tinywell commited on
Commit
9773566
·
verified ·
1 Parent(s): 3333c3c

step 200000

Browse files
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:164ec85de9264a735a58ea14f5a715f2b9a0177fcca57d062f939dbe6e0c3b4a
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5a5bf727a71a172e02098feb4dceacdf645c89f35582015aee09f11d32d8149
3
  size 650646
SnowballTarget/SnowballTarget-149984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8134542fb004d9126317924508485c6486cde2f64a327e302169f1a7ca81de66
3
+ size 650646
SnowballTarget/SnowballTarget-149984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e86d9a1fd5113d57f8d533c92b65723ac6724e459c0acbfd08e60c1fc6767bab
3
+ size 3850075
SnowballTarget/SnowballTarget-199984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5a5bf727a71a172e02098feb4dceacdf645c89f35582015aee09f11d32d8149
3
+ size 650646
SnowballTarget/SnowballTarget-199984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bbd8cbfc29d4cd62c388f0f2cc5d817eca4322bd132bd31df505bafd94f4f3b
3
+ size 3850075
SnowballTarget/SnowballTarget-200112.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5a5bf727a71a172e02098feb4dceacdf645c89f35582015aee09f11d32d8149
3
+ size 650646
SnowballTarget/SnowballTarget-200112.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b41ff5bedffafcb681dbb106788b4d2acbe798162ccadd7c7c779a006142bd98
3
+ size 3850075
SnowballTarget/SnowballTarget-49936.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:be353c26ee1363e928b0991bbb0ed4a329606560977d7d42d1169fe0a471e282
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8df1b2fce5df7c556f63147dcc3e5d4aa001a88d83f6f7d4db908e08217a6ba2
3
  size 650646
SnowballTarget/SnowballTarget-49936.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:529790f871379faacd5d9e950048b8af485071a5ce51dc634594fa28124713a2
3
  size 3850000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76c1bbb9366fcb32af1a5fee63e41fb443d74c48512ab34ecbb8d8a64e606677
3
  size 3850000
SnowballTarget/SnowballTarget-99960.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:164ec85de9264a735a58ea14f5a715f2b9a0177fcca57d062f939dbe6e0c3b4a
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9aa000145ef8d5883584d3fbe6277f7799312b14fa2ae5b24b4a8f68119e89b8
3
  size 650646
SnowballTarget/SnowballTarget-99960.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d2d07f28b553494898e07530db611fc9fa25203672e523c304075b22a21eed1
3
  size 3850000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9eab55e7e34f6ae38c211e653390c1654103a61e4ee10409546e853a4a0d46e
3
  size 3850000
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e0b6b8a210417c545c2893fa58ab4ee0bdd7b13f0f6d920480efb3cb0c8ddd5
3
  size 3849250
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38b0bf2ec7ebc6624abb87fc719ee75caa4bb189dfb172b7094adee87bd43826
3
  size 3849250
SnowballTarget/events.out.tfevents.1711017539.35054b78594f.7520.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:196eea9b50cf3d48bde3a7c80820a73e4624acde6ed2db12a726e1bde82d08da
3
+ size 19471
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": 100000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
 
1
+ {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 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": "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: 100000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: true
@@ -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: 200000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: true
 
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
@@ -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 0.085 seconds
35
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
36
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
37
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -42,7 +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: 0.686205 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]: 2694 frames, [16.0 KB-32.0 KB]: 45 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 42
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]: 2740 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]: 2740 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
- Peak Allocated memory 17.3 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]: 1799 frames, [64.0 KB-128.0 KB]: 941 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
- Peak Allocated memory 67.2 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
- Peak usage frame count: [32.0 KB-64.0 KB]: 2740 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]: 2740 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]: 2739 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]: 2740 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]: 2740 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 0.091 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: 0.696377 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 41
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]: 4575 frames, [64.0 KB-128.0 KB]: 885 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
  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
@@ -2,213 +2,213 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 1.7546833753585815,
6
- "min": 1.7546833753585815,
7
- "max": 2.8598406314849854,
8
- "count": 10
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 18046.91796875,
12
- "min": 17638.845703125,
13
- "max": 29287.62890625,
14
- "count": 10
15
  },
16
  "SnowballTarget.Step.mean": {
17
- "value": 99960.0,
18
  "min": 9952.0,
19
- "max": 99960.0,
20
- "count": 10
21
  },
22
  "SnowballTarget.Step.sum": {
23
- "value": 99960.0,
24
  "min": 9952.0,
25
- "max": 99960.0,
26
- "count": 10
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 8.02830982208252,
30
- "min": 0.494703084230423,
31
- "max": 8.02830982208252,
32
- "count": 10
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 1637.7752685546875,
36
- "min": 95.97239685058594,
37
- "max": 1637.7752685546875,
38
- "count": 10
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
- "count": 10
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
- "value": 10945.0,
48
  "min": 8756.0,
49
  "max": 10945.0,
50
- "count": 10
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
- "value": 0.06671752201064544,
54
- "min": 0.060157805143378436,
55
- "max": 0.073970396318199,
56
- "count": 10
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.33358761005322723,
60
- "min": 0.24063122057351374,
61
- "max": 0.3559026988388687,
62
- "count": 10
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.2608148700466343,
66
- "min": 0.12433032255948467,
67
- "max": 0.2608148700466343,
68
- "count": 10
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 1.3040743502331713,
72
- "min": 0.4973212902379387,
73
- "max": 1.3040743502331713,
74
- "count": 10
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
- "value": 1.6464094511999996e-05,
78
- "min": 1.6464094511999996e-05,
79
- "max": 0.000283764005412,
80
- "count": 10
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
- "value": 8.232047255999999e-05,
84
- "min": 8.232047255999999e-05,
85
- "max": 0.00127032007656,
86
- "count": 10
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
- "value": 0.105488,
90
- "min": 0.105488,
91
- "max": 0.194588,
92
- "count": 10
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
- "value": 0.52744,
96
- "min": 0.4615520000000001,
97
- "max": 0.92344,
98
- "count": 10
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
- "value": 0.0002838512,
102
- "min": 0.0002838512,
103
- "max": 0.0047299412,
104
- "count": 10
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
107
- "value": 0.001419256,
108
- "min": 0.001419256,
109
- "max": 0.021179656,
110
- "count": 10
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 17.072727272727274,
114
- "min": 3.227272727272727,
115
- "max": 17.113636363636363,
116
- "count": 10
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 939.0,
120
- "min": 142.0,
121
- "max": 939.0,
122
- "count": 10
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 17.072727272727274,
126
- "min": 3.227272727272727,
127
- "max": 17.113636363636363,
128
- "count": 10
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 939.0,
132
- "min": 142.0,
133
- "max": 939.0,
134
- "count": 10
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
- "count": 10
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
- "count": 10
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1711016984",
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": "2.2.1+cu121",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1711017206"
160
  },
161
- "total": 221.69510313800015,
162
  "count": 1,
163
- "self": 0.4354103030002534,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.052736038999910306,
167
  "count": 1,
168
- "self": 0.052736038999910306
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 221.206956796,
172
  "count": 1,
173
- "self": 0.2707953499971154,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 2.0288960410000527,
177
  "count": 1,
178
- "self": 2.0288960410000527
179
  },
180
  "TrainerController.advance": {
181
- "total": 218.8072953410026,
182
- "count": 9132,
183
- "self": 0.13172173200200632,
184
  "children": {
185
  "env_step": {
186
- "total": 218.6755736090006,
187
- "count": 9132,
188
- "self": 140.4451223180008,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 78.09403044099417,
192
- "count": 9132,
193
- "self": 0.7054380509850944,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 77.38859239000908,
197
- "count": 9132,
198
- "self": 77.38859239000908
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.13642085000560655,
204
- "count": 9132,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 220.63319591599338,
209
- "count": 9132,
210
  "is_parallel": true,
211
- "self": 110.99905126598287,
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": 0.0022111729999778618,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.0006416930000341381,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0015694799999437237,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0015694799999437237
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.035488875000055486,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0006771549999484705,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.0003973340001266479,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.0003973340001266479
244
  },
245
  "communicator.exchange": {
246
- "total": 0.03255557900001804,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.03255557900001804
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0018588069999623258,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.0003574979998575145,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0015013090001048113,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0015013090001048113
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 109.63414465001051,
271
- "count": 9131,
272
  "is_parallel": true,
273
- "self": 5.1386067409935094,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 2.6554060240125636,
277
- "count": 9131,
278
  "is_parallel": true,
279
- "self": 2.6554060240125636
280
  },
281
  "communicator.exchange": {
282
- "total": 85.5755199579985,
283
- "count": 9131,
284
  "is_parallel": true,
285
- "self": 85.5755199579985
286
  },
287
  "steps_from_proto": {
288
- "total": 16.264611927005944,
289
- "count": 9131,
290
  "is_parallel": true,
291
- "self": 3.0467749300239575,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 13.217836996981987,
295
- "count": 91310,
296
  "is_parallel": true,
297
- "self": 13.217836996981987
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 0.00011155200013490685,
313
  "count": 1,
314
- "self": 0.00011155200013490685,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,36 +320,36 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 216.02437644697443,
324
- "count": 329681,
325
  "is_parallel": true,
326
- "self": 7.237682611968239,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 118.50541695800598,
330
- "count": 329681,
331
  "is_parallel": true,
332
- "self": 118.22468560200582,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
- "total": 0.2807313560001603,
336
- "count": 2,
337
  "is_parallel": true,
338
- "self": 0.2807313560001603
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
- "total": 90.28127687700021,
344
- "count": 45,
345
  "is_parallel": true,
346
- "self": 26.184951086995852,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
- "total": 64.09632579000436,
350
- "count": 2292,
351
  "is_parallel": true,
352
- "self": 64.09632579000436
353
  }
354
  }
355
  }
@@ -360,14 +360,14 @@
360
  }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.09985851200008256,
364
  "count": 1,
365
- "self": 0.0009348550001959666,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.09892365699988659,
369
  "count": 1,
370
- "self": 0.09892365699988659
371
  }
372
  }
373
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.9170640707015991,
6
+ "min": 0.9170640707015991,
7
+ "max": 2.860229730606079,
8
+ "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 8756.1279296875,
12
+ "min": 8756.1279296875,
13
+ "max": 29260.150390625,
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": 12.99020767211914,
30
+ "min": 0.326280802488327,
31
+ "max": 12.99020767211914,
32
+ "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2533.090576171875,
36
+ "min": 63.2984733581543,
37
+ "max": 2638.36376953125,
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": 8756.0,
48
  "min": 8756.0,
49
  "max": 10945.0,
50
+ "count": 20
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.06786526505532617,
54
+ "min": 0.062182869404162316,
55
+ "max": 0.08021763855489839,
56
+ "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.2714610602213047,
60
+ "min": 0.24873147761664927,
61
+ "max": 0.36555384002970054,
62
+ "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.19483383474688903,
66
+ "min": 0.11548231221740043,
67
+ "max": 0.2769905658329234,
68
+ "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.7793353389875561,
72
+ "min": 0.46192924886960174,
73
+ "max": 1.3849528291646171,
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": 25.772727272727273,
114
+ "min": 3.4545454545454546,
115
+ "max": 25.772727272727273,
116
+ "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1134.0,
120
+ "min": 152.0,
121
+ "max": 1406.0,
122
+ "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 25.772727272727273,
126
+ "min": 3.4545454545454546,
127
+ "max": 25.772727272727273,
128
+ "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1134.0,
132
+ "min": 152.0,
133
+ "max": 1406.0,
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": "1711017539",
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": "2.2.1+cu121",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1711017971"
160
  },
161
+ "total": 432.23780170099985,
162
  "count": 1,
163
+ "self": 0.43628886299984515,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.05209177799997633,
167
  "count": 1,
168
+ "self": 0.05209177799997633
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 431.74942106000003,
172
  "count": 1,
173
+ "self": 0.5362670520089523,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 1.960719116999826,
177
  "count": 1,
178
+ "self": 1.960719116999826
179
  },
180
  "TrainerController.advance": {
181
+ "total": 429.1619950759912,
182
+ "count": 18198,
183
+ "self": 0.26251593598635736,
184
  "children": {
185
  "env_step": {
186
+ "total": 428.8994791400048,
187
+ "count": 18198,
188
+ "self": 274.3759014199686,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 154.24752886000965,
192
+ "count": 18198,
193
+ "self": 1.4117804469999555,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 152.8357484130097,
197
+ "count": 18198,
198
+ "self": 152.8357484130097
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.27604886002654894,
204
+ "count": 18198,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 430.6149070170154,
209
+ "count": 18198,
210
  "is_parallel": true,
211
+ "self": 215.42083069100227,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.0022657389999949373,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0006678599997940182,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0015978790002009191,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0015978790002009191
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.03645421500004886,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0006825499999649765,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0004073019999850658,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0004073019999850658
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.033227948000103424,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.033227948000103424
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.002136414999995395,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.00041298300061498594,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0017234319993804093,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0017234319993804093
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 215.19407632601315,
271
+ "count": 18197,
272
  "is_parallel": true,
273
+ "self": 10.024022665011444,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 5.21538268302038,
277
+ "count": 18197,
278
  "is_parallel": true,
279
+ "self": 5.21538268302038
280
  },
281
  "communicator.exchange": {
282
+ "total": 167.40767174697453,
283
+ "count": 18197,
284
  "is_parallel": true,
285
+ "self": 167.40767174697453
286
  },
287
  "steps_from_proto": {
288
+ "total": 32.546999231006794,
289
+ "count": 18197,
290
  "is_parallel": true,
291
+ "self": 6.064365135041953,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 26.48263409596484,
295
+ "count": 181970,
296
  "is_parallel": true,
297
+ "self": 26.48263409596484
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 0.00012526899990916718,
313
  "count": 1,
314
+ "self": 0.00012526899990916718,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 423.68849228009753,
324
+ "count": 659375,
325
  "is_parallel": true,
326
+ "self": 14.235416164080561,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 233.49233048901806,
330
+ "count": 659375,
331
  "is_parallel": true,
332
+ "self": 232.82248147301766,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
+ "total": 0.6698490160003985,
336
+ "count": 4,
337
  "is_parallel": true,
338
+ "self": 0.6698490160003985
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
+ "total": 175.96074562699891,
344
+ "count": 90,
345
  "is_parallel": true,
346
+ "self": 50.79041540399794,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 125.17033022300097,
350
+ "count": 4587,
351
  "is_parallel": true,
352
+ "self": 125.17033022300097
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.09031454600017241,
364
  "count": 1,
365
+ "self": 0.0010352740000598715,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.08927927200011254,
369
  "count": 1,
370
+ "self": 0.08927927200011254
371
  }
372
  }
373
  }
run_logs/training_status.json CHANGED
@@ -3,39 +3,57 @@
3
  "checkpoints": [
4
  {
5
  "steps": 49936,
6
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 10.272727272727273,
8
- "creation_time": 1711017096.6595137,
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": 17.272727272727273,
17
- "creation_time": 1711017206.0792985,
18
  "auxillary_file_paths": [
19
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
21
  },
22
  {
23
- "steps": 100088,
24
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-100088.onnx",
25
- "reward": 17.272727272727273,
26
- "creation_time": 1711017206.2045841,
27
  "auxillary_file_paths": [
28
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-100088.pt"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
29
  ]
30
  }
31
  ],
32
  "final_checkpoint": {
33
- "steps": 100088,
34
- "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
35
- "reward": 17.272727272727273,
36
- "creation_time": 1711017206.2045841,
37
  "auxillary_file_paths": [
38
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-100088.pt"
39
  ]
40
  }
41
  },
 
3
  "checkpoints": [
4
  {
5
  "steps": 49936,
6
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-49936.onnx",
7
+ "reward": 13.909090909090908,
8
+ "creation_time": 1711017649.3470476,
9
  "auxillary_file_paths": [
10
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-49936.pt"
11
  ]
12
  },
13
  {
14
  "steps": 99960,
15
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-99960.onnx",
16
+ "reward": 21.0,
17
+ "creation_time": 1711017756.769436,
18
  "auxillary_file_paths": [
19
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
21
  },
22
  {
23
+ "steps": 149984,
24
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.onnx",
25
+ "reward": 25.363636363636363,
26
+ "creation_time": 1711017864.986829,
27
  "auxillary_file_paths": [
28
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.pt"
29
+ ]
30
+ },
31
+ {
32
+ "steps": 199984,
33
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.onnx",
34
+ "reward": 26.09090909090909,
35
+ "creation_time": 1711017970.849175,
36
+ "auxillary_file_paths": [
37
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.pt"
38
+ ]
39
+ },
40
+ {
41
+ "steps": 200112,
42
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.onnx",
43
+ "reward": 26.09090909090909,
44
+ "creation_time": 1711017970.9633875,
45
+ "auxillary_file_paths": [
46
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.pt"
47
  ]
48
  }
49
  ],
50
  "final_checkpoint": {
51
+ "steps": 200112,
52
+ "file_path": "results/SnowballTarget2/SnowballTarget.onnx",
53
+ "reward": 26.09090909090909,
54
+ "creation_time": 1711017970.9633875,
55
  "auxillary_file_paths": [
56
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },