rwr20 commited on
Commit
57c60ae
1 Parent(s): 57e47d3

First Push

Browse files
README.md ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: ml-agents
3
+ tags:
4
+ - SnowballTarget
5
+ - deep-reinforcement-learning
6
+ - reinforcement-learning
7
+ - ML-Agents-SnowballTarget
8
+ ---
9
+
10
+ # **ppo** Agent playing **SnowballTarget**
11
+ This is a trained model of a **ppo** agent playing **SnowballTarget**
12
+ using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
13
+
14
+ ## Usage (with ML-Agents)
15
+ The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
16
+
17
+ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
18
+ - A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
19
+ browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
20
+ - A *longer tutorial* to understand how works ML-Agents:
21
+ https://huggingface.co/learn/deep-rl-course/unit5/introduction
22
+
23
+ ### Resume the training
24
+ ```bash
25
+ mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
26
+ ```
27
+
28
+ ### Watch your Agent play
29
+ You can watch your agent **playing directly in your browser**
30
+
31
+ 1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
32
+ 2. Step 1: Find your model_id: rwr20/ppo-SnowballTarget2
33
+ 3. Step 2: Select your *.nn /*.onnx file
34
+ 4. Click on Watch the agent play 👀
35
+
SnowballTarget.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f2a46f4287fc3b1777d005c85c48c6c9caa614379b440fc09473f78d04dff38
3
+ size 650646
SnowballTarget/SnowballTarget-10208.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f2a46f4287fc3b1777d005c85c48c6c9caa614379b440fc09473f78d04dff38
3
+ size 650646
SnowballTarget/SnowballTarget-10208.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8bff2980e00b34aa5b81458bd17bc0a76273fe62780e23c641a80d2c4b98289
3
+ size 3850000
SnowballTarget/checkpoint.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53d0a37e9afd7e899a828a61e5a7a7010cb55c72a6b50f60a31d1d50dcca3ac9
3
+ size 3849250
SnowballTarget/events.out.tfevents.1714813149.690628bcd0a1.8902.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de0bbff6d6d2f6218180dd2b5c6eaa6cbaeba65d6eebabf314a96f0e7c52760a
3
+ size 6862
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, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 100000, "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": 10000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget2", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ shared_critic: false
14
+ learning_rate_schedule: linear
15
+ beta_schedule: linear
16
+ epsilon_schedule: linear
17
+ checkpoint_interval: 100000
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
25
+ deterministic: false
26
+ reward_signals:
27
+ extrinsic:
28
+ gamma: 0.99
29
+ strength: 1.0
30
+ network_settings:
31
+ normalize: false
32
+ hidden_units: 128
33
+ num_layers: 2
34
+ vis_encode_type: simple
35
+ memory: null
36
+ goal_conditioning_type: hyper
37
+ deterministic: false
38
+ init_path: null
39
+ keep_checkpoints: 10
40
+ even_checkpoints: false
41
+ max_steps: 10000
42
+ time_horizon: 64
43
+ summary_freq: 10000
44
+ threaded: true
45
+ self_play: null
46
+ behavioral_cloning: null
47
+ env_settings:
48
+ env_path: ./training-envs-executables/linux/SnowballTarget/SnowballTarget
49
+ env_args: null
50
+ base_port: 5005
51
+ num_envs: 1
52
+ num_areas: 1
53
+ timeout_wait: 60
54
+ seed: -1
55
+ max_lifetime_restarts: 10
56
+ restarts_rate_limit_n: 1
57
+ restarts_rate_limit_period_s: 60
58
+ engine_settings:
59
+ width: 84
60
+ height: 84
61
+ quality_level: 5
62
+ time_scale: 20
63
+ target_frame_rate: -1
64
+ capture_frame_rate: 60
65
+ no_graphics: true
66
+ no_graphics_monitor: false
67
+ environment_parameters: null
68
+ checkpoint_settings:
69
+ run_id: SnowballTarget2
70
+ initialize_from: null
71
+ load_model: false
72
+ resume: false
73
+ force: false
74
+ train_model: false
75
+ inference: false
76
+ results_dir: results
77
+ torch_settings:
78
+ device: null
79
+ debug: false
run_logs/Player-0.log ADDED
@@ -0,0 +1,259 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ 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
8
+ GfxDevice: creating device client; threaded=0; jobified=0
9
+ NullGfxDevice:
10
+ Version: NULL 1.0 [1.0]
11
+ Renderer: Null Device
12
+ Vendor: Unity Technologies
13
+ ALSA lib confmisc.c:855:(parse_card) cannot find card '0'
14
+ ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
15
+ ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
16
+ ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
17
+ ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
18
+ ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
19
+ ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
20
+ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
21
+ FMOD failed to initialize the output device.: "Error initializing output device. " (60)
22
+ 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
23
+ ALSA lib confmisc.c:855:(parse_card) cannot find card '0'
24
+ ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
25
+ ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
26
+ ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
27
+ ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
28
+ ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
29
+ ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
30
+ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
31
+ FMOD failed to initialize the output device.: "Error initializing output device. " (60)
32
+ FMOD initialized on nosound output
33
+ Begin MonoManager ReloadAssembly
34
+ - Completed reload, in 0.095 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)
38
+ WARNING: Shader Unsupported: 'Standard' - All subshaders removed
39
+ WARNING: Shader Did you use #pragma only_renderers and omit this platform?
40
+ WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
41
+ ERROR: Shader Standard 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: 0.853936 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.
49
+ Memory Statistics:
50
+ [ALLOC_TEMP_TLS] TLS Allocator
51
+ StackAllocators :
52
+ [ALLOC_TEMP_MAIN]
53
+ Peak usage frame count: [8.0 KB-16.0 KB]: 275 frames, [16.0 KB-32.0 KB]: 4 frames, [2.0 MB-4.0 MB]: 1 frames
54
+ Initial Block Size 4.0 MB
55
+ Current Block Size 4.0 MB
56
+ Peak Allocated Bytes 2.0 MB
57
+ Overflow Count 0
58
+ [ALLOC_TEMP_Loading.AsyncRead]
59
+ Initial Block Size 64.0 KB
60
+ Current Block Size 64.0 KB
61
+ Peak Allocated Bytes 198 B
62
+ Overflow Count 0
63
+ [ALLOC_TEMP_Loading.PreloadManager]
64
+ Initial Block Size 256.0 KB
65
+ Current Block Size 304.0 KB
66
+ Peak Allocated Bytes 228.9 KB
67
+ Overflow Count 4
68
+ [ALLOC_TEMP_Background Job.Worker 8]
69
+ Initial Block Size 32.0 KB
70
+ Current Block Size 32.0 KB
71
+ Peak Allocated Bytes 0 B
72
+ Overflow Count 0
73
+ [ALLOC_TEMP_Background Job.Worker 9]
74
+ Initial Block Size 32.0 KB
75
+ Current Block Size 32.0 KB
76
+ Peak Allocated Bytes 0 B
77
+ Overflow Count 0
78
+ [ALLOC_TEMP_Job.Worker 0]
79
+ Initial Block Size 256.0 KB
80
+ Current Block Size 256.0 KB
81
+ Peak Allocated Bytes 3.6 KB
82
+ Overflow Count 0
83
+ [ALLOC_TEMP_Background Job.Worker 10]
84
+ Initial Block Size 32.0 KB
85
+ Current Block Size 32.0 KB
86
+ Peak Allocated Bytes 0 B
87
+ Overflow Count 0
88
+ [ALLOC_TEMP_Background Job.Worker 14]
89
+ Initial Block Size 32.0 KB
90
+ Current Block Size 32.0 KB
91
+ Peak Allocated Bytes 0 B
92
+ Overflow Count 0
93
+ [ALLOC_TEMP_Background Job.Worker 6]
94
+ Initial Block Size 32.0 KB
95
+ Current Block Size 32.0 KB
96
+ Peak Allocated Bytes 0 B
97
+ Overflow Count 0
98
+ [ALLOC_TEMP_Background Job.Worker 12]
99
+ Initial Block Size 32.0 KB
100
+ Current Block Size 32.0 KB
101
+ Peak Allocated Bytes 0 B
102
+ Overflow Count 0
103
+ [ALLOC_TEMP_EnlightenWorker]
104
+ Initial Block Size 64.0 KB
105
+ Current Block Size 64.0 KB
106
+ Peak Allocated Bytes 0 B
107
+ Overflow Count 0
108
+ [ALLOC_TEMP_Background Job.Worker 15]
109
+ Initial Block Size 32.0 KB
110
+ Current Block Size 32.0 KB
111
+ Peak Allocated Bytes 0 B
112
+ Overflow Count 0
113
+ [ALLOC_TEMP_Background Job.Worker 1]
114
+ Initial Block Size 32.0 KB
115
+ Current Block Size 32.0 KB
116
+ Peak Allocated Bytes 0 B
117
+ Overflow Count 0
118
+ [ALLOC_TEMP_Background Job.Worker 2]
119
+ Initial Block Size 32.0 KB
120
+ Current Block Size 32.0 KB
121
+ Peak Allocated Bytes 0 B
122
+ Overflow Count 0
123
+ [ALLOC_TEMP_Background Job.Worker 7]
124
+ Initial Block Size 32.0 KB
125
+ Current Block Size 32.0 KB
126
+ Peak Allocated Bytes 0 B
127
+ Overflow Count 0
128
+ [ALLOC_TEMP_AssetGarbageCollectorHelper]
129
+ Initial Block Size 64.0 KB
130
+ Current Block Size 64.0 KB
131
+ Peak Allocated Bytes 0 B
132
+ Overflow Count 0
133
+ [ALLOC_TEMP_Background Job.Worker 5]
134
+ Initial Block Size 32.0 KB
135
+ Current Block Size 32.0 KB
136
+ Peak Allocated Bytes 0 B
137
+ Overflow Count 0
138
+ [ALLOC_TEMP_Background Job.Worker 13]
139
+ Initial Block Size 32.0 KB
140
+ Current Block Size 32.0 KB
141
+ Peak Allocated Bytes 0 B
142
+ Overflow Count 0
143
+ [ALLOC_TEMP_Background Job.Worker 11]
144
+ Initial Block Size 32.0 KB
145
+ Current Block Size 32.0 KB
146
+ Peak Allocated Bytes 0 B
147
+ Overflow Count 0
148
+ [ALLOC_TEMP_Background Job.Worker 3]
149
+ Initial Block Size 32.0 KB
150
+ Current Block Size 32.0 KB
151
+ Peak Allocated Bytes 0 B
152
+ Overflow Count 0
153
+ [ALLOC_TEMP_Background Job.Worker 0]
154
+ Initial Block Size 32.0 KB
155
+ Current Block Size 32.0 KB
156
+ Peak Allocated Bytes 0 B
157
+ Overflow Count 0
158
+ [ALLOC_TEMP_Background Job.Worker 4]
159
+ Initial Block Size 32.0 KB
160
+ Current Block Size 32.0 KB
161
+ Peak Allocated Bytes 0 B
162
+ Overflow Count 0
163
+ [ALLOC_TEMP_BatchDeleteObjects]
164
+ Initial Block Size 64.0 KB
165
+ Current Block Size 64.0 KB
166
+ Peak Allocated Bytes 0 B
167
+ Overflow Count 0
168
+ [ALLOC_DEFAULT] Dual Thread Allocator
169
+ Peak main deferred allocation count 29
170
+ [ALLOC_BUCKET]
171
+ Large Block size 4.0 MB
172
+ Used Block count 1
173
+ Peak Allocated bytes 1.0 MB
174
+ [ALLOC_DEFAULT_MAIN]
175
+ Peak usage frame count: [4.0 MB-8.0 MB]: 280 frames
176
+ Requested Block Size 16.0 MB
177
+ Peak Block count 1
178
+ Peak Allocated memory 5.7 MB
179
+ Peak Large allocation bytes 0 B
180
+ [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 280 frames
182
+ Requested Block Size 16.0 MB
183
+ Peak Block count 1
184
+ Peak Allocated memory 17.3 MB
185
+ Peak Large allocation bytes 16.0 MB
186
+ [ALLOC_TEMP_JOB_1_FRAME]
187
+ Initial Block Size 2.0 MB
188
+ Used Block Count 1
189
+ Overflow Count (too large) 0
190
+ Overflow Count (full) 0
191
+ [ALLOC_TEMP_JOB_2_FRAMES]
192
+ Initial Block Size 2.0 MB
193
+ Used Block Count 1
194
+ Overflow Count (too large) 0
195
+ Overflow Count (full) 0
196
+ [ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
197
+ Initial Block Size 2.0 MB
198
+ Used Block Count 2
199
+ Overflow Count (too large) 0
200
+ Overflow Count (full) 0
201
+ [ALLOC_TEMP_JOB_ASYNC (Background)]
202
+ Initial Block Size 1.0 MB
203
+ Used Block Count 3
204
+ Overflow Count (too large) 0
205
+ Overflow Count (full) 0
206
+ [ALLOC_GFX] Dual Thread Allocator
207
+ Peak main deferred allocation count 0
208
+ [ALLOC_BUCKET]
209
+ Large Block size 4.0 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]: 260 frames, [64.0 KB-128.0 KB]: 20 frames
214
+ Requested Block Size 16.0 MB
215
+ Peak Block count 1
216
+ Peak Allocated memory 65.6 KB
217
+ Peak Large allocation bytes 0 B
218
+ [ALLOC_GFX_THREAD]
219
+ Peak usage frame count: [32.0 KB-64.0 KB]: 280 frames
220
+ Requested Block Size 16.0 MB
221
+ Peak Block count 1
222
+ Peak Allocated memory 39.6 KB
223
+ Peak Large allocation bytes 0 B
224
+ [ALLOC_CACHEOBJECTS] Dual Thread Allocator
225
+ Peak main deferred allocation count 0
226
+ [ALLOC_BUCKET]
227
+ Large Block size 4.0 MB
228
+ Used Block count 1
229
+ Peak Allocated bytes 1.0 MB
230
+ [ALLOC_CACHEOBJECTS_MAIN]
231
+ Peak usage frame count: [0.5 MB-1.0 MB]: 280 frames
232
+ Requested Block Size 4.0 MB
233
+ Peak Block count 1
234
+ Peak Allocated memory 0.6 MB
235
+ Peak Large allocation bytes 0 B
236
+ [ALLOC_CACHEOBJECTS_THREAD]
237
+ Peak usage frame count: [0.5 MB-1.0 MB]: 279 frames, [2.0 MB-4.0 MB]: 1 frames
238
+ Requested Block Size 4.0 MB
239
+ Peak Block count 1
240
+ Peak Allocated memory 2.2 MB
241
+ Peak Large allocation bytes 0 B
242
+ [ALLOC_TYPETREE] Dual Thread Allocator
243
+ Peak main deferred allocation count 0
244
+ [ALLOC_BUCKET]
245
+ Large Block size 4.0 MB
246
+ Used Block count 1
247
+ Peak Allocated bytes 1.0 MB
248
+ [ALLOC_TYPETREE_MAIN]
249
+ Peak usage frame count: [0-1.0 KB]: 280 frames
250
+ Requested Block Size 2.0 MB
251
+ Peak Block count 1
252
+ Peak Allocated memory 1.0 KB
253
+ Peak Large allocation bytes 0 B
254
+ [ALLOC_TYPETREE_THREAD]
255
+ Peak usage frame count: [1.0 KB-2.0 KB]: 280 frames
256
+ Requested Block Size 2.0 MB
257
+ Peak Block count 1
258
+ Peak Allocated memory 1.7 KB
259
+ Peak Large allocation bytes 0 B
run_logs/timers.json ADDED
@@ -0,0 +1,369 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "root",
3
+ "gauges": {
4
+ "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 2.8801817893981934,
6
+ "min": 2.8801817893981934,
7
+ "max": 2.8801817893981934,
8
+ "count": 1
9
+ },
10
+ "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 29495.94140625,
12
+ "min": 29495.94140625,
13
+ "max": 29495.94140625,
14
+ "count": 1
15
+ },
16
+ "SnowballTarget.Step.mean": {
17
+ "value": 9952.0,
18
+ "min": 9952.0,
19
+ "max": 9952.0,
20
+ "count": 1
21
+ },
22
+ "SnowballTarget.Step.sum": {
23
+ "value": 9952.0,
24
+ "min": 9952.0,
25
+ "max": 9952.0,
26
+ "count": 1
27
+ },
28
+ "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 0.49050334095954895,
30
+ "min": 0.49050334095954895,
31
+ "max": 0.49050334095954895,
32
+ "count": 1
33
+ },
34
+ "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 95.15764617919922,
36
+ "min": 95.15764617919922,
37
+ "max": 95.15764617919922,
38
+ "count": 1
39
+ },
40
+ "SnowballTarget.Environment.EpisodeLength.mean": {
41
+ "value": 199.0,
42
+ "min": 199.0,
43
+ "max": 199.0,
44
+ "count": 1
45
+ },
46
+ "SnowballTarget.Environment.EpisodeLength.sum": {
47
+ "value": 8756.0,
48
+ "min": 8756.0,
49
+ "max": 8756.0,
50
+ "count": 1
51
+ },
52
+ "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.07404546684276783,
54
+ "min": 0.07404546684276783,
55
+ "max": 0.07404546684276783,
56
+ "count": 1
57
+ },
58
+ "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.29618186737107133,
60
+ "min": 0.29618186737107133,
61
+ "max": 0.29618186737107133,
62
+ "count": 1
63
+ },
64
+ "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.10099118845719916,
66
+ "min": 0.10099118845719916,
67
+ "max": 0.10099118845719916,
68
+ "count": 1
69
+ },
70
+ "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.40396475382879665,
72
+ "min": 0.40396475382879665,
73
+ "max": 0.40396475382879665,
74
+ "count": 1
75
+ },
76
+ "SnowballTarget.Policy.LearningRate.mean": {
77
+ "value": 0.00013764005412,
78
+ "min": 0.00013764005412,
79
+ "max": 0.00013764005412,
80
+ "count": 1
81
+ },
82
+ "SnowballTarget.Policy.LearningRate.sum": {
83
+ "value": 0.00055056021648,
84
+ "min": 0.00055056021648,
85
+ "max": 0.00055056021648,
86
+ "count": 1
87
+ },
88
+ "SnowballTarget.Policy.Epsilon.mean": {
89
+ "value": 0.14588,
90
+ "min": 0.14588,
91
+ "max": 0.14588,
92
+ "count": 1
93
+ },
94
+ "SnowballTarget.Policy.Epsilon.sum": {
95
+ "value": 0.58352,
96
+ "min": 0.58352,
97
+ "max": 0.58352,
98
+ "count": 1
99
+ },
100
+ "SnowballTarget.Policy.Beta.mean": {
101
+ "value": 0.002299412,
102
+ "min": 0.002299412,
103
+ "max": 0.002299412,
104
+ "count": 1
105
+ },
106
+ "SnowballTarget.Policy.Beta.sum": {
107
+ "value": 0.009197648,
108
+ "min": 0.009197648,
109
+ "max": 0.009197648,
110
+ "count": 1
111
+ },
112
+ "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 2.8863636363636362,
114
+ "min": 2.8863636363636362,
115
+ "max": 2.8863636363636362,
116
+ "count": 1
117
+ },
118
+ "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 127.0,
120
+ "min": 127.0,
121
+ "max": 127.0,
122
+ "count": 1
123
+ },
124
+ "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 2.8863636363636362,
126
+ "min": 2.8863636363636362,
127
+ "max": 2.8863636363636362,
128
+ "count": 1
129
+ },
130
+ "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 127.0,
132
+ "min": 127.0,
133
+ "max": 127.0,
134
+ "count": 1
135
+ },
136
+ "SnowballTarget.IsTraining.mean": {
137
+ "value": 1.0,
138
+ "min": 1.0,
139
+ "max": 1.0,
140
+ "count": 1
141
+ },
142
+ "SnowballTarget.IsTraining.sum": {
143
+ "value": 1.0,
144
+ "min": 1.0,
145
+ "max": 1.0,
146
+ "count": 1
147
+ }
148
+ },
149
+ "metadata": {
150
+ "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1714813148",
152
+ "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
153
+ "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --no-graphics",
154
+ "mlagents_version": "1.1.0.dev0",
155
+ "mlagents_envs_version": "1.1.0.dev0",
156
+ "communication_protocol_version": "1.5.0",
157
+ "pytorch_version": "2.2.1+cu121",
158
+ "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1714813174"
160
+ },
161
+ "total": 25.815106173999993,
162
+ "count": 1,
163
+ "self": 0.7448074260000794,
164
+ "children": {
165
+ "run_training.setup": {
166
+ "total": 0.05302846900008262,
167
+ "count": 1,
168
+ "self": 0.05302846900008262
169
+ },
170
+ "TrainerController.start_learning": {
171
+ "total": 25.01727027899983,
172
+ "count": 1,
173
+ "self": 0.049328362005098825,
174
+ "children": {
175
+ "TrainerController._reset_env": {
176
+ "total": 2.742897456000037,
177
+ "count": 1,
178
+ "self": 2.742897456000037
179
+ },
180
+ "TrainerController.advance": {
181
+ "total": 22.10123112699489,
182
+ "count": 932,
183
+ "self": 0.013189132992692976,
184
+ "children": {
185
+ "env_step": {
186
+ "total": 22.088041994002197,
187
+ "count": 932,
188
+ "self": 13.504690167004128,
189
+ "children": {
190
+ "SubprocessEnvManager._take_step": {
191
+ "total": 8.569482182999991,
192
+ "count": 932,
193
+ "self": 0.07452847099898463,
194
+ "children": {
195
+ "TorchPolicy.evaluate": {
196
+ "total": 8.494953712001006,
197
+ "count": 932,
198
+ "self": 8.494953712001006
199
+ }
200
+ }
201
+ },
202
+ "workers": {
203
+ "total": 0.013869643998077663,
204
+ "count": 932,
205
+ "self": 0.0,
206
+ "children": {
207
+ "worker_root": {
208
+ "total": 24.868073781995463,
209
+ "count": 932,
210
+ "is_parallel": true,
211
+ "self": 14.013799128991195,
212
+ "children": {
213
+ "run_training.setup": {
214
+ "total": 0.0,
215
+ "count": 0,
216
+ "is_parallel": true,
217
+ "self": 0.0,
218
+ "children": {
219
+ "steps_from_proto": {
220
+ "total": 0.003067575999921246,
221
+ "count": 1,
222
+ "is_parallel": true,
223
+ "self": 0.0007622169989645045,
224
+ "children": {
225
+ "_process_rank_one_or_two_observation": {
226
+ "total": 0.0023053590009567415,
227
+ "count": 10,
228
+ "is_parallel": true,
229
+ "self": 0.0023053590009567415
230
+ }
231
+ }
232
+ },
233
+ "UnityEnvironment.step": {
234
+ "total": 0.03800216099989484,
235
+ "count": 1,
236
+ "is_parallel": true,
237
+ "self": 0.0006384190000972012,
238
+ "children": {
239
+ "UnityEnvironment._generate_step_input": {
240
+ "total": 0.000414202000001751,
241
+ "count": 1,
242
+ "is_parallel": true,
243
+ "self": 0.000414202000001751
244
+ },
245
+ "communicator.exchange": {
246
+ "total": 0.0349666919998981,
247
+ "count": 1,
248
+ "is_parallel": true,
249
+ "self": 0.0349666919998981
250
+ },
251
+ "steps_from_proto": {
252
+ "total": 0.0019828479998977855,
253
+ "count": 1,
254
+ "is_parallel": true,
255
+ "self": 0.00036528099985844165,
256
+ "children": {
257
+ "_process_rank_one_or_two_observation": {
258
+ "total": 0.0016175670000393438,
259
+ "count": 10,
260
+ "is_parallel": true,
261
+ "self": 0.0016175670000393438
262
+ }
263
+ }
264
+ }
265
+ }
266
+ }
267
+ }
268
+ },
269
+ "UnityEnvironment.step": {
270
+ "total": 10.854274653004268,
271
+ "count": 931,
272
+ "is_parallel": true,
273
+ "self": 0.527694120994056,
274
+ "children": {
275
+ "UnityEnvironment._generate_step_input": {
276
+ "total": 0.2806934130016998,
277
+ "count": 931,
278
+ "is_parallel": true,
279
+ "self": 0.2806934130016998
280
+ },
281
+ "communicator.exchange": {
282
+ "total": 8.333602966999251,
283
+ "count": 931,
284
+ "is_parallel": true,
285
+ "self": 8.333602966999251
286
+ },
287
+ "steps_from_proto": {
288
+ "total": 1.7122841520092607,
289
+ "count": 931,
290
+ "is_parallel": true,
291
+ "self": 0.31524731699096264,
292
+ "children": {
293
+ "_process_rank_one_or_two_observation": {
294
+ "total": 1.397036835018298,
295
+ "count": 9310,
296
+ "is_parallel": true,
297
+ "self": 1.397036835018298
298
+ }
299
+ }
300
+ }
301
+ }
302
+ }
303
+ }
304
+ }
305
+ }
306
+ }
307
+ }
308
+ }
309
+ }
310
+ },
311
+ "trainer_threads": {
312
+ "total": 0.0002192980000472744,
313
+ "count": 1,
314
+ "self": 0.0002192980000472744,
315
+ "children": {
316
+ "thread_root": {
317
+ "total": 0.0,
318
+ "count": 0,
319
+ "is_parallel": true,
320
+ "self": 0.0,
321
+ "children": {
322
+ "trainer_advance": {
323
+ "total": 21.809158544080447,
324
+ "count": 37815,
325
+ "is_parallel": true,
326
+ "self": 0.7616994200357112,
327
+ "children": {
328
+ "process_trajectory": {
329
+ "total": 12.65068600504469,
330
+ "count": 37815,
331
+ "is_parallel": true,
332
+ "self": 12.65068600504469
333
+ },
334
+ "_update_policy": {
335
+ "total": 8.396773119000045,
336
+ "count": 4,
337
+ "is_parallel": true,
338
+ "self": 2.100224684003024,
339
+ "children": {
340
+ "TorchPPOOptimizer.update": {
341
+ "total": 6.296548434997021,
342
+ "count": 201,
343
+ "is_parallel": true,
344
+ "self": 6.296548434997021
345
+ }
346
+ }
347
+ }
348
+ }
349
+ }
350
+ }
351
+ }
352
+ }
353
+ },
354
+ "TrainerController._save_models": {
355
+ "total": 0.12359403599975849,
356
+ "count": 1,
357
+ "self": 0.0010294209996573045,
358
+ "children": {
359
+ "RLTrainer._checkpoint": {
360
+ "total": 0.12256461500010118,
361
+ "count": 1,
362
+ "self": 0.12256461500010118
363
+ }
364
+ }
365
+ }
366
+ }
367
+ }
368
+ }
369
+ }
run_logs/training_status.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "SnowballTarget": {
3
+ "checkpoints": [
4
+ {
5
+ "steps": 10208,
6
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-10208.onnx",
7
+ "reward": 3.090909090909091,
8
+ "creation_time": 1714813173.9862776,
9
+ "auxillary_file_paths": [
10
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-10208.pt"
11
+ ]
12
+ }
13
+ ],
14
+ "final_checkpoint": {
15
+ "steps": 10208,
16
+ "file_path": "results/SnowballTarget2/SnowballTarget.onnx",
17
+ "reward": 3.090909090909091,
18
+ "creation_time": 1714813173.9862776,
19
+ "auxillary_file_paths": [
20
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-10208.pt"
21
+ ]
22
+ }
23
+ },
24
+ "metadata": {
25
+ "stats_format_version": "0.3.0",
26
+ "mlagents_version": "1.1.0.dev0",
27
+ "torch_version": "2.2.1+cu121"
28
+ }
29
+ }