Hugging Face's logo

HadrienCr
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
HadrienCr commited on
Commit
bea9dcd
·
verified ·
1 Parent(s): c159fdc

Deep RL Course 2nd try

Browse files
Files changed (14) hide show
  1. SnowballTarget.onnx +2 -2
  2. SnowballTarget/SnowballTarget-100408.onnx +2 -2
  3. SnowballTarget/SnowballTarget-100408.pt +2 -2
  4. SnowballTarget/SnowballTarget-49936.onnx +2 -2
  5. SnowballTarget/SnowballTarget-49936.pt +2 -2
  6. SnowballTarget/SnowballTarget-99960.onnx +2 -2
  7. SnowballTarget/SnowballTarget-99960.pt +2 -2
  8. SnowballTarget/checkpoint.pt +2 -2
  9. SnowballTarget/events.out.tfevents.1719035001.c032e391e02e.9091.0 +3 -0
  10. config.json +1 -1
  11. configuration.yaml +3 -3
  12. run_logs/Player-0.log +5 -8
  13. run_logs/timers.json +140 -140
  14. run_logs/training_status.json +8 -8
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec052258055c506159ca657d3003d16cb392d58a307e943ecd9107ed1f55ac8a
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:896e725cc0349fa3fd91341e09c51055e297aa4dfe21d170488645918778af80
3
+ size 331587
SnowballTarget/SnowballTarget-100408.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec052258055c506159ca657d3003d16cb392d58a307e943ecd9107ed1f55ac8a
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:896e725cc0349fa3fd91341e09c51055e297aa4dfe21d170488645918778af80
3
+ size 331587
SnowballTarget/SnowballTarget-100408.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:29850c12ff293cbfbe4e495001eeeb9935dcdfe06f683ab2e6aef019dfaa3864
3
- size 3850075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffc19dc0ddb01732d792cfafd051558064d0b967b9e5250d0fc2f090117ade2a
3
+ size 1945995
SnowballTarget/SnowballTarget-49936.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8067103560ce037e4800a70955c676c2aa1bbb7dce617575bc8a8c03a2070438
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cecf764be80e9dbf3c176c8f55f8cc36e5b1727a2ff309dd081df4fab1a45d3
3
+ size 331587
SnowballTarget/SnowballTarget-49936.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d1ae2f8d30bef38092ca8f1ff303ae55aea61beafa158d06229b704611935ea1
3
- size 3850000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a05dbac9f7a7e28c86b958e6b1be4ddb791626622af3decd967278de0feec5c
3
+ size 1945904
SnowballTarget/SnowballTarget-99960.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec052258055c506159ca657d3003d16cb392d58a307e943ecd9107ed1f55ac8a
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:896e725cc0349fa3fd91341e09c51055e297aa4dfe21d170488645918778af80
3
+ size 331587
SnowballTarget/SnowballTarget-99960.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ad473f2a04035d8f04c82a08e98ed4b8a3fa0b51fc160de6b53e451b70c9acc
3
- size 3850000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7469bf4fc633cf955952d71988d96a18863dd7a6d663d010b80ecbe4e2766cc8
3
+ size 1945904
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eb1f13abc6af8aa0925153b373f30975ccde1785bf54d18d039be13035432626
3
- size 3849250
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9ffc836b6f8eecefba35dbf2cf33bfa08478709308932fd0f7d4881b49ecff6
3
+ size 1944994
SnowballTarget/events.out.tfevents.1719035001.c032e391e02e.9091.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcf541f02d2f11767cd44a66d9f82f072d6dd5772345860ccf9e95240f8fbc45
3
+ size 20533
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": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
 
1
+ {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 4096, "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": 128, "num_layers": 3, "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": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -4,7 +4,7 @@ behaviors:
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
@@ -17,8 +17,8 @@ behaviors:
17
  checkpoint_interval: 50000
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
 
4
  trainer_type: ppo
5
  hyperparameters:
6
  batch_size: 128
7
+ buffer_size: 4096
8
  learning_rate: 0.0003
9
  beta: 0.005
10
  epsilon: 0.2
 
17
  checkpoint_interval: 50000
18
  network_settings:
19
  normalize: false
20
+ hidden_units: 128
21
+ num_layers: 3
22
  vis_encode_type: simple
23
  memory: null
24
  goal_conditioning_type: hyper
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 0.099 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: 0.697229 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.
@@ -169,7 +166,7 @@ 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
@@ -213,10 +210,10 @@ 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]: 2392 frames, [64.0 KB-128.0 KB]: 349 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
- Peak Allocated memory 66.7 KB
220
  Peak Large allocation bytes 0 B
221
  [ALLOC_GFX_THREAD]
222
  Peak usage frame count: [32.0 KB-64.0 KB]: 2741 frames
 
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 0.086 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: 0.744692 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.
 
166
  Peak Allocated Bytes 0 B
167
  Overflow Count 0
168
  [ALLOC_DEFAULT] Dual Thread Allocator
169
+ Peak main deferred allocation count 44
170
  [ALLOC_BUCKET]
171
  Large Block size 4.0 MB
172
  Used Block count 1
 
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]: 2058 frames, [64.0 KB-128.0 KB]: 683 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
+ Peak Allocated memory 66.8 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
  Peak usage frame count: [32.0 KB-64.0 KB]: 2741 frames
run_logs/timers.json CHANGED
@@ -2,15 +2,15 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 1.6545395851135254,
6
- "min": 1.6545395851135254,
7
- "max": 2.865912914276123,
8
  "count": 10
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 16853.140625,
12
- "min": 16853.140625,
13
- "max": 29475.9140625,
14
  "count": 10
15
  },
16
  "SnowballTarget.Step.mean": {
@@ -26,15 +26,15 @@
26
  "count": 10
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 9.161903381347656,
30
- "min": 0.3639596402645111,
31
- "max": 9.161903381347656,
32
  "count": 10
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 1869.0283203125,
36
- "min": 70.60816955566406,
37
- "max": 1869.0283203125,
38
  "count": 10
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
@@ -49,88 +49,88 @@
49
  "max": 10945.0,
50
  "count": 10
51
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
- "value": 0.06668726046298296,
54
- "min": 0.06566922007512081,
55
- "max": 0.07467531853556056,
56
  "count": 10
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.3334363023149148,
60
- "min": 0.2677655371906653,
61
- "max": 0.3551044942635367,
62
  "count": 10
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.2572032511818643,
66
- "min": 0.122001881134815,
67
- "max": 0.2861780487731392,
68
  "count": 10
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 1.2860162559093216,
72
- "min": 0.48800752453926,
73
- "max": 1.3895678444235933,
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": 19.90909090909091,
114
- "min": 3.659090909090909,
115
- "max": 19.90909090909091,
116
- "count": 10
117
- },
118
- "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1095.0,
120
- "min": 161.0,
121
- "max": 1095.0,
122
- "count": 10
123
- },
124
- "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 19.90909090909091,
126
- "min": 3.659090909090909,
127
- "max": 19.90909090909091,
128
- "count": 10
129
- },
130
- "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1095.0,
132
- "min": 161.0,
133
- "max": 1095.0,
134
  "count": 10
135
  },
136
  "SnowballTarget.IsTraining.mean": {
@@ -148,7 +148,7 @@
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1719033731",
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 --force",
154
  "mlagents_version": "1.1.0.dev0",
@@ -156,59 +156,59 @@
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.3.0+cu121",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1719033955"
160
  },
161
- "total": 224.69840804800003,
162
  "count": 1,
163
- "self": 0.43245920100002877,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.0769518119999475,
167
  "count": 1,
168
- "self": 0.0769518119999475
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 224.18899703500006,
172
  "count": 1,
173
- "self": 0.5460637679990441,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 3.0302591349999375,
177
  "count": 1,
178
- "self": 3.0302591349999375
179
  },
180
  "TrainerController.advance": {
181
- "total": 220.51003486000127,
182
- "count": 9135,
183
- "self": 0.13079704700112416,
184
  "children": {
185
  "env_step": {
186
- "total": 220.37923781300015,
187
- "count": 9135,
188
- "self": 142.10116460199583,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 78.13666314100203,
192
- "count": 9135,
193
- "self": 0.709724793006103,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 77.42693834799593,
197
- "count": 9135,
198
- "self": 77.42693834799593
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.14141007000228,
204
- "count": 9135,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 223.33572198400668,
209
- "count": 9135,
210
  "is_parallel": true,
211
- "self": 114.77791775600201,
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": 0.007909454000014193,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.00648123700011638,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0014282169998978134,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0014282169998978134
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.03553736200001367,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0006540329999324968,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.0004143720000229223,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.0004143720000229223
244
  },
245
  "communicator.exchange": {
246
- "total": 0.0326149100000066,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.0326149100000066
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0018540470000516507,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.0003548190002220508,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0014992279998295999,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0014992279998295999
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 108.55780422800467,
271
- "count": 9134,
272
  "is_parallel": true,
273
- "self": 4.9432859259984525,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 2.6019552990039756,
277
- "count": 9134,
278
  "is_parallel": true,
279
- "self": 2.6019552990039756
280
  },
281
  "communicator.exchange": {
282
- "total": 85.07568894199892,
283
- "count": 9134,
284
  "is_parallel": true,
285
- "self": 85.07568894199892
286
  },
287
  "steps_from_proto": {
288
- "total": 15.936874061003323,
289
- "count": 9134,
290
  "is_parallel": true,
291
- "self": 2.9845476230069607,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 12.952326437996362,
295
- "count": 91340,
296
  "is_parallel": true,
297
- "self": 12.952326437996362
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 0.0003972689999045542,
313
  "count": 1,
314
- "self": 0.0003972689999045542,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,36 +320,36 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 218.30389485791818,
324
- "count": 321791,
325
  "is_parallel": true,
326
- "self": 6.38754597197601,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 120.7924449289419,
330
- "count": 321791,
331
  "is_parallel": true,
332
- "self": 120.39559686894188,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
- "total": 0.3968480600000248,
336
  "count": 2,
337
  "is_parallel": true,
338
- "self": 0.3968480600000248
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
- "total": 91.12390395700027,
344
- "count": 45,
345
  "is_parallel": true,
346
- "self": 28.05040366300102,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
- "total": 63.073500293999246,
350
- "count": 2292,
351
  "is_parallel": true,
352
- "self": 63.073500293999246
353
  }
354
  }
355
  }
@@ -360,14 +360,14 @@
360
  }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.10224200299990116,
364
  "count": 1,
365
- "self": 0.0010237589997359464,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.10121824400016521,
369
  "count": 1,
370
- "self": 0.10121824400016521
371
  }
372
  }
373
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 2.0896008014678955,
6
+ "min": 2.0896008014678955,
7
+ "max": 2.8781380653381348,
8
  "count": 10
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 21307.66015625,
12
+ "min": 20771.3203125,
13
+ "max": 29475.01171875,
14
  "count": 10
15
  },
16
  "SnowballTarget.Step.mean": {
 
26
  "count": 10
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 5.565084457397461,
30
+ "min": 0.17080172896385193,
31
+ "max": 5.565084457397461,
32
  "count": 10
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 1135.2772216796875,
36
+ "min": 33.135536193847656,
37
+ "max": 1135.2772216796875,
38
  "count": 10
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
 
49
  "max": 10945.0,
50
  "count": 10
51
  },
52
+ "SnowballTarget.Environment.CumulativeReward.mean": {
53
+ "value": 13.8,
54
+ "min": 3.1363636363636362,
55
+ "max": 13.8,
56
+ "count": 10
57
+ },
58
+ "SnowballTarget.Environment.CumulativeReward.sum": {
59
+ "value": 759.0,
60
+ "min": 138.0,
61
+ "max": 759.0,
62
+ "count": 10
63
+ },
64
+ "SnowballTarget.Policy.ExtrinsicReward.mean": {
65
+ "value": 13.8,
66
+ "min": 3.1363636363636362,
67
+ "max": 13.8,
68
+ "count": 10
69
+ },
70
+ "SnowballTarget.Policy.ExtrinsicReward.sum": {
71
+ "value": 759.0,
72
+ "min": 138.0,
73
+ "max": 759.0,
74
+ "count": 10
75
+ },
76
  "SnowballTarget.Losses.PolicyLoss.mean": {
77
+ "value": 0.077521520225798,
78
+ "min": 0.06467075724332758,
79
+ "max": 0.077521520225798,
80
  "count": 10
81
  },
82
  "SnowballTarget.Losses.PolicyLoss.sum": {
83
+ "value": 0.155043040451596,
84
+ "min": 0.12934151448665515,
85
+ "max": 0.20724409716814418,
86
  "count": 10
87
  },
88
  "SnowballTarget.Losses.ValueLoss.mean": {
89
+ "value": 0.28602686633958535,
90
+ "min": 0.11679404042882538,
91
+ "max": 0.28602686633958535,
92
  "count": 10
93
  },
94
  "SnowballTarget.Losses.ValueLoss.sum": {
95
+ "value": 0.5720537326791707,
96
+ "min": 0.23358808085765076,
97
+ "max": 0.7956818916341837,
98
  "count": 10
99
  },
100
  "SnowballTarget.Policy.LearningRate.mean": {
101
+ "value": 1.6464094511999992e-05,
102
+ "min": 1.6464094511999992e-05,
103
+ "max": 0.00028046400651199994,
104
  "count": 10
105
  },
106
  "SnowballTarget.Policy.LearningRate.sum": {
107
+ "value": 3.2928189023999985e-05,
108
+ "min": 3.2928189023999985e-05,
109
+ "max": 0.0005839921053360001,
110
  "count": 10
111
  },
112
  "SnowballTarget.Policy.Epsilon.mean": {
113
+ "value": 0.10548799999999997,
114
+ "min": 0.10548799999999997,
115
+ "max": 0.19348800000000005,
116
  "count": 10
117
  },
118
  "SnowballTarget.Policy.Epsilon.sum": {
119
+ "value": 0.21097599999999994,
120
+ "min": 0.21097599999999994,
121
+ "max": 0.4946640000000001,
122
  "count": 10
123
  },
124
  "SnowballTarget.Policy.Beta.mean": {
125
  "value": 0.0002838512,
126
  "min": 0.0002838512,
127
+ "max": 0.0046750512,
128
  "count": 10
129
  },
130
  "SnowballTarget.Policy.Beta.sum": {
131
+ "value": 0.0005677024,
132
+ "min": 0.0005677024,
133
+ "max": 0.009743733600000004,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
134
  "count": 10
135
  },
136
  "SnowballTarget.IsTraining.mean": {
 
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1719035000",
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 --force",
154
  "mlagents_version": "1.1.0.dev0",
 
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.3.0+cu121",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1719035231"
160
  },
161
+ "total": 231.1935535309999,
162
  "count": 1,
163
+ "self": 0.42512272800013307,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.05121374600003037,
167
  "count": 1,
168
+ "self": 0.05121374600003037
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 230.71721705699974,
172
  "count": 1,
173
+ "self": 0.313961196010041,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 2.1678631690001566,
177
  "count": 1,
178
+ "self": 2.1678631690001566
179
  },
180
  "TrainerController.advance": {
181
+ "total": 228.1420507909893,
182
+ "count": 9136,
183
+ "self": 0.13254497699517742,
184
  "children": {
185
  "env_step": {
186
+ "total": 228.0095058139941,
187
+ "count": 9136,
188
+ "self": 157.48329376299944,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 70.39158679798129,
192
+ "count": 9136,
193
+ "self": 0.6971241959809049,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 69.69446260200039,
197
+ "count": 9136,
198
+ "self": 69.69446260200039
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.13462525301338246,
204
+ "count": 9136,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 230.01476085700733,
209
+ "count": 9136,
210
  "is_parallel": true,
211
+ "self": 120.64642620004179,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.0020915219997732493,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0006469720001405221,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0014445499996327271,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0014445499996327271
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.03532054499964943,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0006808919997638441,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.00038987700008874526,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.00038987700008874526
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.03237776700007089,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.03237776700007089
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0018720089997259493,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0003487399994810403,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.001523269000244909,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.001523269000244909
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 109.36833465696554,
271
+ "count": 9135,
272
  "is_parallel": true,
273
+ "self": 4.979603768009383,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 2.6678287209888367,
277
+ "count": 9135,
278
  "is_parallel": true,
279
+ "self": 2.6678287209888367
280
  },
281
  "communicator.exchange": {
282
+ "total": 85.64176659998293,
283
+ "count": 9135,
284
  "is_parallel": true,
285
+ "self": 85.64176659998293
286
  },
287
  "steps_from_proto": {
288
+ "total": 16.079135567984395,
289
+ "count": 9135,
290
  "is_parallel": true,
291
+ "self": 2.954485399956411,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 13.124650168027983,
295
+ "count": 91350,
296
  "is_parallel": true,
297
+ "self": 13.124650168027983
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 0.0002983570002470515,
313
  "count": 1,
314
+ "self": 0.0002983570002470515,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 224.79246962912157,
324
+ "count": 420750,
325
  "is_parallel": true,
326
+ "self": 8.413199142081794,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 148.7846739390393,
330
+ "count": 420750,
331
  "is_parallel": true,
332
+ "self": 148.46090210403918,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
+ "total": 0.32377183500011597,
336
  "count": 2,
337
  "is_parallel": true,
338
+ "self": 0.32377183500011597
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
+ "total": 67.59459654800048,
344
+ "count": 22,
345
  "is_parallel": true,
346
+ "self": 23.149594113990588,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 44.44500243400989,
350
+ "count": 2241,
351
  "is_parallel": true,
352
+ "self": 44.44500243400989
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.09304354400001102,
364
  "count": 1,
365
+ "self": 0.0009155469997494947,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.09212799700026153,
369
  "count": 1,
370
+ "self": 0.09212799700026153
371
  }
372
  }
373
  }
run_logs/training_status.json CHANGED
@@ -4,8 +4,8 @@
4
  {
5
  "steps": 49936,
6
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 13.272727272727273,
8
- "creation_time": 1719033845.1762831,
9
  "auxillary_file_paths": [
10
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
11
  ]
@@ -13,8 +13,8 @@
13
  {
14
  "steps": 99960,
15
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
16
- "reward": 20.181818181818183,
17
- "creation_time": 1719033954.8887966,
18
  "auxillary_file_paths": [
19
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
@@ -22,8 +22,8 @@
22
  {
23
  "steps": 100408,
24
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-100408.onnx",
25
- "reward": 20.181818181818183,
26
- "creation_time": 1719033955.26789,
27
  "auxillary_file_paths": [
28
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-100408.pt"
29
  ]
@@ -32,8 +32,8 @@
32
  "final_checkpoint": {
33
  "steps": 100408,
34
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
35
- "reward": 20.181818181818183,
36
- "creation_time": 1719033955.26789,
37
  "auxillary_file_paths": [
38
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-100408.pt"
39
  ]
 
4
  {
5
  "steps": 49936,
6
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
+ "reward": 11.0,
8
+ "creation_time": 1719035118.8526025,
9
  "auxillary_file_paths": [
10
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
11
  ]
 
13
  {
14
  "steps": 99960,
15
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
16
+ "reward": 13.636363636363637,
17
+ "creation_time": 1719035231.2753816,
18
  "auxillary_file_paths": [
19
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
 
22
  {
23
  "steps": 100408,
24
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-100408.onnx",
25
+ "reward": 13.636363636363637,
26
+ "creation_time": 1719035231.4224975,
27
  "auxillary_file_paths": [
28
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-100408.pt"
29
  ]
 
32
  "final_checkpoint": {
33
  "steps": 100408,
34
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
35
+ "reward": 13.636363636363637,
36
+ "creation_time": 1719035231.4224975,
37
  "auxillary_file_paths": [
38
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-100408.pt"
39
  ]