Hugging Face's logo

haolx
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
haolx commited on
Commit
68f0c90
·
verified ·
1 Parent(s): 142a82f

First Push

Browse files
Files changed (21) hide show
  1. SnowballTarget.onnx +2 -2
  2. SnowballTarget/SnowballTarget-200112.onnx +2 -2
  3. SnowballTarget/SnowballTarget-200112.pt +2 -2
  4. SnowballTarget/SnowballTarget-249984.onnx +3 -0
  5. SnowballTarget/SnowballTarget-249984.pt +3 -0
  6. SnowballTarget/SnowballTarget-299944.onnx +3 -0
  7. SnowballTarget/SnowballTarget-299944.pt +3 -0
  8. SnowballTarget/SnowballTarget-349968.onnx +3 -0
  9. SnowballTarget/SnowballTarget-349968.pt +3 -0
  10. SnowballTarget/SnowballTarget-399968.onnx +3 -0
  11. SnowballTarget/SnowballTarget-399968.pt +3 -0
  12. SnowballTarget/SnowballTarget-400224.onnx +3 -0
  13. SnowballTarget/SnowballTarget-400224.pt +3 -0
  14. SnowballTarget/checkpoint.pt +2 -2
  15. SnowballTarget/events.out.tfevents.1706586587.64f70067c60d.6658.0 +3 -0
  16. SnowballTarget/events.out.tfevents.1706586651.64f70067c60d.6984.0 +3 -0
  17. config.json +1 -1
  18. configuration.yaml +3 -3
  19. run_logs/Player-0.log +5 -8
  20. run_logs/timers.json +135 -135
  21. run_logs/training_status.json +58 -13
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aea0441032f0bbd0baaf11a4ca41429a93264db22dd40b1b685f4ca27f2ce8a0
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7de8e61718c0d3b83cd0bd296f1e9ed631cd2296a23843e60d8b03b8d3cef4d9
3
+ size 1178864
SnowballTarget/SnowballTarget-200112.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aea0441032f0bbd0baaf11a4ca41429a93264db22dd40b1b685f4ca27f2ce8a0
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e55ecbef98674628f2cbb3468df640ed49c1e7fea012c74fbf1d9067c36af96
3
+ size 1177899
SnowballTarget/SnowballTarget-200112.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e60f12a2417ca8ca54268ff04dd683d18401d7fd3a5a08bcb42cbcd238816dcc
3
- size 3850075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dca1a50bc723fcbdf15080845d455a677a02934fc9e18be24974a71d83873f6
3
+ size 2342243
SnowballTarget/SnowballTarget-249984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7dde4581d9b88a82ece2438d9b3c0a9329120a24fc38de85e992eb06ff0fad7
3
+ size 1178864
SnowballTarget/SnowballTarget-249984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6638b2e4283e7ae9e64f5a1662cb85cec9814c652a718b6cc1b86d5a6fbe5be1
3
+ size 7018622
SnowballTarget/SnowballTarget-299944.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71d12875e92651c02e3e847b0dbf42d879c500d61bb3022314925ba84a742e91
3
+ size 1178864
SnowballTarget/SnowballTarget-299944.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb2e799d258c8d73a6219e105f5196d97c1679e556f49dd549d7110a8e79286e
3
+ size 7018622
SnowballTarget/SnowballTarget-349968.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:340c5a6e9ebd7a8c7f235df4ef6e41c98e01bd4e88d65864e91bf72366a5fdcc
3
+ size 1178864
SnowballTarget/SnowballTarget-349968.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8fc4fe71537b69da9e0203d58c388d101dc73f7dec45434cbb41ffe972bb96f
3
+ size 7018622
SnowballTarget/SnowballTarget-399968.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7de8e61718c0d3b83cd0bd296f1e9ed631cd2296a23843e60d8b03b8d3cef4d9
3
+ size 1178864
SnowballTarget/SnowballTarget-399968.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0fdd5ebf8c3cc8f31b32307cdffbcd8226893e4c8ff15baca2fef57e38b8bd8
3
+ size 7018622
SnowballTarget/SnowballTarget-400224.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7de8e61718c0d3b83cd0bd296f1e9ed631cd2296a23843e60d8b03b8d3cef4d9
3
+ size 1178864
SnowballTarget/SnowballTarget-400224.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:669d417c3b0e9b179ff392ce8d7b74a88856fa664896b21352e57cce9e7e37cd
3
+ size 7018622
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5cee364ef680cc084f26dad581ab9761f19748bcce33e79a656aaac58ac3eee7
3
- size 3849250
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64d85691043578f273f492e7a535a37b1391a15d7b9e836df1863ce13b7bae5f
3
+ size 7017445
SnowballTarget/events.out.tfevents.1706586587.64f70067c60d.6658.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05cd256de86814088408d0599f04266b38513f6f2f790961de63865ba8681816
3
+ size 1114
SnowballTarget/events.out.tfevents.1706586651.64f70067c60d.6984.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c66f69d8d5be37e2328ab5a9e2c042c3a0a4744cd4b9ae192bf8c079eab1de0
3
+ size 23247
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
 
1
+ {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 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": 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": 400000, "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": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -18,7 +18,7 @@ behaviors:
18
  network_settings:
19
  normalize: false
20
  hidden_units: 256
21
- num_layers: 2
22
  vis_encode_type: simple
23
  memory: null
24
  goal_conditioning_type: hyper
@@ -38,7 +38,7 @@ behaviors:
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
- max_steps: 200000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: true
@@ -69,7 +69,7 @@ checkpoint_settings:
69
  run_id: SnowballTarget1
70
  initialize_from: null
71
  load_model: false
72
- resume: false
73
  force: false
74
  train_model: false
75
  inference: false
 
18
  network_settings:
19
  normalize: false
20
  hidden_units: 256
21
+ num_layers: 4
22
  vis_encode_type: simple
23
  memory: null
24
  goal_conditioning_type: hyper
 
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
+ max_steps: 400000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: true
 
69
  run_id: SnowballTarget1
70
  initialize_from: null
71
  load_model: false
72
+ resume: true
73
  force: false
74
  train_model: false
75
  inference: false
run_logs/Player-0.log CHANGED
@@ -2,9 +2,6 @@ Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarge
2
  Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
3
  Preloaded 'lib_burst_generated.so'
4
  Preloaded 'libgrpc_csharp_ext.x64.so'
5
- PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face
6
- PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face/SnowballTarget
7
- Unable to load player prefs
8
  Initialize engine version: 2021.3.14f1 (eee1884e7226)
9
  [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
10
  Forcing GfxDevice: Null
@@ -34,7 +31,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
34
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
35
  FMOD initialized on nosound output
36
  Begin MonoManager ReloadAssembly
37
- - Completed reload, in 0.101 seconds
38
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
39
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
40
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -45,7 +42,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
45
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
46
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
47
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
48
- UnloadTime: 0.894757 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.
@@ -178,13 +175,13 @@ Memory Statistics:
178
  Peak usage frame count: [4.0 MB-8.0 MB]: 5460 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
- Peak Allocated memory 6.6 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
  Peak usage frame count: [16.0 MB-32.0 MB]: 5460 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
- Peak Allocated memory 17.9 MB
188
  Peak Large allocation bytes 16.0 MB
189
  [ALLOC_TEMP_JOB_1_FRAME]
190
  Initial Block Size 2.0 MB
@@ -213,7 +210,7 @@ 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]: 5253 frames, [64.0 KB-128.0 KB]: 207 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
  Peak Allocated memory 66.0 KB
 
2
  Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
3
  Preloaded 'lib_burst_generated.so'
4
  Preloaded 'libgrpc_csharp_ext.x64.so'
 
 
 
5
  Initialize engine version: 2021.3.14f1 (eee1884e7226)
6
  [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
7
  Forcing GfxDevice: Null
 
31
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
32
  FMOD initialized on nosound output
33
  Begin MonoManager ReloadAssembly
34
+ - Completed reload, in 0.093 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: 0.841640 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.
 
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 17.8 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]: 5257 frames, [64.0 KB-128.0 KB]: 203 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
  Peak Allocated memory 66.0 KB
run_logs/timers.json CHANGED
@@ -2,39 +2,39 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 0.9640917181968689,
6
- "min": 0.9640917181968689,
7
- "max": 2.875121831893921,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 9194.54296875,
12
- "min": 9194.54296875,
13
- "max": 29475.748046875,
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": 13.0621919631958,
30
- "min": 0.2580852210521698,
31
- "max": 13.0621919631958,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2547.12744140625,
36
- "min": 50.06853485107422,
37
- "max": 2632.72509765625,
38
  "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
@@ -50,87 +50,87 @@
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
- "value": 0.07620219156310401,
54
- "min": 0.058910317715772716,
55
- "max": 0.07620219156310401,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.30480876625241604,
60
- "min": 0.23564127086309086,
61
- "max": 0.36918028767047195,
62
  "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.1935376073507702,
66
- "min": 0.10430312625762514,
67
- "max": 0.30434047576843526,
68
  "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.7741504294030808,
72
- "min": 0.41721250503050056,
73
- "max": 1.5160913888145895,
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": 25.454545454545453,
114
- "min": 3.022727272727273,
115
- "max": 25.78181818181818,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1120.0,
120
- "min": 133.0,
121
- "max": 1418.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 25.454545454545453,
126
- "min": 3.022727272727273,
127
- "max": 25.78181818181818,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1120.0,
132
- "min": 133.0,
133
- "max": 1418.0,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
@@ -148,67 +148,67 @@
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1706585821",
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": "2.1.2+cu121",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1706586320"
160
  },
161
- "total": 498.938967403,
162
  "count": 1,
163
- "self": 0.5930980260000069,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.06141591299990523,
167
  "count": 1,
168
- "self": 0.06141591299990523
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 498.2844534640001,
172
  "count": 1,
173
- "self": 0.7128704429934487,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 3.9214750250000634,
177
  "count": 1,
178
- "self": 3.9214750250000634
179
  },
180
  "TrainerController.advance": {
181
- "total": 493.55023995700674,
182
- "count": 18198,
183
- "self": 0.3701143110024532,
184
  "children": {
185
  "env_step": {
186
- "total": 493.1801256460043,
187
- "count": 18198,
188
- "self": 326.14169851899044,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 166.69239135500163,
192
- "count": 18198,
193
- "self": 1.6520208929865703,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 165.04037046201506,
197
- "count": 18198,
198
- "self": 165.04037046201506
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.3460357720122147,
204
- "count": 18198,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 496.8587532680011,
209
- "count": 18198,
210
  "is_parallel": true,
211
- "self": 242.92099891199825,
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": 0.005800985000064429,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.003589930000202912,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.002211054999861517,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.002211054999861517
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.04478171999994629,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0007815909998498682,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.0005036119999886068,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.0005036119999886068
244
  },
245
  "communicator.exchange": {
246
- "total": 0.041240630000061174,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.041240630000061174
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0022558870000466413,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.0004436040003383823,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.001812282999708259,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.001812282999708259
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 253.93775435600287,
271
- "count": 18197,
272
  "is_parallel": true,
273
- "self": 11.717513592010505,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 5.80607967000708,
277
- "count": 18197,
278
  "is_parallel": true,
279
- "self": 5.80607967000708
280
  },
281
  "communicator.exchange": {
282
- "total": 199.6506076370058,
283
- "count": 18197,
284
  "is_parallel": true,
285
- "self": 199.6506076370058
286
  },
287
  "steps_from_proto": {
288
- "total": 36.76355345697948,
289
- "count": 18197,
290
  "is_parallel": true,
291
- "self": 7.211129860025494,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 29.552423596953986,
295
- "count": 181970,
296
  "is_parallel": true,
297
- "self": 29.552423596953986
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 4.622200003723265e-05,
313
  "count": 1,
314
- "self": 4.622200003723265e-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": 487.30327751295226,
324
- "count": 745202,
325
  "is_parallel": true,
326
- "self": 16.026501295877665,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 269.20563459607524,
330
- "count": 745202,
331
  "is_parallel": true,
332
- "self": 268.6841391000754,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
- "total": 0.5214954959998295,
336
  "count": 4,
337
  "is_parallel": true,
338
- "self": 0.5214954959998295
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
- "total": 202.07114162099936,
344
  "count": 90,
345
  "is_parallel": true,
346
- "self": 61.49067776899642,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
- "total": 140.58046385200294,
350
  "count": 4587,
351
  "is_parallel": true,
352
- "self": 140.58046385200294
353
  }
354
  }
355
  }
@@ -360,14 +360,14 @@
360
  }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.09982181699979265,
364
  "count": 1,
365
- "self": 0.0011567599997306388,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.098665057000062,
369
  "count": 1,
370
- "self": 0.098665057000062
371
  }
372
  }
373
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.8955487012863159,
6
+ "min": 0.8948118686676025,
7
+ "max": 2.853564739227295,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 9053.1015625,
12
+ "min": 8701.150390625,
13
+ "max": 29223.357421875,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 399968.0,
18
+ "min": 209936.0,
19
+ "max": 399968.0,
20
  "count": 20
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 399968.0,
24
+ "min": 209936.0,
25
+ "max": 399968.0,
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 13.22802734375,
30
+ "min": 0.2574637532234192,
31
+ "max": 13.2938232421875,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2579.46533203125,
36
+ "min": 49.433040618896484,
37
+ "max": 2711.93994140625,
38
  "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
 
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.07011461774013963,
54
+ "min": 0.06358130356124556,
55
+ "max": 0.07595940214380914,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.28045847096055854,
60
+ "min": 0.2543252142449822,
61
+ "max": 0.3797970107190457,
62
  "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.21542924686389808,
66
+ "min": 0.1385706035470517,
67
+ "max": 0.30058827799032717,
68
  "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.8617169874555923,
72
+ "min": 0.5542824141882068,
73
+ "max": 1.391813202231538,
74
  "count": 20
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
+ "value": 3.957098681000002e-06,
78
+ "min": 3.957098681000002e-06,
79
+ "max": 0.000145857051381,
80
  "count": 20
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
+ "value": 1.582839472400001e-05,
84
+ "min": 1.582839472400001e-05,
85
+ "max": 0.00069216026928,
86
  "count": 20
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
+ "value": 0.101319,
90
+ "min": 0.101319,
91
+ "max": 0.14861900000000003,
92
  "count": 20
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
+ "value": 0.405276,
96
+ "min": 0.405276,
97
+ "max": 0.73072,
98
  "count": 20
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
+ "value": 7.581810000000006e-05,
102
+ "min": 7.581810000000006e-05,
103
+ "max": 0.0024360881000000003,
104
  "count": 20
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
107
+ "value": 0.00030327240000000024,
108
+ "min": 0.00030327240000000024,
109
+ "max": 0.011562928000000002,
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 25.704545454545453,
114
+ "min": 3.6363636363636362,
115
+ "max": 25.98181818181818,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1131.0,
120
+ "min": 160.0,
121
+ "max": 1429.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 25.704545454545453,
126
+ "min": 3.6363636363636362,
127
+ "max": 25.98181818181818,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1131.0,
132
+ "min": 160.0,
133
+ "max": 1429.0,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
 
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1706586650",
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 --resume",
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": "2.1.2+cu121",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1706587162"
160
  },
161
+ "total": 512.0949007670001,
162
  "count": 1,
163
+ "self": 0.47622578300024543,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.0539380440000059,
167
  "count": 1,
168
+ "self": 0.0539380440000059
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 511.5647369399999,
172
  "count": 1,
173
+ "self": 0.7514956730024096,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 2.3224954419999904,
177
  "count": 1,
178
+ "self": 2.3224954419999904
179
  },
180
  "TrainerController.advance": {
181
+ "total": 508.35818274799726,
182
+ "count": 18199,
183
+ "self": 0.35644740900397665,
184
  "children": {
185
  "env_step": {
186
+ "total": 508.0017353389933,
187
+ "count": 18199,
188
+ "self": 331.5146749430048,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 176.1266867020031,
192
+ "count": 18199,
193
+ "self": 1.6763091989912482,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 174.45037750301185,
197
+ "count": 18199,
198
+ "self": 174.45037750301185
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.3603736939853661,
204
+ "count": 18199,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 509.99262467098515,
209
+ "count": 18199,
210
  "is_parallel": true,
211
+ "self": 255.9905113189609,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.00214061299993773,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0006248759998470632,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0015157370000906667,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0015157370000906667
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.03927482999984022,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.000713487999746576,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.00043658399999912945,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.00043658399999912945
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.03600957499998003,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.03600957499998003
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0021151830001144845,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.00043435500015220896,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0016808279999622755,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0016808279999622755
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 254.00211335202425,
271
+ "count": 18198,
272
  "is_parallel": true,
273
+ "self": 11.615472576003185,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 5.810355305988878,
277
+ "count": 18198,
278
  "is_parallel": true,
279
+ "self": 5.810355305988878
280
  },
281
  "communicator.exchange": {
282
+ "total": 199.92710642801785,
283
+ "count": 18198,
284
  "is_parallel": true,
285
+ "self": 199.92710642801785
286
  },
287
  "steps_from_proto": {
288
+ "total": 36.64917904201434,
289
+ "count": 18198,
290
  "is_parallel": true,
291
+ "self": 7.209387495973033,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 29.439791546041306,
295
+ "count": 181980,
296
  "is_parallel": true,
297
+ "self": 29.439791546041306
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 0.0002489560001777136,
313
  "count": 1,
314
+ "self": 0.0002489560001777136,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 502.01383666296533,
324
+ "count": 762377,
325
  "is_parallel": true,
326
+ "self": 16.35181663889466,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 274.5566146790702,
330
+ "count": 762377,
331
  "is_parallel": true,
332
+ "self": 273.66009452307003,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
+ "total": 0.8965201560001788,
336
  "count": 4,
337
  "is_parallel": true,
338
+ "self": 0.8965201560001788
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
+ "total": 211.10540534500046,
344
  "count": 90,
345
  "is_parallel": true,
346
+ "self": 60.61084359299434,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 150.49456175200612,
350
  "count": 4587,
351
  "is_parallel": true,
352
+ "self": 150.49456175200612
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.1323141210000358,
364
  "count": 1,
365
+ "self": 0.002316863000032754,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.12999725800000306,
369
  "count": 1,
370
+ "self": 0.12999725800000306
371
  }
372
  }
373
  }
run_logs/training_status.json CHANGED
@@ -1,15 +1,6 @@
1
  {
2
  "SnowballTarget": {
3
  "checkpoints": [
4
- {
5
- "steps": 49936,
6
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 15.181818181818182,
8
- "creation_time": 1706585952.6417303,
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",
@@ -45,15 +36,69 @@
45
  "auxillary_file_paths": [
46
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
47
  ]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "final_checkpoint": {
51
- "steps": 200112,
52
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
53
- "reward": 24.90909090909091,
54
- "creation_time": 1706586320.2787673,
55
  "auxillary_file_paths": [
56
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },
 
1
  {
2
  "SnowballTarget": {
3
  "checkpoints": [
 
 
 
 
 
 
 
 
 
4
  {
5
  "steps": 99960,
6
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
 
36
  "auxillary_file_paths": [
37
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
38
  ]
39
+ },
40
+ {
41
+ "steps": 200112,
42
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
43
+ "reward": null,
44
+ "creation_time": 1706586589.852068,
45
+ "auxillary_file_paths": [
46
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
47
+ ]
48
+ },
49
+ {
50
+ "steps": 249984,
51
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-249984.onnx",
52
+ "reward": 18.636363636363637,
53
+ "creation_time": 1706586782.2838278,
54
+ "auxillary_file_paths": [
55
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-249984.pt"
56
+ ]
57
+ },
58
+ {
59
+ "steps": 299944,
60
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-299944.onnx",
61
+ "reward": 25.363636363636363,
62
+ "creation_time": 1706586910.081696,
63
+ "auxillary_file_paths": [
64
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-299944.pt"
65
+ ]
66
+ },
67
+ {
68
+ "steps": 349968,
69
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-349968.onnx",
70
+ "reward": 26.0,
71
+ "creation_time": 1706587036.3253357,
72
+ "auxillary_file_paths": [
73
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-349968.pt"
74
+ ]
75
+ },
76
+ {
77
+ "steps": 399968,
78
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-399968.onnx",
79
+ "reward": 25.272727272727273,
80
+ "creation_time": 1706587161.87238,
81
+ "auxillary_file_paths": [
82
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-399968.pt"
83
+ ]
84
+ },
85
+ {
86
+ "steps": 400224,
87
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-400224.onnx",
88
+ "reward": 25.272727272727273,
89
+ "creation_time": 1706587162.0471206,
90
+ "auxillary_file_paths": [
91
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-400224.pt"
92
+ ]
93
  }
94
  ],
95
  "final_checkpoint": {
96
+ "steps": 400224,
97
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
98
+ "reward": 25.272727272727273,
99
+ "creation_time": 1706587162.0471206,
100
  "auxillary_file_paths": [
101
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-400224.pt"
102
  ]
103
  }
104
  },