Cesar514 commited on
Commit
8cefb11
·
1 Parent(s): d46f80d
README.md ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ tags:
4
+ - unity-ml-agents
5
+ - ml-agents
6
+ - deep-reinforcement-learning
7
+ - reinforcement-learning
8
+ - ML-Agents-SnowballTarget
9
+ library_name: ml-agents
10
+ ---
11
+
12
+ # **ppo** Agent playing **SnowballTarget**
13
+ This is a trained model of a **ppo** agent playing **SnowballTarget** using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
14
+
15
+ ## Usage (with ML-Agents)
16
+ The Documentation: https://github.com/huggingface/ml-agents#get-started
17
+ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
18
+
19
+
20
+ ### Resume the training
21
+ ```
22
+ mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
23
+ ```
24
+ ### Watch your Agent play
25
+ You can watch your agent **playing directly in your browser:**.
26
+
27
+ 1. Go to https://huggingface.co/spaces/unity/ML-Agents-SnowballTarget
28
+ 2. Step 1: Write your model_id: Cesar514/SnowballTarget
29
+ 3. Step 2: Select your *.nn /*.onnx file
30
+ 4. Click on Watch the agent play 👀
31
+
SnowballTarget.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b7b09723c061888c21f9f03d9c902d2e2d7f48e1aa7851e08f585d2d1ee6bfa
3
+ size 645119
SnowballTarget/SnowballTarget-20504.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b7b09723c061888c21f9f03d9c902d2e2d7f48e1aa7851e08f585d2d1ee6bfa
3
+ size 645119
SnowballTarget/SnowballTarget-20504.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d801471fa3aec9192978a2e4277ff0789c62d8185d1e75de1da34c93a1368a75
3
+ size 3845592
SnowballTarget/checkpoint.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d801471fa3aec9192978a2e4277ff0789c62d8185d1e75de1da34c93a1368a75
3
+ size 3845592
SnowballTarget/events.out.tfevents.1677690909.a453ba9e88e3.2313.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8885b4ebe459a4a7e4b7b8c272668f90dbe3e740c9bde9d4db23637ae5f1b401
3
+ size 7925
config.json ADDED
@@ -0,0 +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, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "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": 0.95, "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, "checkpoint_interval": 50000, "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, "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}, "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 ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ default_settings: null
2
+ behaviors:
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
12
+ num_epoch: 3
13
+ learning_rate_schedule: linear
14
+ beta_schedule: linear
15
+ epsilon_schedule: linear
16
+ network_settings:
17
+ normalize: false
18
+ hidden_units: 256
19
+ num_layers: 2
20
+ vis_encode_type: simple
21
+ memory: null
22
+ goal_conditioning_type: hyper
23
+ deterministic: false
24
+ reward_signals:
25
+ extrinsic:
26
+ gamma: 0.95
27
+ strength: 1.0
28
+ network_settings:
29
+ normalize: false
30
+ hidden_units: 128
31
+ num_layers: 2
32
+ vis_encode_type: simple
33
+ memory: null
34
+ goal_conditioning_type: hyper
35
+ deterministic: false
36
+ init_path: null
37
+ keep_checkpoints: 10
38
+ checkpoint_interval: 50000
39
+ max_steps: 200000
40
+ time_horizon: 64
41
+ summary_freq: 10000
42
+ threaded: true
43
+ self_play: null
44
+ behavioral_cloning: null
45
+ env_settings:
46
+ env_path: ./training-envs-executables/linux/SnowballTarget/SnowballTarget
47
+ env_args: null
48
+ base_port: 5005
49
+ num_envs: 1
50
+ num_areas: 1
51
+ seed: -1
52
+ max_lifetime_restarts: 10
53
+ restarts_rate_limit_n: 1
54
+ restarts_rate_limit_period_s: 60
55
+ engine_settings:
56
+ width: 84
57
+ height: 84
58
+ quality_level: 5
59
+ time_scale: 20
60
+ target_frame_rate: -1
61
+ capture_frame_rate: 60
62
+ no_graphics: true
63
+ environment_parameters: null
64
+ checkpoint_settings:
65
+ run_id: SnowballTarget1
66
+ initialize_from: null
67
+ load_model: false
68
+ resume: false
69
+ force: false
70
+ train_model: false
71
+ inference: false
72
+ results_dir: results
73
+ torch_settings:
74
+ device: null
75
+ debug: false
run_logs/Player-0.log ADDED
@@ -0,0 +1,263 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/Managed'
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
11
+ GfxDevice: creating device client; threaded=0; jobified=0
12
+ NullGfxDevice:
13
+ Version: NULL 1.0 [1.0]
14
+ Renderer: Null Device
15
+ Vendor: Unity Technologies
16
+ ALSA lib confmisc.c:767:(parse_card) cannot find card '0'
17
+ ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_card_driver returned error: No such file or directory
18
+ ALSA lib confmisc.c:392:(snd_func_concat) error evaluating strings
19
+ ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
20
+ ALSA lib confmisc.c:1246:(snd_func_refer) error evaluating name
21
+ ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
22
+ ALSA lib conf.c:5220:(snd_config_expand) Evaluate error: No such file or directory
23
+ ALSA lib pcm.c:2642:(snd_pcm_open_noupdate) Unknown PCM default
24
+ FMOD failed to initialize the output device.: "Error initializing output device. " (60)
25
+ Forced to initialize FMOD to to the device driver's system output rate 48000, this may impact performance and/or give inconsistent experiences compared to selected sample rate 48000
26
+ ALSA lib confmisc.c:767:(parse_card) cannot find card '0'
27
+ ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_card_driver returned error: No such file or directory
28
+ ALSA lib confmisc.c:392:(snd_func_concat) error evaluating strings
29
+ ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
30
+ ALSA lib confmisc.c:1246:(snd_func_refer) error evaluating name
31
+ ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
32
+ ALSA lib conf.c:5220:(snd_config_expand) Evaluate error: No such file or directory
33
+ ALSA lib pcm.c:2642:(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 0.087 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)
41
+ WARNING: Shader Unsupported: 'Standard' - All subshaders removed
42
+ WARNING: Shader Did you use #pragma only_renderers and omit this platform?
43
+ WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
44
+ ERROR: Shader Standard 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: 0.761882 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
+ GRPC Exception: Status(StatusCode=Cancelled, Detail="CANCELLED"). Disconnecting from trainer.
52
+ Setting up 1 worker threads for Enlighten.
53
+ Memory Statistics:
54
+ [ALLOC_TEMP_TLS] TLS Allocator
55
+ StackAllocators :
56
+ [ALLOC_TEMP_MAIN]
57
+ Peak usage frame count: [8.0 KB-16.0 KB]: 557 frames, [16.0 KB-32.0 KB]: 9 frames, [2.0 MB-4.0 MB]: 1 frames
58
+ Initial Block Size 4.0 MB
59
+ Current Block Size 4.0 MB
60
+ Peak Allocated Bytes 2.0 MB
61
+ Overflow Count 0
62
+ [ALLOC_TEMP_Loading.AsyncRead]
63
+ Initial Block Size 64.0 KB
64
+ Current Block Size 64.0 KB
65
+ Peak Allocated Bytes 198 B
66
+ Overflow Count 0
67
+ [ALLOC_TEMP_Loading.PreloadManager]
68
+ Initial Block Size 256.0 KB
69
+ Current Block Size 304.0 KB
70
+ Peak Allocated Bytes 228.9 KB
71
+ Overflow Count 4
72
+ [ALLOC_TEMP_Background Job.Worker 8]
73
+ Initial Block Size 32.0 KB
74
+ Current Block Size 32.0 KB
75
+ Peak Allocated Bytes 0 B
76
+ Overflow Count 0
77
+ [ALLOC_TEMP_Background Job.Worker 9]
78
+ Initial Block Size 32.0 KB
79
+ Current Block Size 32.0 KB
80
+ Peak Allocated Bytes 0 B
81
+ Overflow Count 0
82
+ [ALLOC_TEMP_Job.Worker 0]
83
+ Initial Block Size 256.0 KB
84
+ Current Block Size 256.0 KB
85
+ Peak Allocated Bytes 3.6 KB
86
+ Overflow Count 0
87
+ [ALLOC_TEMP_Background Job.Worker 10]
88
+ Initial Block Size 32.0 KB
89
+ Current Block Size 32.0 KB
90
+ Peak Allocated Bytes 0 B
91
+ Overflow Count 0
92
+ [ALLOC_TEMP_Background Job.Worker 14]
93
+ Initial Block Size 32.0 KB
94
+ Current Block Size 32.0 KB
95
+ Peak Allocated Bytes 0 B
96
+ Overflow Count 0
97
+ [ALLOC_TEMP_Background Job.Worker 6]
98
+ Initial Block Size 32.0 KB
99
+ Current Block Size 32.0 KB
100
+ Peak Allocated Bytes 0 B
101
+ Overflow Count 0
102
+ [ALLOC_TEMP_Background Job.Worker 12]
103
+ Initial Block Size 32.0 KB
104
+ Current Block Size 32.0 KB
105
+ Peak Allocated Bytes 0 B
106
+ Overflow Count 0
107
+ [ALLOC_TEMP_EnlightenWorker]
108
+ Initial Block Size 64.0 KB
109
+ Current Block Size 64.0 KB
110
+ Peak Allocated Bytes 0 B
111
+ Overflow Count 0
112
+ [ALLOC_TEMP_Background Job.Worker 15]
113
+ Initial Block Size 32.0 KB
114
+ Current Block Size 32.0 KB
115
+ Peak Allocated Bytes 0 B
116
+ Overflow Count 0
117
+ [ALLOC_TEMP_Background Job.Worker 1]
118
+ Initial Block Size 32.0 KB
119
+ Current Block Size 32.0 KB
120
+ Peak Allocated Bytes 0 B
121
+ Overflow Count 0
122
+ [ALLOC_TEMP_Background Job.Worker 2]
123
+ Initial Block Size 32.0 KB
124
+ Current Block Size 32.0 KB
125
+ Peak Allocated Bytes 0 B
126
+ Overflow Count 0
127
+ [ALLOC_TEMP_Background Job.Worker 7]
128
+ Initial Block Size 32.0 KB
129
+ Current Block Size 32.0 KB
130
+ Peak Allocated Bytes 0 B
131
+ Overflow Count 0
132
+ [ALLOC_TEMP_AssetGarbageCollectorHelper]
133
+ Initial Block Size 64.0 KB
134
+ Current Block Size 64.0 KB
135
+ Peak Allocated Bytes 0 B
136
+ Overflow Count 0
137
+ [ALLOC_TEMP_Background Job.Worker 5]
138
+ Initial Block Size 32.0 KB
139
+ Current Block Size 32.0 KB
140
+ Peak Allocated Bytes 0 B
141
+ Overflow Count 0
142
+ [ALLOC_TEMP_Background Job.Worker 13]
143
+ Initial Block Size 32.0 KB
144
+ Current Block Size 32.0 KB
145
+ Peak Allocated Bytes 0 B
146
+ Overflow Count 0
147
+ [ALLOC_TEMP_Background Job.Worker 11]
148
+ Initial Block Size 32.0 KB
149
+ Current Block Size 32.0 KB
150
+ Peak Allocated Bytes 0 B
151
+ Overflow Count 0
152
+ [ALLOC_TEMP_Background Job.Worker 3]
153
+ Initial Block Size 32.0 KB
154
+ Current Block Size 32.0 KB
155
+ Peak Allocated Bytes 0 B
156
+ Overflow Count 0
157
+ [ALLOC_TEMP_Background Job.Worker 0]
158
+ Initial Block Size 32.0 KB
159
+ Current Block Size 32.0 KB
160
+ Peak Allocated Bytes 0 B
161
+ Overflow Count 0
162
+ [ALLOC_TEMP_Background Job.Worker 4]
163
+ Initial Block Size 32.0 KB
164
+ Current Block Size 32.0 KB
165
+ Peak Allocated Bytes 0 B
166
+ Overflow Count 0
167
+ [ALLOC_TEMP_BatchDeleteObjects]
168
+ Initial Block Size 64.0 KB
169
+ Current Block Size 64.0 KB
170
+ Peak Allocated Bytes 0 B
171
+ Overflow Count 0
172
+ [ALLOC_DEFAULT] Dual Thread Allocator
173
+ Peak main deferred allocation count 39
174
+ [ALLOC_BUCKET]
175
+ Large Block size 4.0 MB
176
+ Used Block count 1
177
+ Peak Allocated bytes 1.0 MB
178
+ [ALLOC_DEFAULT_MAIN]
179
+ Peak usage frame count: [4.0 MB-8.0 MB]: 567 frames
180
+ Requested Block Size 16.0 MB
181
+ Peak Block count 1
182
+ Peak Allocated memory 5.9 MB
183
+ Peak Large allocation bytes 0 B
184
+ [ALLOC_DEFAULT_THREAD]
185
+ Peak usage frame count: [16.0 MB-32.0 MB]: 567 frames
186
+ Requested Block Size 16.0 MB
187
+ Peak Block count 1
188
+ Peak Allocated memory 17.3 MB
189
+ Peak Large allocation bytes 16.0 MB
190
+ [ALLOC_TEMP_JOB_1_FRAME]
191
+ Initial Block Size 2.0 MB
192
+ Used Block Count 1
193
+ Overflow Count (too large) 0
194
+ Overflow Count (full) 0
195
+ [ALLOC_TEMP_JOB_2_FRAMES]
196
+ Initial Block Size 2.0 MB
197
+ Used Block Count 1
198
+ Overflow Count (too large) 0
199
+ Overflow Count (full) 0
200
+ [ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
201
+ Initial Block Size 2.0 MB
202
+ Used Block Count 2
203
+ Overflow Count (too large) 0
204
+ Overflow Count (full) 0
205
+ [ALLOC_TEMP_JOB_ASYNC (Background)]
206
+ Initial Block Size 1.0 MB
207
+ Used Block Count 3
208
+ Overflow Count (too large) 0
209
+ Overflow Count (full) 0
210
+ [ALLOC_GFX] Dual Thread Allocator
211
+ Peak main deferred allocation count 0
212
+ [ALLOC_BUCKET]
213
+ Large Block size 4.0 MB
214
+ Used Block count 1
215
+ Peak Allocated bytes 1.0 MB
216
+ [ALLOC_GFX_MAIN]
217
+ Peak usage frame count: [32.0 KB-64.0 KB]: 496 frames, [64.0 KB-128.0 KB]: 71 frames
218
+ Requested Block Size 16.0 MB
219
+ Peak Block count 1
220
+ Peak Allocated memory 66.0 KB
221
+ Peak Large allocation bytes 0 B
222
+ [ALLOC_GFX_THREAD]
223
+ Peak usage frame count: [32.0 KB-64.0 KB]: 567 frames
224
+ Requested Block Size 16.0 MB
225
+ Peak Block count 1
226
+ Peak Allocated memory 39.6 KB
227
+ Peak Large allocation bytes 0 B
228
+ [ALLOC_CACHEOBJECTS] Dual Thread Allocator
229
+ Peak main deferred allocation count 0
230
+ [ALLOC_BUCKET]
231
+ Large Block size 4.0 MB
232
+ Used Block count 1
233
+ Peak Allocated bytes 1.0 MB
234
+ [ALLOC_CACHEOBJECTS_MAIN]
235
+ Peak usage frame count: [0.5 MB-1.0 MB]: 567 frames
236
+ Requested Block Size 4.0 MB
237
+ Peak Block count 1
238
+ Peak Allocated memory 0.6 MB
239
+ Peak Large allocation bytes 0 B
240
+ [ALLOC_CACHEOBJECTS_THREAD]
241
+ Peak usage frame count: [0.5 MB-1.0 MB]: 566 frames, [2.0 MB-4.0 MB]: 1 frames
242
+ Requested Block Size 4.0 MB
243
+ Peak Block count 1
244
+ Peak Allocated memory 2.2 MB
245
+ Peak Large allocation bytes 0 B
246
+ [ALLOC_TYPETREE] Dual Thread Allocator
247
+ Peak main deferred allocation count 0
248
+ [ALLOC_BUCKET]
249
+ Large Block size 4.0 MB
250
+ Used Block count 1
251
+ Peak Allocated bytes 1.0 MB
252
+ [ALLOC_TYPETREE_MAIN]
253
+ Peak usage frame count: [0-1.0 KB]: 567 frames
254
+ Requested Block Size 2.0 MB
255
+ Peak Block count 1
256
+ Peak Allocated memory 1.0 KB
257
+ Peak Large allocation bytes 0 B
258
+ [ALLOC_TYPETREE_THREAD]
259
+ Peak usage frame count: [1.0 KB-2.0 KB]: 567 frames
260
+ Requested Block Size 2.0 MB
261
+ Peak Block count 1
262
+ Peak Allocated memory 1.7 KB
263
+ Peak Large allocation bytes 0 B
run_logs/timers.json ADDED
@@ -0,0 +1,376 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "root",
3
+ "gauges": {
4
+ "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 2.773995876312256,
6
+ "min": 2.773995876312256,
7
+ "max": 2.8692355155944824,
8
+ "count": 2
9
+ },
10
+ "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 28591.576171875,
12
+ "min": 28591.576171875,
13
+ "max": 29383.841796875,
14
+ "count": 2
15
+ },
16
+ "SnowballTarget.Step.mean": {
17
+ "value": 19992.0,
18
+ "min": 9952.0,
19
+ "max": 19992.0,
20
+ "count": 2
21
+ },
22
+ "SnowballTarget.Step.sum": {
23
+ "value": 19992.0,
24
+ "min": 9952.0,
25
+ "max": 19992.0,
26
+ "count": 2
27
+ },
28
+ "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 0.5726273655891418,
30
+ "min": 0.147334024310112,
31
+ "max": 0.5726273655891418,
32
+ "count": 2
33
+ },
34
+ "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 117.38861083984375,
36
+ "min": 28.582801818847656,
37
+ "max": 117.38861083984375,
38
+ "count": 2
39
+ },
40
+ "SnowballTarget.Environment.EpisodeLength.mean": {
41
+ "value": 199.0,
42
+ "min": 199.0,
43
+ "max": 199.0,
44
+ "count": 2
45
+ },
46
+ "SnowballTarget.Environment.EpisodeLength.sum": {
47
+ "value": 10945.0,
48
+ "min": 8756.0,
49
+ "max": 10945.0,
50
+ "count": 2
51
+ },
52
+ "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.06799672417566363,
54
+ "min": 0.0635242219334531,
55
+ "max": 0.06799672417566363,
56
+ "count": 2
57
+ },
58
+ "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.3399836208783181,
60
+ "min": 0.2540968877338124,
61
+ "max": 0.3399836208783181,
62
+ "count": 2
63
+ },
64
+ "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.10964079529923551,
66
+ "min": 0.07155623769572497,
67
+ "max": 0.10964079529923551,
68
+ "count": 2
69
+ },
70
+ "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.5482039764961776,
72
+ "min": 0.2862249507828999,
73
+ "max": 0.5482039764961776,
74
+ "count": 2
75
+ },
76
+ "SnowballTarget.Policy.LearningRate.mean": {
77
+ "value": 0.000277032007656,
78
+ "min": 0.000277032007656,
79
+ "max": 0.000291882002706,
80
+ "count": 2
81
+ },
82
+ "SnowballTarget.Policy.LearningRate.sum": {
83
+ "value": 0.00138516003828,
84
+ "min": 0.001167528010824,
85
+ "max": 0.00138516003828,
86
+ "count": 2
87
+ },
88
+ "SnowballTarget.Policy.Epsilon.mean": {
89
+ "value": 0.19234400000000001,
90
+ "min": 0.19234400000000001,
91
+ "max": 0.19729400000000002,
92
+ "count": 2
93
+ },
94
+ "SnowballTarget.Policy.Epsilon.sum": {
95
+ "value": 0.96172,
96
+ "min": 0.7891760000000001,
97
+ "max": 0.96172,
98
+ "count": 2
99
+ },
100
+ "SnowballTarget.Policy.Beta.mean": {
101
+ "value": 0.0046179656,
102
+ "min": 0.0046179656,
103
+ "max": 0.0048649706,
104
+ "count": 2
105
+ },
106
+ "SnowballTarget.Policy.Beta.sum": {
107
+ "value": 0.023089828,
108
+ "min": 0.0194598824,
109
+ "max": 0.023089828,
110
+ "count": 2
111
+ },
112
+ "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 6.381818181818182,
114
+ "min": 3.522727272727273,
115
+ "max": 6.381818181818182,
116
+ "count": 2
117
+ },
118
+ "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 351.0,
120
+ "min": 155.0,
121
+ "max": 351.0,
122
+ "count": 2
123
+ },
124
+ "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 6.381818181818182,
126
+ "min": 3.522727272727273,
127
+ "max": 6.381818181818182,
128
+ "count": 2
129
+ },
130
+ "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 351.0,
132
+ "min": 155.0,
133
+ "max": 351.0,
134
+ "count": 2
135
+ },
136
+ "SnowballTarget.IsTraining.mean": {
137
+ "value": 1.0,
138
+ "min": 1.0,
139
+ "max": 1.0,
140
+ "count": 2
141
+ },
142
+ "SnowballTarget.IsTraining.sum": {
143
+ "value": 1.0,
144
+ "min": 1.0,
145
+ "max": 1.0,
146
+ "count": 2
147
+ }
148
+ },
149
+ "metadata": {
150
+ "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1677690902",
152
+ "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
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": "0.29.0.dev0",
155
+ "mlagents_envs_version": "0.29.0.dev0",
156
+ "communication_protocol_version": "1.5.0",
157
+ "pytorch_version": "1.8.1+cu102",
158
+ "numpy_version": "1.22.4",
159
+ "end_time_seconds": "1677690959"
160
+ },
161
+ "total": 57.057522927000036,
162
+ "count": 1,
163
+ "self": 0.19455147500002568,
164
+ "children": {
165
+ "run_training.setup": {
166
+ "total": 0.12869011099996897,
167
+ "count": 1,
168
+ "self": 0.12869011099996897
169
+ },
170
+ "TrainerController.start_learning": {
171
+ "total": 56.73428134100004,
172
+ "count": 1,
173
+ "self": 0.05467043700139129,
174
+ "children": {
175
+ "TrainerController._reset_env": {
176
+ "total": 9.745152264000012,
177
+ "count": 1,
178
+ "self": 9.745152264000012
179
+ },
180
+ "TrainerController.advance": {
181
+ "total": 46.69803345599871,
182
+ "count": 1890,
183
+ "self": 0.02846104999957788,
184
+ "children": {
185
+ "env_step": {
186
+ "total": 46.66957240599913,
187
+ "count": 1890,
188
+ "self": 32.4225230240005,
189
+ "children": {
190
+ "SubprocessEnvManager._take_step": {
191
+ "total": 14.219574842000497,
192
+ "count": 1890,
193
+ "self": 0.15459914099926664,
194
+ "children": {
195
+ "TorchPolicy.evaluate": {
196
+ "total": 14.06497570100123,
197
+ "count": 1890,
198
+ "self": 3.197259389003875,
199
+ "children": {
200
+ "TorchPolicy.sample_actions": {
201
+ "total": 10.867716311997356,
202
+ "count": 1890,
203
+ "self": 10.867716311997356
204
+ }
205
+ }
206
+ }
207
+ }
208
+ },
209
+ "workers": {
210
+ "total": 0.027474539998138425,
211
+ "count": 1889,
212
+ "self": 0.0,
213
+ "children": {
214
+ "worker_root": {
215
+ "total": 56.44349898399946,
216
+ "count": 1889,
217
+ "is_parallel": true,
218
+ "self": 31.668323080998448,
219
+ "children": {
220
+ "run_training.setup": {
221
+ "total": 0.0,
222
+ "count": 0,
223
+ "is_parallel": true,
224
+ "self": 0.0,
225
+ "children": {
226
+ "steps_from_proto": {
227
+ "total": 0.005927119000034509,
228
+ "count": 1,
229
+ "is_parallel": true,
230
+ "self": 0.0046233269999902404,
231
+ "children": {
232
+ "_process_rank_one_or_two_observation": {
233
+ "total": 0.0013037920000442682,
234
+ "count": 10,
235
+ "is_parallel": true,
236
+ "self": 0.0013037920000442682
237
+ }
238
+ }
239
+ },
240
+ "UnityEnvironment.step": {
241
+ "total": 0.06998756699999831,
242
+ "count": 1,
243
+ "is_parallel": true,
244
+ "self": 0.0006314280001333827,
245
+ "children": {
246
+ "UnityEnvironment._generate_step_input": {
247
+ "total": 0.00036928599990915245,
248
+ "count": 1,
249
+ "is_parallel": true,
250
+ "self": 0.00036928599990915245
251
+ },
252
+ "communicator.exchange": {
253
+ "total": 0.06721094199997424,
254
+ "count": 1,
255
+ "is_parallel": true,
256
+ "self": 0.06721094199997424
257
+ },
258
+ "steps_from_proto": {
259
+ "total": 0.0017759109999815337,
260
+ "count": 1,
261
+ "is_parallel": true,
262
+ "self": 0.0003889860000754197,
263
+ "children": {
264
+ "_process_rank_one_or_two_observation": {
265
+ "total": 0.001386924999906114,
266
+ "count": 10,
267
+ "is_parallel": true,
268
+ "self": 0.001386924999906114
269
+ }
270
+ }
271
+ }
272
+ }
273
+ }
274
+ }
275
+ },
276
+ "UnityEnvironment.step": {
277
+ "total": 24.775175903001013,
278
+ "count": 1888,
279
+ "is_parallel": true,
280
+ "self": 1.0005609239989326,
281
+ "children": {
282
+ "UnityEnvironment._generate_step_input": {
283
+ "total": 0.5416260569996894,
284
+ "count": 1888,
285
+ "is_parallel": true,
286
+ "self": 0.5416260569996894
287
+ },
288
+ "communicator.exchange": {
289
+ "total": 20.084928497000647,
290
+ "count": 1888,
291
+ "is_parallel": true,
292
+ "self": 20.084928497000647
293
+ },
294
+ "steps_from_proto": {
295
+ "total": 3.148060425001745,
296
+ "count": 1888,
297
+ "is_parallel": true,
298
+ "self": 0.6749315049964935,
299
+ "children": {
300
+ "_process_rank_one_or_two_observation": {
301
+ "total": 2.4731289200052515,
302
+ "count": 18880,
303
+ "is_parallel": true,
304
+ "self": 2.4731289200052515
305
+ }
306
+ }
307
+ }
308
+ }
309
+ }
310
+ }
311
+ }
312
+ }
313
+ }
314
+ }
315
+ }
316
+ }
317
+ },
318
+ "trainer_threads": {
319
+ "total": 4.258399997070228e-05,
320
+ "count": 1,
321
+ "self": 4.258399997070228e-05,
322
+ "children": {
323
+ "thread_root": {
324
+ "total": 0.0,
325
+ "count": 0,
326
+ "is_parallel": true,
327
+ "self": 0.0,
328
+ "children": {
329
+ "trainer_advance": {
330
+ "total": 46.31070583801579,
331
+ "count": 46739,
332
+ "is_parallel": true,
333
+ "self": 1.1014963490375749,
334
+ "children": {
335
+ "process_trajectory": {
336
+ "total": 27.44743387197809,
337
+ "count": 46739,
338
+ "is_parallel": true,
339
+ "self": 27.44743387197809
340
+ },
341
+ "_update_policy": {
342
+ "total": 17.761775617000126,
343
+ "count": 9,
344
+ "is_parallel": true,
345
+ "self": 6.11111961200163,
346
+ "children": {
347
+ "TorchPPOOptimizer.update": {
348
+ "total": 11.650656004998496,
349
+ "count": 456,
350
+ "is_parallel": true,
351
+ "self": 11.650656004998496
352
+ }
353
+ }
354
+ }
355
+ }
356
+ }
357
+ }
358
+ }
359
+ }
360
+ },
361
+ "TrainerController._save_models": {
362
+ "total": 0.23638259999995626,
363
+ "count": 1,
364
+ "self": 0.0012184499998966203,
365
+ "children": {
366
+ "RLTrainer._checkpoint": {
367
+ "total": 0.23516415000005964,
368
+ "count": 1,
369
+ "self": 0.23516415000005964
370
+ }
371
+ }
372
+ }
373
+ }
374
+ }
375
+ }
376
+ }
run_logs/training_status.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "SnowballTarget": {
3
+ "checkpoints": [
4
+ {
5
+ "steps": 20504,
6
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-20504.onnx",
7
+ "reward": 7.090909090909091,
8
+ "creation_time": 1677690959.7399228,
9
+ "auxillary_file_paths": [
10
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-20504.pt"
11
+ ]
12
+ }
13
+ ],
14
+ "final_checkpoint": {
15
+ "steps": 20504,
16
+ "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
17
+ "reward": 7.090909090909091,
18
+ "creation_time": 1677690959.7399228,
19
+ "auxillary_file_paths": [
20
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-20504.pt"
21
+ ]
22
+ }
23
+ },
24
+ "metadata": {
25
+ "stats_format_version": "0.3.0",
26
+ "mlagents_version": "0.29.0.dev0",
27
+ "torch_version": "1.8.1+cu102"
28
+ }
29
+ }