Hugging Face's logo

kollis
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
kollis commited on
Commit
d24a5fd
·
1 Parent(s): 47b8700

First Push

Browse files
Files changed (12) hide show
  1. SnowballTarget.onnx +1 -1
  2. SnowballTarget/SnowballTarget-49936.onnx +3 -0
  3. SnowballTarget/SnowballTarget-49936.pt +3 -0
  4. SnowballTarget/SnowballTarget-50128.onnx +3 -0
  5. SnowballTarget/SnowballTarget-50128.pt +3 -0
  6. SnowballTarget/checkpoint.pt +1 -1
  7. SnowballTarget/events.out.tfevents.1704187513.06b3f43261dd.1785.0 +3 -0
  8. config.json +1 -1
  9. configuration.yaml +5 -5
  10. run_logs/Player-0.log +15 -15
  11. run_logs/timers.json +170 -170
  12. run_logs/training_status.json +14 -23
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7739f0b3f8becc302ec453d9122c02e7f7edeab35a4ea0c39d64149f88adf557
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:548b6cb2a7a495d1eea056b114f2c9e65346ca2c8e49c4d32f9bbd33d3091f59
3
  size 650646
SnowballTarget/SnowballTarget-49936.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:548b6cb2a7a495d1eea056b114f2c9e65346ca2c8e49c4d32f9bbd33d3091f59
3
+ size 650646
SnowballTarget/SnowballTarget-49936.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67a77751e1882eb6a4c29f3d333ba6ef5363ba1667abc2db011f5444f4c90d31
3
+ size 3850000
SnowballTarget/SnowballTarget-50128.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:548b6cb2a7a495d1eea056b114f2c9e65346ca2c8e49c4d32f9bbd33d3091f59
3
+ size 650646
SnowballTarget/SnowballTarget-50128.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9d9f6f9fee3252d42d42f70c76d198ab7cc0262409128586dd02d5b134d6a0d
3
+ size 3850000
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f720cdb7593c45232c214bacfa725b935eace4f04f62e557ce31d29e77f39ae7
3
  size 3849250
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:738633123596366ecada90a65b53e360f2d8f56fb8f97737318690fe0ad38d2c
3
  size 3849250
SnowballTarget/events.out.tfevents.1704187513.06b3f43261dd.1785.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fc5a6152d365ecfb721246a9559a611124506d25a41e1171004d8240f606e33
3
+ size 11117
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 256, "buffer_size": 4096, "learning_rate": 0.0004, "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": 32, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "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": 50000, "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}
configuration.yaml CHANGED
@@ -3,9 +3,9 @@ behaviors:
3
  SnowballTarget:
4
  trainer_type: ppo
5
  hyperparameters:
6
- batch_size: 256
7
- buffer_size: 4096
8
- learning_rate: 0.0004
9
  beta: 0.005
10
  epsilon: 0.2
11
  lambd: 0.95
@@ -38,8 +38,8 @@ behaviors:
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
- max_steps: 100000
42
- time_horizon: 32
43
  summary_freq: 10000
44
  threaded: true
45
  self_play: null
 
3
  SnowballTarget:
4
  trainer_type: ppo
5
  hyperparameters:
6
+ batch_size: 128
7
+ buffer_size: 2048
8
+ learning_rate: 0.0003
9
  beta: 0.005
10
  epsilon: 0.2
11
  lambd: 0.95
 
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
+ max_steps: 50000
42
+ time_horizon: 64
43
  summary_freq: 10000
44
  threaded: true
45
  self_play: null
run_logs/Player-0.log CHANGED
@@ -34,7 +34,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
34
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
35
  FMOD initialized on nosound output
36
  Begin MonoManager ReloadAssembly
37
- - Completed reload, in 0.090 seconds
38
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
39
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
40
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -45,7 +45,7 @@ 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: 0.746773 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 +53,7 @@ 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]: 2686 frames, [16.0 KB-32.0 KB]: 45 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 +169,22 @@ Memory Statistics:
169
  Peak Allocated Bytes 0 B
170
  Overflow Count 0
171
  [ALLOC_DEFAULT] Dual Thread Allocator
172
- Peak main deferred allocation count 37
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]: 2732 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
- Peak Allocated memory 6.1 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
- Peak usage frame count: [16.0 MB-32.0 MB]: 2732 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
- Peak Allocated memory 17.7 MB
188
  Peak Large allocation bytes 16.0 MB
189
  [ALLOC_TEMP_JOB_1_FRAME]
190
  Initial Block Size 2.0 MB
@@ -213,13 +213,13 @@ 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]: 2298 frames, [64.0 KB-128.0 KB]: 434 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]: 2732 frames
223
  Requested Block Size 16.0 MB
224
  Peak Block count 1
225
  Peak Allocated memory 39.6 KB
@@ -231,13 +231,13 @@ 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]: 2732 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]: 2731 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 +249,13 @@ 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]: 2732 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]: 2732 frames
259
  Requested Block Size 2.0 MB
260
  Peak Block count 1
261
  Peak Allocated memory 1.7 KB
 
34
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
35
  FMOD initialized on nosound output
36
  Begin MonoManager ReloadAssembly
37
+ - Completed reload, in 0.088 seconds
38
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
39
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
40
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 
45
  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: 0.678902 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
  [ALLOC_TEMP_TLS] TLS Allocator
54
  StackAllocators :
55
  [ALLOC_TEMP_MAIN]
56
+ Peak usage frame count: [8.0 KB-16.0 KB]: 1356 frames, [16.0 KB-32.0 KB]: 22 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
  Peak Allocated Bytes 0 B
170
  Overflow Count 0
171
  [ALLOC_DEFAULT] Dual Thread Allocator
172
+ Peak main deferred allocation count 41
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]: 1379 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
+ Peak Allocated memory 5.7 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
+ Peak usage frame count: [16.0 MB-32.0 MB]: 1379 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
+ Peak Allocated memory 17.8 MB
188
  Peak Large allocation bytes 16.0 MB
189
  [ALLOC_TEMP_JOB_1_FRAME]
190
  Initial Block Size 2.0 MB
 
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]: 889 frames, [64.0 KB-128.0 KB]: 490 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
+ Peak Allocated memory 67.7 KB
220
  Peak Large allocation bytes 0 B
221
  [ALLOC_GFX_THREAD]
222
+ Peak usage frame count: [32.0 KB-64.0 KB]: 1379 frames
223
  Requested Block Size 16.0 MB
224
  Peak Block count 1
225
  Peak Allocated memory 39.6 KB
 
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]: 1379 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]: 1378 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
  Used Block count 1
250
  Peak Allocated bytes 1.0 MB
251
  [ALLOC_TYPETREE_MAIN]
252
+ Peak usage frame count: [0-1.0 KB]: 1379 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]: 1379 frames
259
  Requested Block Size 2.0 MB
260
  Peak Block count 1
261
  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": 2.2281649112701416,
6
- "min": 2.2281649112701416,
7
- "max": 2.877828598022461,
8
- "count": 10
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 22230.40234375,
12
- "min": 22230.40234375,
13
- "max": 29376.875,
14
- "count": 10
15
  },
16
  "SnowballTarget.Step.mean": {
17
- "value": 99992.0,
18
- "min": 9984.0,
19
- "max": 99992.0,
20
- "count": 10
21
  },
22
  "SnowballTarget.Step.sum": {
23
- "value": 99992.0,
24
- "min": 9984.0,
25
- "max": 99992.0,
26
- "count": 10
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 4.906261920928955,
30
- "min": 0.2686314582824707,
31
- "max": 4.906261920928955,
32
- "count": 10
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 1736.816650390625,
36
- "min": 92.67784881591797,
37
- "max": 1736.816650390625,
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.Environment.CumulativeReward.mean": {
53
- "value": 14.49090909090909,
54
- "min": 3.0454545454545454,
55
- "max": 14.49090909090909,
56
- "count": 10
57
- },
58
- "SnowballTarget.Environment.CumulativeReward.sum": {
59
- "value": 797.0,
60
- "min": 134.0,
61
- "max": 797.0,
62
- "count": 10
63
- },
64
- "SnowballTarget.Policy.ExtrinsicReward.mean": {
65
- "value": 14.49090909090909,
66
- "min": 3.0454545454545454,
67
- "max": 14.49090909090909,
68
- "count": 10
69
- },
70
- "SnowballTarget.Policy.ExtrinsicReward.sum": {
71
- "value": 797.0,
72
- "min": 134.0,
73
- "max": 797.0,
74
- "count": 10
75
  },
76
  "SnowballTarget.Losses.PolicyLoss.mean": {
77
- "value": 0.0444741687871321,
78
- "min": 0.0429690334519061,
79
- "max": 0.05712510223712147,
80
- "count": 10
81
  },
82
  "SnowballTarget.Losses.PolicyLoss.sum": {
83
- "value": 0.1334225063613963,
84
- "min": 0.0859380669038122,
85
- "max": 0.1593253970655211,
86
- "count": 10
87
  },
88
  "SnowballTarget.Losses.ValueLoss.mean": {
89
- "value": 0.26583200469126106,
90
- "min": 0.08503536588293226,
91
- "max": 0.26583200469126106,
92
- "count": 10
93
  },
94
  "SnowballTarget.Losses.ValueLoss.sum": {
95
- "value": 0.7974960140737832,
96
- "min": 0.1700707317658645,
97
- "max": 0.7974960140737832,
98
- "count": 10
99
  },
100
  "SnowballTarget.Policy.LearningRate.mean": {
101
- "value": 2.0192094952000007e-05,
102
- "min": 2.0192094952000007e-05,
103
- "max": 0.000373952006512,
104
- "count": 10
105
  },
106
  "SnowballTarget.Policy.LearningRate.sum": {
107
- "value": 6.057628485600002e-05,
108
- "min": 6.057628485600002e-05,
109
- "max": 0.000785312103672,
110
- "count": 10
111
  },
112
  "SnowballTarget.Policy.Epsilon.mean": {
113
- "value": 0.10504800000000003,
114
- "min": 0.10504800000000003,
115
- "max": 0.193488,
116
- "count": 10
117
  },
118
  "SnowballTarget.Policy.Epsilon.sum": {
119
- "value": 0.3151440000000001,
120
- "min": 0.23203200000000002,
121
- "max": 0.496328,
122
- "count": 10
123
  },
124
  "SnowballTarget.Policy.Beta.mean": {
125
- "value": 0.0002618952000000001,
126
- "min": 0.0002618952000000001,
127
- "max": 0.0046750512,
128
- "count": 10
129
  },
130
  "SnowballTarget.Policy.Beta.sum": {
131
- "value": 0.0007856856000000004,
132
- "min": 0.0007856856000000004,
133
- "max": 0.009826767200000001,
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": "1704182906",
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",
@@ -156,59 +156,59 @@
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.1.2+cu121",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1704183165"
160
  },
161
- "total": 258.30843173799997,
162
  "count": 1,
163
- "self": 0.45240751999995155,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.054931602999999996,
167
  "count": 1,
168
- "self": 0.054931602999999996
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 257.801092615,
172
  "count": 1,
173
- "self": 0.33640647199956675,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 3.603312361999997,
177
  "count": 1,
178
- "self": 3.603312361999997
179
  },
180
  "TrainerController.advance": {
181
- "total": 253.76126643800046,
182
- "count": 9105,
183
- "self": 0.17064165900291073,
184
  "children": {
185
  "env_step": {
186
- "total": 253.59062477899755,
187
- "count": 9105,
188
- "self": 172.2523618009934,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 81.15899457600023,
192
- "count": 9105,
193
- "self": 0.8386254229977226,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 80.3203691530025,
197
- "count": 9105,
198
- "self": 80.3203691530025
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.17926840200391325,
204
- "count": 9105,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 257.0546496349964,
209
- "count": 9105,
210
  "is_parallel": true,
211
- "self": 127.12206386299954,
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": 0.005643419999984189,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.004118428000055019,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0015249919999291706,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0015249919999291706
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.054149961999996776,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0006776979999472132,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.0002613590000350996,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.0002613590000350996
244
  },
245
  "communicator.exchange": {
246
- "total": 0.05099656499999128,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.05099656499999128
250
  },
251
  "steps_from_proto": {
252
- "total": 0.002214340000023185,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.000421219000088513,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.001793120999934672,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.001793120999934672
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 129.93258577199686,
271
- "count": 9104,
272
  "is_parallel": true,
273
- "self": 5.992596635994744,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 3.10947615999919,
277
- "count": 9104,
278
  "is_parallel": true,
279
- "self": 3.10947615999919
280
  },
281
  "communicator.exchange": {
282
- "total": 101.00756925900083,
283
- "count": 9104,
284
  "is_parallel": true,
285
- "self": 101.00756925900083
286
  },
287
  "steps_from_proto": {
288
- "total": 19.82294371700209,
289
- "count": 9104,
290
  "is_parallel": true,
291
- "self": 3.6922180960042965,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 16.130725620997794,
295
- "count": 91040,
296
  "is_parallel": true,
297
- "self": 16.130725620997794
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 4.292899996016786e-05,
313
  "count": 1,
314
- "self": 4.292899996016786e-05,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,36 +320,36 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 249.8028308769944,
324
- "count": 441667,
325
  "is_parallel": true,
326
- "self": 10.263717565976265,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 181.43503808301824,
330
- "count": 441667,
331
  "is_parallel": true,
332
- "self": 181.13073067601823,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
- "total": 0.30430740700001024,
336
- "count": 2,
337
  "is_parallel": true,
338
- "self": 0.30430740700001024
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
- "total": 58.104075227999886,
344
- "count": 23,
345
  "is_parallel": true,
346
- "self": 26.096005237999634,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
- "total": 32.00806999000025,
350
- "count": 1140,
351
  "is_parallel": true,
352
- "self": 32.00806999000025
353
  }
354
  }
355
  }
@@ -360,14 +360,14 @@
360
  }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.10006441400003041,
364
  "count": 1,
365
- "self": 0.0010149299999966388,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.09904948400003377,
369
  "count": 1,
370
- "self": 0.09904948400003377
371
  }
372
  }
373
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 2.3838696479797363,
6
+ "min": 2.3838696479797363,
7
+ "max": 2.852088212966919,
8
+ "count": 5
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 24150.984375,
12
+ "min": 24150.984375,
13
+ "max": 29239.607421875,
14
+ "count": 5
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 49936.0,
18
+ "min": 9952.0,
19
+ "max": 49936.0,
20
+ "count": 5
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 49936.0,
24
+ "min": 9952.0,
25
+ "max": 49936.0,
26
+ "count": 5
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 4.238966464996338,
30
+ "min": 0.4837804436683655,
31
+ "max": 4.238966464996338,
32
+ "count": 5
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 822.3594970703125,
36
+ "min": 93.85340881347656,
37
+ "max": 822.3594970703125,
38
+ "count": 5
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
+ "count": 5
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
+ "value": 8756.0,
48
  "min": 8756.0,
49
  "max": 10945.0,
50
+ "count": 5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.07191764903608618,
54
+ "min": 0.06578410346079253,
55
+ "max": 0.07402498377213143,
56
+ "count": 5
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.2876705961443447,
60
+ "min": 0.2667634130807082,
61
+ "max": 0.3701249188606572,
62
+ "count": 5
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.2919054653714685,
66
+ "min": 0.12397497212833854,
67
+ "max": 0.2919054653714685,
68
+ "count": 5
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 1.167621861485874,
72
+ "min": 0.49589988851335415,
73
+ "max": 1.3578723143128786,
74
+ "count": 5
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
+ "value": 2.9928090024000003e-05,
78
+ "min": 2.9928090024000003e-05,
79
+ "max": 0.00026752801082399996,
80
+ "count": 5
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
+ "value": 0.00011971236009600001,
84
+ "min": 0.00011971236009600001,
85
+ "max": 0.0010701120432959998,
86
+ "count": 5
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
+ "value": 0.10997600000000002,
90
+ "min": 0.10997600000000002,
91
+ "max": 0.18917599999999998,
92
+ "count": 5
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
+ "value": 0.4399040000000001,
96
+ "min": 0.4399040000000001,
97
+ "max": 0.8468800000000001,
98
+ "count": 5
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
+ "value": 0.0005078024,
102
+ "min": 0.0005078024,
103
+ "max": 0.0044598824,
104
+ "count": 5
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
107
+ "value": 0.0020312096,
108
+ "min": 0.0020312096,
109
+ "max": 0.0178395296,
110
+ "count": 5
111
+ },
112
+ "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 10.613636363636363,
114
+ "min": 3.5681818181818183,
115
+ "max": 10.613636363636363,
116
+ "count": 5
117
+ },
118
+ "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 467.0,
120
+ "min": 157.0,
121
+ "max": 518.0,
122
+ "count": 5
123
+ },
124
+ "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 10.613636363636363,
126
+ "min": 3.5681818181818183,
127
+ "max": 10.613636363636363,
128
+ "count": 5
129
+ },
130
+ "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 467.0,
132
+ "min": 157.0,
133
+ "max": 518.0,
134
+ "count": 5
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
+ "count": 5
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
+ "count": 5
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1704187512",
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",
 
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.1.2+cu121",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1704187636"
160
  },
161
+ "total": 124.60185008100001,
162
  "count": 1,
163
+ "self": 0.43392399700002215,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.0535794420000002,
167
  "count": 1,
168
+ "self": 0.0535794420000002
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 124.11434664199999,
172
  "count": 1,
173
+ "self": 0.15222619399912674,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 3.3155957490000105,
177
  "count": 1,
178
+ "self": 3.3155957490000105
179
  },
180
  "TrainerController.advance": {
181
+ "total": 120.54410353900079,
182
+ "count": 4596,
183
+ "self": 0.07507929100245292,
184
  "children": {
185
  "env_step": {
186
+ "total": 120.46902424799833,
187
+ "count": 4596,
188
+ "self": 79.75593617999624,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 40.637967126001456,
192
+ "count": 4596,
193
+ "self": 0.3947150700030875,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 40.24325205599837,
197
+ "count": 4596,
198
+ "self": 40.24325205599837
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.07512094200063757,
204
+ "count": 4596,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 123.74857979400173,
209
+ "count": 4596,
210
  "is_parallel": true,
211
+ "self": 62.84004262000326,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.004507263999983024,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.003088598000033471,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0014186659999495532,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0014186659999495532
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.07089522499995837,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0007547259999114431,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0005386290000046756,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0005386290000046756
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.06747432200000958,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.06747432200000958
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.002127548000032675,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0004281170000695056,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0016994309999631696,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0016994309999631696
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 60.90853717399847,
271
+ "count": 4595,
272
  "is_parallel": true,
273
+ "self": 2.876464373998715,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 1.443413275000978,
277
+ "count": 4595,
278
  "is_parallel": true,
279
+ "self": 1.443413275000978
280
  },
281
  "communicator.exchange": {
282
+ "total": 47.18857699599715,
283
+ "count": 4595,
284
  "is_parallel": true,
285
+ "self": 47.18857699599715
286
  },
287
  "steps_from_proto": {
288
+ "total": 9.400082529001622,
289
+ "count": 4595,
290
  "is_parallel": true,
291
+ "self": 1.7683065549998673,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 7.631775974001755,
295
+ "count": 45950,
296
  "is_parallel": true,
297
+ "self": 7.631775974001755
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 0.00010626100004174077,
313
  "count": 1,
314
+ "self": 0.00010626100004174077,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 118.9823660080155,
324
+ "count": 183923,
325
  "is_parallel": true,
326
+ "self": 3.989067652022868,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 66.6986308049926,
330
+ "count": 183923,
331
  "is_parallel": true,
332
+ "self": 66.56206042699262,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
+ "total": 0.1365703779999876,
336
+ "count": 1,
337
  "is_parallel": true,
338
+ "self": 0.1365703779999876
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
+ "total": 48.29466755100003,
344
+ "count": 22,
345
  "is_parallel": true,
346
+ "self": 16.629499025999735,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 31.665168525000297,
350
+ "count": 1119,
351
  "is_parallel": true,
352
+ "self": 31.665168525000297
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.10231489900002089,
364
  "count": 1,
365
+ "self": 0.0010375400000839363,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.10127735899993695,
369
  "count": 1,
370
+ "self": 0.10127735899993695
371
  }
372
  }
373
  }
run_logs/training_status.json CHANGED
@@ -2,40 +2,31 @@
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
- "steps": 49968,
6
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49968.onnx",
7
- "reward": 9.272727272727273,
8
- "creation_time": 1704183039.6224968,
9
  "auxillary_file_paths": [
10
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-49968.pt"
11
  ]
12
  },
13
  {
14
- "steps": 99992,
15
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99992.onnx",
16
- "reward": null,
17
- "creation_time": 1704183164.4669566,
18
  "auxillary_file_paths": [
19
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-99992.pt"
20
- ]
21
- },
22
- {
23
- "steps": 100056,
24
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-100056.onnx",
25
- "reward": null,
26
- "creation_time": 1704183164.5897987,
27
- "auxillary_file_paths": [
28
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-100056.pt"
29
  ]
30
  }
31
  ],
32
  "final_checkpoint": {
33
- "steps": 100056,
34
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
35
- "reward": null,
36
- "creation_time": 1704183164.5897987,
37
  "auxillary_file_paths": [
38
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-100056.pt"
39
  ]
40
  }
41
  },
 
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
+ "steps": 49936,
6
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
+ "reward": 10.454545454545455,
8
+ "creation_time": 1704187636.325546,
9
  "auxillary_file_paths": [
10
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
11
  ]
12
  },
13
  {
14
+ "steps": 50128,
15
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-50128.onnx",
16
+ "reward": 10.454545454545455,
17
+ "creation_time": 1704187636.4891336,
18
  "auxillary_file_paths": [
19
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-50128.pt"
 
 
 
 
 
 
 
 
 
20
  ]
21
  }
22
  ],
23
  "final_checkpoint": {
24
+ "steps": 50128,
25
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
26
+ "reward": 10.454545454545455,
27
+ "creation_time": 1704187636.4891336,
28
  "auxillary_file_paths": [
29
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-50128.pt"
30
  ]
31
  }
32
  },