a9a2a48f111cc3076b75
3
+ size 7019111
SnowballTarget/SnowballTarget-299968.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4bdba45cf26508370cbdb24299bc1a1e4ecd3efbe425d0589d5d86c73c66e49
3
+ size 1178864
SnowballTarget/SnowballTarget-299968.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a72c96387d8821876b71800e0ff1f27355d25017509ace555aa021c40c08dfd5
3
+ size 7019111
SnowballTarget/SnowballTarget-349928.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5661a4f4835246ef62a72bf10ff272a08b50f95f95ecb1deb7260fc7e2d92a93
3
+ size 1178864
SnowballTarget/SnowballTarget-349928.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff6c2ec72cde7cdefb8a8748d8f4865a0e473766d5e7d70d2a562bd8bace9b32
3
+ size 7019111
SnowballTarget/SnowballTarget-399968.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ab8cfbd09a7b89a39ba865562f3711beb2aa53a6bdaca30088159cd99cbaec7
3
+ size 1178864
SnowballTarget/SnowballTarget-399968.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11cda171ed512820a6cf53f574e99fa6107027a225106c8967498dbfca8d4252
3
+ size 7019111
SnowballTarget/SnowballTarget-449952.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d3947619129406df8be495f28ef085fcb86d4c00ecf5e07b068dc6d95e4db0a
3
+ size 1178864
SnowballTarget/SnowballTarget-449952.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5231b582539b0cd9b77272fc07d0d8da70b21d1e568475a175b6413de2661a0b
3
+ size 7019111
SnowballTarget/SnowballTarget-499912.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b9db2c7cc0588bda93caa8c9c3d3d21ea7b29a39743e95dd276b62e6b852ff3
3
+ size 1178864
SnowballTarget/SnowballTarget-499912.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:799678453ed3536d5e1de653786e5c31bf74a902b37a7d6f7787e8d6bcd3ae84
3
+ size 7019111
SnowballTarget/SnowballTarget-500808.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b9db2c7cc0588bda93caa8c9c3d3d21ea7b29a39743e95dd276b62e6b852ff3
3
+ size 1178864
SnowballTarget/SnowballTarget-500808.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daa218b2e1171885cd838c23d025004a0501713aa1ffaf2f1f98274ffd12c80a
3
+ size 7019111
SnowballTarget/SnowballTarget-99896.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ad8713571a5cf043c0044346e4baed2bffc8400909e584e5365c993c5efa7169
3
  size 1178864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:264c40346fabe6ee6db74c939de1ed01f6833e11bc94ac5bb3ae0080fac87405
3
  size 1178864
SnowballTarget/SnowballTarget-99896.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:128e73a52d0ee37ca4fcfda445f39d430fe461773106cbfcaa430bd3597cf206
3
  size 7019002
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0969a606eeac956cf81aed39d960628ca426a6992e575f828080671a1f87343b
3
  size 7019002
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a2e37fc7cf789e660b7f1a59d9f719ef334d872cec218da6d47cd7940c43309
3
  size 7017912
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05376217291dbb940d5cd2aa615c86ac51dd1932b26065c75d2e9e407015fefe
3
  size 7017912
SnowballTarget/events.out.tfevents.1746728087.b2fdf73fad11.14653.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a42eae68f6accb2b08a823b7ed1bff31c0cfec7051a54cb68063c305cdeed9ae
3
+ size 53975
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0001, "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": 4, "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": 128, "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": true, "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": 0.0001, "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": 4, "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": 500000, "time_horizon": 128, "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": true, "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: 128
43
  summary_freq: 10000
44
  threaded: false
 
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
+ max_steps: 500000
42
  time_horizon: 128
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 0.088 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: 0.626930 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]: 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
@@ -166,22 +166,22 @@ Memory Statistics:
166
  Peak Allocated Bytes 0 B
167
  Overflow Count 0
168
  [ALLOC_DEFAULT] Dual Thread Allocator
169
- Peak main deferred allocation count 45
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 6.7 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 17.9 MB
185
  Peak Large allocation bytes 16.0 MB
186
  [ALLOC_TEMP_JOB_1_FRAME]
187
  Initial Block Size 2.0 MB
@@ -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]: 4259 frames, [64.0 KB-128.0 KB]: 1201 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]: 5460 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]: 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
@@ -246,13 +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]: 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
 
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
  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: 0.654624 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]: 13431 frames, [16.0 KB-32.0 KB]: 227 frames, [2.0 MB-4.0 MB]: 1 frames
54
  Initial Block Size 4.0 MB
55
  Current Block Size 4.0 MB
56
  Peak Allocated Bytes 2.0 MB
 
166
  Peak Allocated Bytes 0 B
167
  Overflow Count 0
168
  [ALLOC_DEFAULT] Dual Thread Allocator
169
+ Peak main deferred allocation count 44
170
  [ALLOC_BUCKET]
171
  Large Block size 4.0 MB
172
  Used Block count 1
173
  Peak Allocated bytes 1.0 MB
174
  [ALLOC_DEFAULT_MAIN]
175
+ Peak usage frame count: [4.0 MB-8.0 MB]: 12084 frames, [8.0 MB-16.0 MB]: 1575 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
+ Peak Allocated memory 9.6 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 13659 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]: 11838 frames, [64.0 KB-128.0 KB]: 1821 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]: 13659 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]: 13659 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]: 13658 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]: 13659 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]: 13659 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": 0.866055965423584,
6
- "min": 0.866055965423584,
7
- "max": 2.8736066818237305,
8
- "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 8307.208984375,
12
- "min": 8307.208984375,
13
- "max": 30149.6875,
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": 10.340476989746094,
30
- "min": 0.33099132776260376,
31
- "max": 10.340476989746094,
32
- "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 1044.38818359375,
36
- "min": 32.10615921020508,
37
- "max": 1044.38818359375,
38
- "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
- "count": 20
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
- "value": 10945.0,
48
  "min": 8756.0,
49
  "max": 10945.0,
50
- "count": 20
51
  },
52
  "SnowballTarget.Environment.CumulativeReward.mean": {
53
- "value": 20.76923076923077,
54
  "min": 3.3181818181818183,
55
- "max": 20.76923076923077,
56
- "count": 20
57
  },
58
  "SnowballTarget.Environment.CumulativeReward.sum": {
59
- "value": 1080.0,
60
  "min": 146.0,
61
- "max": 1087.0,
62
- "count": 20
63
  },
64
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
65
- "value": 20.76923076923077,
66
  "min": 3.3181818181818183,
67
- "max": 20.76923076923077,
68
- "count": 20
69
  },
70
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
71
- "value": 1080.0,
72
  "min": 146.0,
73
- "max": 1087.0,
74
- "count": 20
75
  },
76
  "SnowballTarget.Losses.PolicyLoss.mean": {
77
- "value": 0.0745790804596575,
78
- "min": 0.06057858057753822,
79
- "max": 0.07678922078088292,
80
- "count": 20
81
  },
82
  "SnowballTarget.Losses.PolicyLoss.sum": {
83
- "value": 0.29831632183863,
84
- "min": 0.24595807271772155,
85
- "max": 0.3839461039044146,
86
- "count": 20
87
  },
88
  "SnowballTarget.Losses.ValueLoss.mean": {
89
- "value": 0.2597986389608944,
90
- "min": 0.11439315633227427,
91
- "max": 0.3273543331260775,
92
- "count": 20
93
  },
94
  "SnowballTarget.Losses.ValueLoss.sum": {
95
- "value": 1.0391945558435776,
96
- "min": 0.4575726253290971,
97
- "max": 1.4930201053035026,
98
- "count": 20
99
  },
100
  "SnowballTarget.Policy.LearningRate.mean": {
101
- "value": 2.6500973500000027e-06,
102
- "min": 2.6500973500000027e-06,
103
- "max": 9.725000275000001e-05,
104
- "count": 20
105
  },
106
  "SnowballTarget.Policy.LearningRate.sum": {
107
- "value": 1.0600389400000011e-05,
108
- "min": 1.0600389400000011e-05,
109
- "max": 0.0004615000385,
110
- "count": 20
111
  },
112
  "SnowballTarget.Policy.Epsilon.mean": {
113
- "value": 0.10265,
114
- "min": 0.10265,
115
- "max": 0.19725000000000004,
116
- "count": 20
117
  },
118
  "SnowballTarget.Policy.Epsilon.sum": {
119
- "value": 0.4106,
120
- "min": 0.4106,
121
- "max": 0.9615,
122
- "count": 20
123
  },
124
  "SnowballTarget.Policy.Beta.mean": {
125
- "value": 0.00014223500000000013,
126
- "min": 0.00014223500000000013,
127
- "max": 0.004862775,
128
- "count": 20
129
  },
130
  "SnowballTarget.Policy.Beta.sum": {
131
- "value": 0.0005689400000000005,
132
- "min": 0.0005689400000000005,
133
- "max": 0.023078849999999998,
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": "1746727554",
152
  "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
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 --force",
154
  "mlagents_version": "1.2.0.dev0",
@@ -156,59 +156,59 @@
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.7.0+cu126",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1746727995"
160
  },
161
- "total": 440.8755808630003,
162
  "count": 1,
163
- "self": 0.43463302800000747,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.02063435100035349,
167
  "count": 1,
168
- "self": 0.02063435100035349
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 440.42031348399996,
172
  "count": 1,
173
- "self": 0.3755915409778936,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 2.0705331960002695,
177
  "count": 1,
178
- "self": 2.0705331960002695
179
  },
180
  "TrainerController.advance": {
181
- "total": 437.85194271302225,
182
- "count": 18200,
183
- "self": 0.37860206703544463,
184
  "children": {
185
  "env_step": {
186
- "total": 310.4684176669916,
187
- "count": 18200,
188
- "self": 235.69029849699382,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 74.56212913599393,
192
- "count": 18200,
193
- "self": 1.2931699509645114,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 73.26895918502942,
197
- "count": 18200,
198
- "self": 73.26895918502942
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.21599003400388028,
204
- "count": 18200,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 438.89239969098753,
209
- "count": 18200,
210
  "is_parallel": true,
211
- "self": 232.51465910796833,
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": 0.0020808340000257886,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.0006971189995965688,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0013837150004292198,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0013837150004292198
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.03744603499990262,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0006000580001455091,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.00042623899980753777,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.00042623899980753777
244
  },
245
  "communicator.exchange": {
246
- "total": 0.034493812000164326,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.034493812000164326
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0019259259997852496,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.00038434600037362543,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0015415799994116242,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0015415799994116242
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 206.3777405830192,
271
- "count": 18199,
272
  "is_parallel": true,
273
- "self": 9.651060604046506,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 5.513769348989172,
277
- "count": 18199,
278
  "is_parallel": true,
279
- "self": 5.513769348989172
280
  },
281
  "communicator.exchange": {
282
- "total": 159.06907518401204,
283
- "count": 18199,
284
  "is_parallel": true,
285
- "self": 159.06907518401204
286
  },
287
  "steps_from_proto": {
288
- "total": 32.14383544597149,
289
- "count": 18199,
290
  "is_parallel": true,
291
- "self": 5.796821430038108,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 26.347014015933382,
295
- "count": 181990,
296
  "is_parallel": true,
297
- "self": 26.347014015933382
298
  }
299
  }
300
  }
@@ -307,31 +307,31 @@
307
  }
308
  },
309
  "trainer_advance": {
310
- "total": 127.00492297899518,
311
- "count": 18200,
312
- "self": 0.45877129195469024,
313
  "children": {
314
  "process_trajectory": {
315
- "total": 24.47945037703539,
316
- "count": 18200,
317
- "self": 23.961989552035448,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
- "total": 0.5174608249999437,
321
- "count": 4,
322
- "self": 0.5174608249999437
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
- "total": 102.0667013100051,
328
- "count": 90,
329
- "self": 38.76706982499081,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
- "total": 63.29963148501429,
333
- "count": 4590,
334
- "self": 63.29963148501429
335
  }
336
  }
337
  }
@@ -340,19 +340,19 @@
340
  }
341
  },
342
  "trainer_threads": {
343
- "total": 1.002999852062203e-06,
344
  "count": 1,
345
- "self": 1.002999852062203e-06
346
  },
347
  "TrainerController._save_models": {
348
- "total": 0.12224503099969297,
349
  "count": 1,
350
- "self": 0.0014444499997807725,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
- "total": 0.1208005809999122,
354
  "count": 1,
355
- "self": 0.1208005809999122
356
  }
357
  }
358
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.6451561450958252,
6
+ "min": 0.6286781430244446,
7
+ "max": 2.8756980895996094,
8
+ "count": 50
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 6585.75390625,
12
+ "min": 5853.9853515625,
13
+ "max": 29852.865234375,
14
+ "count": 50
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 499912.0,
18
  "min": 9952.0,
19
+ "max": 499912.0,
20
+ "count": 50
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 499912.0,
24
  "min": 9952.0,
25
+ "max": 499912.0,
26
+ "count": 50
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 13.346131324768066,
30
+ "min": 0.3838321566581726,
31
+ "max": 13.421761512756348,
32
+ "count": 50
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 1347.959228515625,
36
+ "min": 37.231719970703125,
37
+ "max": 1372.527099609375,
38
+ "count": 50
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
+ "count": 50
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
+ "value": 8756.0,
48
  "min": 8756.0,
49
  "max": 10945.0,
50
+ "count": 50
51
  },
52
  "SnowballTarget.Environment.CumulativeReward.mean": {
53
+ "value": 26.245283018867923,
54
  "min": 3.3181818181818183,
55
+ "max": 26.636363636363637,
56
+ "count": 50
57
  },
58
  "SnowballTarget.Environment.CumulativeReward.sum": {
59
+ "value": 1391.0,
60
  "min": 146.0,
61
+ "max": 1465.0,
62
+ "count": 50
63
  },
64
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
65
+ "value": 26.245283018867923,
66
  "min": 3.3181818181818183,
67
+ "max": 26.636363636363637,
68
+ "count": 50
69
  },
70
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
71
+ "value": 1391.0,
72
  "min": 146.0,
73
+ "max": 1465.0,
74
+ "count": 50
75
  },
76
  "SnowballTarget.Losses.PolicyLoss.mean": {
77
+ "value": 0.06964334745151814,
78
+ "min": 0.061930045465352114,
79
+ "max": 0.07796469195654579,
80
+ "count": 50
81
  },
82
  "SnowballTarget.Losses.PolicyLoss.sum": {
83
+ "value": 0.34821673725759067,
84
+ "min": 0.25014667038586225,
85
+ "max": 0.38377857424190964,
86
+ "count": 50
87
  },
88
  "SnowballTarget.Losses.ValueLoss.mean": {
89
+ "value": 0.18812478988193998,
90
+ "min": 0.1348829431568875,
91
+ "max": 0.29769709139477973,
92
+ "count": 50
93
  },
94
  "SnowballTarget.Losses.ValueLoss.sum": {
95
+ "value": 0.9406239494096998,
96
+ "min": 0.53953177262755,
97
+ "max": 1.4884854569738986,
98
+ "count": 50
99
  },
100
  "SnowballTarget.Policy.LearningRate.mean": {
101
+ "value": 1.000099000000001e-06,
102
+ "min": 1.000099000000001e-06,
103
+ "max": 9.890000109999999e-05,
104
+ "count": 50
105
  },
106
  "SnowballTarget.Policy.LearningRate.sum": {
107
+ "value": 5.0004950000000045e-06,
108
+ "min": 5.0004950000000045e-06,
109
+ "max": 0.00048460001540000003,
110
+ "count": 50
111
  },
112
  "SnowballTarget.Policy.Epsilon.mean": {
113
+ "value": 0.101,
114
+ "min": 0.101,
115
+ "max": 0.19890000000000002,
116
+ "count": 50
117
  },
118
  "SnowballTarget.Policy.Epsilon.sum": {
119
+ "value": 0.505,
120
+ "min": 0.41192000000000006,
121
+ "max": 0.9846000000000001,
122
+ "count": 50
123
  },
124
  "SnowballTarget.Policy.Beta.mean": {
125
+ "value": 5.9900000000000047e-05,
126
+ "min": 5.9900000000000047e-05,
127
+ "max": 0.00494511,
128
+ "count": 50
129
  },
130
  "SnowballTarget.Policy.Beta.sum": {
131
+ "value": 0.00029950000000000023,
132
+ "min": 0.00029950000000000023,
133
+ "max": 0.024231540000000003,
134
+ "count": 50
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
+ "count": 50
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
+ "count": 50
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1746728086",
152
  "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
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 --force",
154
  "mlagents_version": "1.2.0.dev0",
 
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.7.0+cu126",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1746729194"
160
  },
161
+ "total": 1107.603658034,
162
  "count": 1,
163
+ "self": 0.43907356799945774,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.021276195000154985,
167
  "count": 1,
168
+ "self": 0.021276195000154985
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 1107.1433082710005,
172
  "count": 1,
173
+ "self": 1.000585237999985,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 2.0653975459999856,
177
  "count": 1,
178
+ "self": 2.0653975459999856
179
  },
180
  "TrainerController.advance": {
181
+ "total": 1103.9625112460003,
182
+ "count": 45528,
183
+ "self": 1.0190705160430298,
184
  "children": {
185
  "env_step": {
186
+ "total": 782.389772776025,
187
+ "count": 45528,
188
+ "self": 592.5068356929787,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 189.3150668580315,
192
+ "count": 45528,
193
+ "self": 3.3085044539170667,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 186.00656240411445,
197
+ "count": 45528,
198
+ "self": 186.00656240411445
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.567870225014758,
204
+ "count": 45528,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 1103.6144141670084,
209
+ "count": 45528,
210
  "is_parallel": true,
211
+ "self": 584.7007441641026,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.0025877699999909964,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.000841334000142524,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0017464359998484724,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0017464359998484724
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.036133436000000074,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0005638149996229913,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0003900700003214297,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0003900700003214297
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.03342848400006915,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.03342848400006915
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0017510669999865058,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.00035100400009469013,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0014000629998918157,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0014000629998918157
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 518.9136700029057,
271
+ "count": 45527,
272
  "is_parallel": true,
273
+ "self": 24.4672301069686,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 13.899344948092676,
277
+ "count": 45527,
278
  "is_parallel": true,
279
+ "self": 13.899344948092676
280
  },
281
  "communicator.exchange": {
282
+ "total": 398.9947476699763,
283
+ "count": 45527,
284
  "is_parallel": true,
285
+ "self": 398.9947476699763
286
  },
287
  "steps_from_proto": {
288
+ "total": 81.5523472778682,
289
+ "count": 45527,
290
  "is_parallel": true,
291
+ "self": 14.71189978594748,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 66.84044749192071,
295
+ "count": 455270,
296
  "is_parallel": true,
297
+ "self": 66.84044749192071
298
  }
299
  }
300
  }
 
307
  }
308
  },
309
  "trainer_advance": {
310
+ "total": 320.5536679539323,
311
+ "count": 45528,
312
+ "self": 1.1939517788146077,
313
  "children": {
314
  "process_trajectory": {
315
+ "total": 61.22596244312717,
316
+ "count": 45528,
317
+ "self": 59.80232532412765,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
+ "total": 1.4236371189995225,
321
+ "count": 10,
322
+ "self": 1.4236371189995225
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
+ "total": 258.1337537319905,
328
+ "count": 227,
329
+ "self": 98.05847612397702,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
+ "total": 160.0752776080135,
333
+ "count": 11577,
334
+ "self": 160.0752776080135
335
  }
336
  }
337
  }
 
340
  }
341
  },
342
  "trainer_threads": {
343
+ "total": 8.859997251420282e-07,
344
  "count": 1,
345
+ "self": 8.859997251420282e-07
346
  },
347
  "TrainerController._save_models": {
348
+ "total": 0.11481335500047862,
349
  "count": 1,
350
+ "self": 0.0015698730012445594,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
+ "total": 0.11324348199923406,
354
  "count": 1,
355
+ "self": 0.11324348199923406
356
  }
357
  }
358
  }
run_logs/training_status.json CHANGED
@@ -1,20 +1,11 @@
1
  {
2
  "SnowballTarget": {
3
  "checkpoints": [
4
- {
5
- "steps": 49952,
6
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49952.onnx",
7
- "reward": 18.0,
8
- "creation_time": 1746727664.0903647,
9
- "auxillary_file_paths": [
10
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-49952.pt"
11
- ]
12
- },
13
  {
14
  "steps": 99896,
15
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99896.onnx",
16
  "reward": null,
17
- "creation_time": 1746727772.530335,
18
  "auxillary_file_paths": [
19
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-99896.pt"
20
  ]
@@ -23,7 +14,7 @@
23
  "steps": 149984,
24
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
25
  "reward": null,
26
- "creation_time": 1746727885.371097,
27
  "auxillary_file_paths": [
28
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
@@ -31,29 +22,83 @@
31
  {
32
  "steps": 199984,
33
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
34
- "reward": 21.875,
35
- "creation_time": 1746727995.1877828,
36
  "auxillary_file_paths": [
37
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
39
  },
40
  {
41
- "steps": 200200,
42
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200200.onnx",
43
- "reward": 21.818181818181817,
44
- "creation_time": 1746727995.3295784,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
45
  "auxillary_file_paths": [
46
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200200.pt"
47
  ]
48
  }
49
  ],
50
  "final_checkpoint": {
51
- "steps": 200200,
52
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
53
- "reward": 21.818181818181817,
54
- "creation_time": 1746727995.3295784,
55
  "auxillary_file_paths": [
56
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200200.pt"
57
  ]
58
  }
59
  },
 
1
  {
2
  "SnowballTarget": {
3
  "checkpoints": [
 
 
 
 
 
 
 
 
 
4
  {
5
  "steps": 99896,
6
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99896.onnx",
7
  "reward": null,
8
+ "creation_time": 1746728311.7257853,
9
  "auxillary_file_paths": [
10
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-99896.pt"
11
  ]
 
14
  "steps": 149984,
15
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
16
  "reward": null,
17
+ "creation_time": 1746728425.6751235,
18
  "auxillary_file_paths": [
19
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
20
  ]
 
22
  {
23
  "steps": 199984,
24
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
25
+ "reward": 24.375,
26
+ "creation_time": 1746728534.4469717,
27
  "auxillary_file_paths": [
28
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
29
  ]
30
  },
31
  {
32
+ "steps": 249880,
33
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-249880.onnx",
34
+ "reward": null,
35
+ "creation_time": 1746728645.164421,
36
+ "auxillary_file_paths": [
37
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-249880.pt"
38
+ ]
39
+ },
40
+ {
41
+ "steps": 299968,
42
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.onnx",
43
+ "reward": null,
44
+ "creation_time": 1746728755.7101135,
45
+ "auxillary_file_paths": [
46
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.pt"
47
+ ]
48
+ },
49
+ {
50
+ "steps": 349928,
51
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-349928.onnx",
52
+ "reward": null,
53
+ "creation_time": 1746728865.4934444,
54
+ "auxillary_file_paths": [
55
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-349928.pt"
56
+ ]
57
+ },
58
+ {
59
+ "steps": 399968,
60
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-399968.onnx",
61
+ "reward": 26.6,
62
+ "creation_time": 1746728972.8183732,
63
+ "auxillary_file_paths": [
64
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-399968.pt"
65
+ ]
66
+ },
67
+ {
68
+ "steps": 449952,
69
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-449952.onnx",
70
+ "reward": null,
71
+ "creation_time": 1746729082.1113374,
72
+ "auxillary_file_paths": [
73
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-449952.pt"
74
+ ]
75
+ },
76
+ {
77
+ "steps": 499912,
78
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-499912.onnx",
79
+ "reward": null,
80
+ "creation_time": 1746729193.7179675,
81
+ "auxillary_file_paths": [
82
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-499912.pt"
83
+ ]
84
+ },
85
+ {
86
+ "steps": 500808,
87
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-500808.onnx",
88
+ "reward": null,
89
+ "creation_time": 1746729193.8984017,
90
  "auxillary_file_paths": [
91
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-500808.pt"
92
  ]
93
  }
94
  ],
95
  "final_checkpoint": {
96
+ "steps": 500808,
97
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
98
+ "reward": null,
99
+ "creation_time": 1746729193.8984017,
100
  "auxillary_file_paths": [
101
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-500808.pt"
102
  ]
103
  }
104
  },