jakubgajski commited on
Commit
42073b7
1 Parent(s): 45e0430

First Push

Browse files
README.md ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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** using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
12
+
13
+ ## Usage (with ML-Agents)
14
+ The Documentation: https://github.com/huggingface/ml-agents#get-started
15
+ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
16
+
17
+
18
+ ### Resume the training
19
+ ```
20
+ mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
21
+ ```
22
+ ### Watch your Agent play
23
+ You can watch your agent **playing directly in your browser:**.
24
+
25
+ 1. Go to https://huggingface.co/spaces/unity/ML-Agents-SnowballTarget
26
+ 2. Step 1: Find your model_id: jakubgajski/ppo-SnowballTarget
27
+ 3. Step 2: Select your *.nn /*.onnx file
28
+ 4. Click on Watch the agent play 👀
29
+
SnowballTarget.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2679e4ecf25657b31e5d46670ac96e7fd0b2d1cc193f6db57d0c1d9e328bf891
3
+ size 910131
SnowballTarget/SnowballTarget-149984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca7b4b2d1ba94549b6a5e7948936155a72029f64097cf9f903d1d4a66e1dad68
3
+ size 910131
SnowballTarget/SnowballTarget-149984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25d69cdf4e496a5e392994db17aa565f2e21a10c0fbff507961eb7e120372b6e
3
+ size 5827622
SnowballTarget/SnowballTarget-199984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2679e4ecf25657b31e5d46670ac96e7fd0b2d1cc193f6db57d0c1d9e328bf891
3
+ size 910131
SnowballTarget/SnowballTarget-199984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:564431dbff5675fa60354a12718aac016a5b756d80336e5e56a7954c6c475939
3
+ size 5827622
SnowballTarget/SnowballTarget-200112.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2679e4ecf25657b31e5d46670ac96e7fd0b2d1cc193f6db57d0c1d9e328bf891
3
+ size 910131
SnowballTarget/SnowballTarget-200112.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad0703609ab5a669b2f33261545589b3cefc8732656bdf27ca525331eda35b3f
3
+ size 5827622
SnowballTarget/SnowballTarget-49936.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0917c76b977e4aa9f7be60cbab03ecea2dc00bf35df101dda9e1165da970ec11
3
+ size 910131
SnowballTarget/SnowballTarget-49936.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebc9a913bd3ab6ddf0e5c63ab22affff34535785d93bd812b508dea5f5ed85d5
3
+ size 5827622
SnowballTarget/SnowballTarget-99960.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a105b1aac6a8fe3242f4c4b956fb5a34881afbea91a461b2a900e68b0d61f89c
3
+ size 910131
SnowballTarget/SnowballTarget-99960.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3f386f547af3b3bd1d3d0adcd55e82355394036a1397c877b31d305af4aa060
3
+ size 5827622
SnowballTarget/checkpoint.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad0703609ab5a669b2f33261545589b3cefc8732656bdf27ca525331eda35b3f
3
+ size 5827622
SnowballTarget/events.out.tfevents.1683811597.0f179e1dc6c5.7852.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:924eaf7ae3f7adb44f9446b51187e118e8a81bd382045c8c9d806a073c3d44eb
3
+ size 42116
config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 32, "buffer_size": 16384, "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": 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}}, "curiosity": {"gamma": 0.99, "strength": 0.1, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "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, "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 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ default_settings: null
2
+ behaviors:
3
+ SnowballTarget:
4
+ trainer_type: ppo
5
+ hyperparameters:
6
+ batch_size: 32
7
+ buffer_size: 16384
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: 50000
18
+ network_settings:
19
+ normalize: false
20
+ hidden_units: 256
21
+ num_layers: 3
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
+ curiosity:
39
+ gamma: 0.99
40
+ strength: 0.1
41
+ network_settings:
42
+ normalize: false
43
+ hidden_units: 64
44
+ num_layers: 2
45
+ vis_encode_type: simple
46
+ memory: null
47
+ goal_conditioning_type: hyper
48
+ deterministic: false
49
+ learning_rate: 0.0001
50
+ encoding_size: null
51
+ init_path: null
52
+ keep_checkpoints: 10
53
+ even_checkpoints: false
54
+ max_steps: 200000
55
+ time_horizon: 64
56
+ summary_freq: 10000
57
+ threaded: true
58
+ self_play: null
59
+ behavioral_cloning: null
60
+ env_settings:
61
+ env_path: ./training-envs-executables/linux/SnowballTarget/SnowballTarget
62
+ env_args: null
63
+ base_port: 5005
64
+ num_envs: 1
65
+ num_areas: 1
66
+ seed: -1
67
+ max_lifetime_restarts: 10
68
+ restarts_rate_limit_n: 1
69
+ restarts_rate_limit_period_s: 60
70
+ engine_settings:
71
+ width: 84
72
+ height: 84
73
+ quality_level: 5
74
+ time_scale: 20
75
+ target_frame_rate: -1
76
+ capture_frame_rate: 60
77
+ no_graphics: true
78
+ environment_parameters: null
79
+ checkpoint_settings:
80
+ run_id: SnowballTarget1
81
+ initialize_from: null
82
+ load_model: false
83
+ resume: false
84
+ force: false
85
+ train_model: false
86
+ inference: false
87
+ results_dir: results
88
+ torch_settings:
89
+ device: null
90
+ debug: false
run_logs/Player-0.log ADDED
@@ -0,0 +1,262 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: 0.827891 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.
52
+ Memory Statistics:
53
+ [ALLOC_TEMP_TLS] TLS Allocator
54
+ StackAllocators :
55
+ [ALLOC_TEMP_MAIN]
56
+ Peak usage frame count: [8.0 KB-16.0 KB]: 5371 frames, [16.0 KB-32.0 KB]: 91 frames, [2.0 MB-4.0 MB]: 1 frames
57
+ Initial Block Size 4.0 MB
58
+ Current Block Size 4.0 MB
59
+ Peak Allocated Bytes 2.0 MB
60
+ Overflow Count 0
61
+ [ALLOC_TEMP_Loading.AsyncRead]
62
+ Initial Block Size 64.0 KB
63
+ Current Block Size 64.0 KB
64
+ Peak Allocated Bytes 198 B
65
+ Overflow Count 0
66
+ [ALLOC_TEMP_Loading.PreloadManager]
67
+ Initial Block Size 256.0 KB
68
+ Current Block Size 304.0 KB
69
+ Peak Allocated Bytes 228.9 KB
70
+ Overflow Count 4
71
+ [ALLOC_TEMP_Background Job.Worker 8]
72
+ Initial Block Size 32.0 KB
73
+ Current Block Size 32.0 KB
74
+ Peak Allocated Bytes 0 B
75
+ Overflow Count 0
76
+ [ALLOC_TEMP_Background Job.Worker 9]
77
+ Initial Block Size 32.0 KB
78
+ Current Block Size 32.0 KB
79
+ Peak Allocated Bytes 0 B
80
+ Overflow Count 0
81
+ [ALLOC_TEMP_Job.Worker 0]
82
+ Initial Block Size 256.0 KB
83
+ Current Block Size 256.0 KB
84
+ Peak Allocated Bytes 3.6 KB
85
+ Overflow Count 0
86
+ [ALLOC_TEMP_Background Job.Worker 10]
87
+ Initial Block Size 32.0 KB
88
+ Current Block Size 32.0 KB
89
+ Peak Allocated Bytes 0 B
90
+ Overflow Count 0
91
+ [ALLOC_TEMP_Background Job.Worker 14]
92
+ Initial Block Size 32.0 KB
93
+ Current Block Size 32.0 KB
94
+ Peak Allocated Bytes 0 B
95
+ Overflow Count 0
96
+ [ALLOC_TEMP_Background Job.Worker 6]
97
+ Initial Block Size 32.0 KB
98
+ Current Block Size 32.0 KB
99
+ Peak Allocated Bytes 0 B
100
+ Overflow Count 0
101
+ [ALLOC_TEMP_Background Job.Worker 12]
102
+ Initial Block Size 32.0 KB
103
+ Current Block Size 32.0 KB
104
+ Peak Allocated Bytes 0 B
105
+ Overflow Count 0
106
+ [ALLOC_TEMP_EnlightenWorker]
107
+ Initial Block Size 64.0 KB
108
+ Current Block Size 64.0 KB
109
+ Peak Allocated Bytes 0 B
110
+ Overflow Count 0
111
+ [ALLOC_TEMP_Background Job.Worker 15]
112
+ Initial Block Size 32.0 KB
113
+ Current Block Size 32.0 KB
114
+ Peak Allocated Bytes 0 B
115
+ Overflow Count 0
116
+ [ALLOC_TEMP_Background Job.Worker 1]
117
+ Initial Block Size 32.0 KB
118
+ Current Block Size 32.0 KB
119
+ Peak Allocated Bytes 0 B
120
+ Overflow Count 0
121
+ [ALLOC_TEMP_Background Job.Worker 2]
122
+ Initial Block Size 32.0 KB
123
+ Current Block Size 32.0 KB
124
+ Peak Allocated Bytes 0 B
125
+ Overflow Count 0
126
+ [ALLOC_TEMP_Background Job.Worker 7]
127
+ Initial Block Size 32.0 KB
128
+ Current Block Size 32.0 KB
129
+ Peak Allocated Bytes 0 B
130
+ Overflow Count 0
131
+ [ALLOC_TEMP_AssetGarbageCollectorHelper]
132
+ Initial Block Size 64.0 KB
133
+ Current Block Size 64.0 KB
134
+ Peak Allocated Bytes 0 B
135
+ Overflow Count 0
136
+ [ALLOC_TEMP_Background Job.Worker 5]
137
+ Initial Block Size 32.0 KB
138
+ Current Block Size 32.0 KB
139
+ Peak Allocated Bytes 0 B
140
+ Overflow Count 0
141
+ [ALLOC_TEMP_Background Job.Worker 13]
142
+ Initial Block Size 32.0 KB
143
+ Current Block Size 32.0 KB
144
+ Peak Allocated Bytes 0 B
145
+ Overflow Count 0
146
+ [ALLOC_TEMP_Background Job.Worker 11]
147
+ Initial Block Size 32.0 KB
148
+ Current Block Size 32.0 KB
149
+ Peak Allocated Bytes 0 B
150
+ Overflow Count 0
151
+ [ALLOC_TEMP_Background Job.Worker 3]
152
+ Initial Block Size 32.0 KB
153
+ Current Block Size 32.0 KB
154
+ Peak Allocated Bytes 0 B
155
+ Overflow Count 0
156
+ [ALLOC_TEMP_Background Job.Worker 0]
157
+ Initial Block Size 32.0 KB
158
+ Current Block Size 32.0 KB
159
+ Peak Allocated Bytes 0 B
160
+ Overflow Count 0
161
+ [ALLOC_TEMP_Background Job.Worker 4]
162
+ Initial Block Size 32.0 KB
163
+ Current Block Size 32.0 KB
164
+ Peak Allocated Bytes 0 B
165
+ Overflow Count 0
166
+ [ALLOC_TEMP_BatchDeleteObjects]
167
+ Initial Block Size 64.0 KB
168
+ Current Block Size 64.0 KB
169
+ Peak Allocated Bytes 0 B
170
+ Overflow Count 0
171
+ [ALLOC_DEFAULT] Dual Thread Allocator
172
+ Peak main deferred allocation count 45
173
+ [ALLOC_BUCKET]
174
+ Large Block size 4.0 MB
175
+ Used Block count 1
176
+ Peak Allocated bytes 1.0 MB
177
+ [ALLOC_DEFAULT_MAIN]
178
+ Peak usage frame count: [4.0 MB-8.0 MB]: 5463 frames
179
+ Requested Block Size 16.0 MB
180
+ Peak Block count 1
181
+ Peak Allocated memory 6.7 MB
182
+ Peak Large allocation bytes 0 B
183
+ [ALLOC_DEFAULT_THREAD]
184
+ Peak usage frame count: [16.0 MB-32.0 MB]: 5463 frames
185
+ Requested Block Size 16.0 MB
186
+ Peak Block count 1
187
+ Peak Allocated memory 17.8 MB
188
+ Peak Large allocation bytes 16.0 MB
189
+ [ALLOC_TEMP_JOB_1_FRAME]
190
+ Initial Block Size 2.0 MB
191
+ Used Block Count 1
192
+ Overflow Count (too large) 0
193
+ Overflow Count (full) 0
194
+ [ALLOC_TEMP_JOB_2_FRAMES]
195
+ Initial Block Size 2.0 MB
196
+ Used Block Count 1
197
+ Overflow Count (too large) 0
198
+ Overflow Count (full) 0
199
+ [ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
200
+ Initial Block Size 2.0 MB
201
+ Used Block Count 2
202
+ Overflow Count (too large) 0
203
+ Overflow Count (full) 0
204
+ [ALLOC_TEMP_JOB_ASYNC (Background)]
205
+ Initial Block Size 1.0 MB
206
+ Used Block Count 3
207
+ Overflow Count (too large) 0
208
+ Overflow Count (full) 0
209
+ [ALLOC_GFX] Dual Thread Allocator
210
+ Peak main deferred allocation count 0
211
+ [ALLOC_BUCKET]
212
+ Large Block size 4.0 MB
213
+ Used Block count 1
214
+ Peak Allocated bytes 1.0 MB
215
+ [ALLOC_GFX_MAIN]
216
+ Peak usage frame count: [32.0 KB-64.0 KB]: 4581 frames, [64.0 KB-128.0 KB]: 882 frames
217
+ Requested Block Size 16.0 MB
218
+ Peak Block count 1
219
+ Peak Allocated memory 66.4 KB
220
+ Peak Large allocation bytes 0 B
221
+ [ALLOC_GFX_THREAD]
222
+ Peak usage frame count: [32.0 KB-64.0 KB]: 5463 frames
223
+ Requested Block Size 16.0 MB
224
+ Peak Block count 1
225
+ Peak Allocated memory 39.6 KB
226
+ Peak Large allocation bytes 0 B
227
+ [ALLOC_CACHEOBJECTS] Dual Thread Allocator
228
+ Peak main deferred allocation count 0
229
+ [ALLOC_BUCKET]
230
+ Large Block size 4.0 MB
231
+ Used Block count 1
232
+ Peak Allocated bytes 1.0 MB
233
+ [ALLOC_CACHEOBJECTS_MAIN]
234
+ Peak usage frame count: [0.5 MB-1.0 MB]: 5463 frames
235
+ Requested Block Size 4.0 MB
236
+ Peak Block count 1
237
+ Peak Allocated memory 0.6 MB
238
+ Peak Large allocation bytes 0 B
239
+ [ALLOC_CACHEOBJECTS_THREAD]
240
+ Peak usage frame count: [0.5 MB-1.0 MB]: 5462 frames, [2.0 MB-4.0 MB]: 1 frames
241
+ Requested Block Size 4.0 MB
242
+ Peak Block count 1
243
+ Peak Allocated memory 2.2 MB
244
+ Peak Large allocation bytes 0 B
245
+ [ALLOC_TYPETREE] Dual Thread Allocator
246
+ Peak main deferred allocation count 0
247
+ [ALLOC_BUCKET]
248
+ Large Block size 4.0 MB
249
+ Used Block count 1
250
+ Peak Allocated bytes 1.0 MB
251
+ [ALLOC_TYPETREE_MAIN]
252
+ Peak usage frame count: [0-1.0 KB]: 5463 frames
253
+ Requested Block Size 2.0 MB
254
+ Peak Block count 1
255
+ Peak Allocated memory 1.0 KB
256
+ Peak Large allocation bytes 0 B
257
+ [ALLOC_TYPETREE_THREAD]
258
+ Peak usage frame count: [1.0 KB-2.0 KB]: 5463 frames
259
+ Requested Block Size 2.0 MB
260
+ Peak Block count 1
261
+ Peak Allocated memory 1.7 KB
262
+ Peak Large allocation bytes 0 B
run_logs/timers.json ADDED
@@ -0,0 +1,425 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "root",
3
+ "gauges": {
4
+ "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 2.385432004928589,
6
+ "min": 2.385432004928589,
7
+ "max": 2.8903470039367676,
8
+ "count": 20
9
+ },
10
+ "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 22907.3046875,
12
+ "min": 22907.3046875,
13
+ "max": 29695.42578125,
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": 4.15912389755249,
30
+ "min": 0.013997421599924564,
31
+ "max": 4.15912389755249,
32
+ "count": 20
33
+ },
34
+ "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 811.0291748046875,
36
+ "min": 2.7154998779296875,
37
+ "max": 811.0291748046875,
38
+ "count": 20
39
+ },
40
+ "SnowballTarget.Policy.CuriosityValueEstimate.mean": {
41
+ "value": 0.33712518215179443,
42
+ "min": 0.0004443278885446489,
43
+ "max": 0.33712518215179443,
44
+ "count": 20
45
+ },
46
+ "SnowballTarget.Policy.CuriosityValueEstimate.sum": {
47
+ "value": 65.73941040039062,
48
+ "min": 0.08619961142539978,
49
+ "max": 67.01959228515625,
50
+ "count": 20
51
+ },
52
+ "SnowballTarget.Environment.EpisodeLength.mean": {
53
+ "value": 199.0,
54
+ "min": 199.0,
55
+ "max": 199.0,
56
+ "count": 20
57
+ },
58
+ "SnowballTarget.Environment.EpisodeLength.sum": {
59
+ "value": 10945.0,
60
+ "min": 8756.0,
61
+ "max": 10945.0,
62
+ "count": 20
63
+ },
64
+ "SnowballTarget.Environment.CumulativeReward.mean": {
65
+ "value": 14.818181818181818,
66
+ "min": 3.090909090909091,
67
+ "max": 14.818181818181818,
68
+ "count": 20
69
+ },
70
+ "SnowballTarget.Environment.CumulativeReward.sum": {
71
+ "value": 652.0,
72
+ "min": 136.0,
73
+ "max": 786.0,
74
+ "count": 20
75
+ },
76
+ "SnowballTarget.Policy.ExtrinsicReward.mean": {
77
+ "value": 14.818181818181818,
78
+ "min": 3.090909090909091,
79
+ "max": 14.818181818181818,
80
+ "count": 20
81
+ },
82
+ "SnowballTarget.Policy.ExtrinsicReward.sum": {
83
+ "value": 652.0,
84
+ "min": 136.0,
85
+ "max": 786.0,
86
+ "count": 20
87
+ },
88
+ "SnowballTarget.Policy.CuriosityReward.mean": {
89
+ "value": 0.9024262693922289,
90
+ "min": 0.0,
91
+ "max": 1.07683557609993,
92
+ "count": 20
93
+ },
94
+ "SnowballTarget.Policy.CuriosityReward.sum": {
95
+ "value": 39.70675585325807,
96
+ "min": 0.0,
97
+ "max": 58.14912110939622,
98
+ "count": 20
99
+ },
100
+ "SnowballTarget.IsTraining.mean": {
101
+ "value": 1.0,
102
+ "min": 1.0,
103
+ "max": 1.0,
104
+ "count": 20
105
+ },
106
+ "SnowballTarget.IsTraining.sum": {
107
+ "value": 1.0,
108
+ "min": 1.0,
109
+ "max": 1.0,
110
+ "count": 20
111
+ },
112
+ "SnowballTarget.Losses.PolicyLoss.mean": {
113
+ "value": 0.14216311709067075,
114
+ "min": 0.13723099632516236,
115
+ "max": 0.14307166072689548,
116
+ "count": 11
117
+ },
118
+ "SnowballTarget.Losses.PolicyLoss.sum": {
119
+ "value": 0.14216311709067075,
120
+ "min": 0.13723099632516236,
121
+ "max": 0.14307166072689548,
122
+ "count": 11
123
+ },
124
+ "SnowballTarget.Losses.ValueLoss.mean": {
125
+ "value": 0.14027505533482704,
126
+ "min": 0.045727412595990155,
127
+ "max": 0.14027505533482704,
128
+ "count": 11
129
+ },
130
+ "SnowballTarget.Losses.ValueLoss.sum": {
131
+ "value": 0.14027505533482704,
132
+ "min": 0.045727412595990155,
133
+ "max": 0.14027505533482704,
134
+ "count": 11
135
+ },
136
+ "SnowballTarget.Policy.LearningRate.mean": {
137
+ "value": 2.2932092355999987e-05,
138
+ "min": 2.2932092355999987e-05,
139
+ "max": 0.000274788008404,
140
+ "count": 11
141
+ },
142
+ "SnowballTarget.Policy.LearningRate.sum": {
143
+ "value": 2.2932092355999987e-05,
144
+ "min": 2.2932092355999987e-05,
145
+ "max": 0.000274788008404,
146
+ "count": 11
147
+ },
148
+ "SnowballTarget.Policy.Epsilon.mean": {
149
+ "value": 0.107644,
150
+ "min": 0.107644,
151
+ "max": 0.19159600000000004,
152
+ "count": 11
153
+ },
154
+ "SnowballTarget.Policy.Epsilon.sum": {
155
+ "value": 0.107644,
156
+ "min": 0.107644,
157
+ "max": 0.19159600000000004,
158
+ "count": 11
159
+ },
160
+ "SnowballTarget.Policy.Beta.mean": {
161
+ "value": 0.00039143559999999975,
162
+ "min": 0.00039143559999999975,
163
+ "max": 0.0045806404000000005,
164
+ "count": 11
165
+ },
166
+ "SnowballTarget.Policy.Beta.sum": {
167
+ "value": 0.00039143559999999975,
168
+ "min": 0.00039143559999999975,
169
+ "max": 0.0045806404000000005,
170
+ "count": 11
171
+ },
172
+ "SnowballTarget.Losses.CuriosityForwardLoss.mean": {
173
+ "value": 0.04660418435455637,
174
+ "min": 0.03838069728324338,
175
+ "max": 0.07110486752575353,
176
+ "count": 11
177
+ },
178
+ "SnowballTarget.Losses.CuriosityForwardLoss.sum": {
179
+ "value": 0.04660418435455637,
180
+ "min": 0.03838069728324338,
181
+ "max": 0.07110486752575353,
182
+ "count": 11
183
+ },
184
+ "SnowballTarget.Losses.CuriosityInverseLoss.mean": {
185
+ "value": 2.065821149824205,
186
+ "min": 2.065821149824205,
187
+ "max": 2.756891046554323,
188
+ "count": 11
189
+ },
190
+ "SnowballTarget.Losses.CuriosityInverseLoss.sum": {
191
+ "value": 2.065821149824205,
192
+ "min": 2.065821149824205,
193
+ "max": 2.756891046554323,
194
+ "count": 11
195
+ }
196
+ },
197
+ "metadata": {
198
+ "timer_format_version": "0.1.0",
199
+ "start_time_seconds": "1683811596",
200
+ "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]",
201
+ "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
202
+ "mlagents_version": "0.31.0.dev0",
203
+ "mlagents_envs_version": "0.31.0.dev0",
204
+ "communication_protocol_version": "1.5.0",
205
+ "pytorch_version": "1.11.0+cu102",
206
+ "numpy_version": "1.21.2",
207
+ "end_time_seconds": "1683812358"
208
+ },
209
+ "total": 761.7432244089998,
210
+ "count": 1,
211
+ "self": 0.43862323299958916,
212
+ "children": {
213
+ "run_training.setup": {
214
+ "total": 0.04238357899998846,
215
+ "count": 1,
216
+ "self": 0.04238357899998846
217
+ },
218
+ "TrainerController.start_learning": {
219
+ "total": 761.2622175970002,
220
+ "count": 1,
221
+ "self": 0.5552386300096259,
222
+ "children": {
223
+ "TrainerController._reset_env": {
224
+ "total": 3.8741584639999473,
225
+ "count": 1,
226
+ "self": 3.8741584639999473
227
+ },
228
+ "TrainerController.advance": {
229
+ "total": 756.681970258991,
230
+ "count": 18207,
231
+ "self": 0.2753362879659562,
232
+ "children": {
233
+ "env_step": {
234
+ "total": 756.406633971025,
235
+ "count": 18207,
236
+ "self": 643.0490705560201,
237
+ "children": {
238
+ "SubprocessEnvManager._take_step": {
239
+ "total": 113.09053104500686,
240
+ "count": 18207,
241
+ "self": 2.0404263569810155,
242
+ "children": {
243
+ "TorchPolicy.evaluate": {
244
+ "total": 111.05010468802584,
245
+ "count": 18207,
246
+ "self": 111.05010468802584
247
+ }
248
+ }
249
+ },
250
+ "workers": {
251
+ "total": 0.2670323699981054,
252
+ "count": 18207,
253
+ "self": 0.0,
254
+ "children": {
255
+ "worker_root": {
256
+ "total": 759.8618616810047,
257
+ "count": 18207,
258
+ "is_parallel": true,
259
+ "self": 514.9759165389949,
260
+ "children": {
261
+ "run_training.setup": {
262
+ "total": 0.0,
263
+ "count": 0,
264
+ "is_parallel": true,
265
+ "self": 0.0,
266
+ "children": {
267
+ "steps_from_proto": {
268
+ "total": 0.005080220000081681,
269
+ "count": 1,
270
+ "is_parallel": true,
271
+ "self": 0.00354788400045436,
272
+ "children": {
273
+ "_process_rank_one_or_two_observation": {
274
+ "total": 0.0015323359996273211,
275
+ "count": 10,
276
+ "is_parallel": true,
277
+ "self": 0.0015323359996273211
278
+ }
279
+ }
280
+ },
281
+ "UnityEnvironment.step": {
282
+ "total": 0.04351448300008087,
283
+ "count": 1,
284
+ "is_parallel": true,
285
+ "self": 0.000659725000105027,
286
+ "children": {
287
+ "UnityEnvironment._generate_step_input": {
288
+ "total": 0.00037621799992848537,
289
+ "count": 1,
290
+ "is_parallel": true,
291
+ "self": 0.00037621799992848537
292
+ },
293
+ "communicator.exchange": {
294
+ "total": 0.04028667900001892,
295
+ "count": 1,
296
+ "is_parallel": true,
297
+ "self": 0.04028667900001892
298
+ },
299
+ "steps_from_proto": {
300
+ "total": 0.002191861000028439,
301
+ "count": 1,
302
+ "is_parallel": true,
303
+ "self": 0.00043742000002566783,
304
+ "children": {
305
+ "_process_rank_one_or_two_observation": {
306
+ "total": 0.001754441000002771,
307
+ "count": 10,
308
+ "is_parallel": true,
309
+ "self": 0.001754441000002771
310
+ }
311
+ }
312
+ }
313
+ }
314
+ }
315
+ }
316
+ },
317
+ "UnityEnvironment.step": {
318
+ "total": 244.88594514200986,
319
+ "count": 18206,
320
+ "is_parallel": true,
321
+ "self": 10.038581193020491,
322
+ "children": {
323
+ "UnityEnvironment._generate_step_input": {
324
+ "total": 5.299940268000682,
325
+ "count": 18206,
326
+ "is_parallel": true,
327
+ "self": 5.299940268000682
328
+ },
329
+ "communicator.exchange": {
330
+ "total": 196.67254681099803,
331
+ "count": 18206,
332
+ "is_parallel": true,
333
+ "self": 196.67254681099803
334
+ },
335
+ "steps_from_proto": {
336
+ "total": 32.87487686999066,
337
+ "count": 18206,
338
+ "is_parallel": true,
339
+ "self": 6.261275034059963,
340
+ "children": {
341
+ "_process_rank_one_or_two_observation": {
342
+ "total": 26.613601835930695,
343
+ "count": 182060,
344
+ "is_parallel": true,
345
+ "self": 26.613601835930695
346
+ }
347
+ }
348
+ }
349
+ }
350
+ }
351
+ }
352
+ }
353
+ }
354
+ }
355
+ }
356
+ }
357
+ }
358
+ },
359
+ "trainer_threads": {
360
+ "total": 0.00014040799987924402,
361
+ "count": 1,
362
+ "self": 0.00014040799987924402,
363
+ "children": {
364
+ "thread_root": {
365
+ "total": 0.0,
366
+ "count": 0,
367
+ "is_parallel": true,
368
+ "self": 0.0,
369
+ "children": {
370
+ "trainer_advance": {
371
+ "total": 751.8785557158856,
372
+ "count": 543778,
373
+ "is_parallel": true,
374
+ "self": 13.25509078697769,
375
+ "children": {
376
+ "process_trajectory": {
377
+ "total": 354.3881192759077,
378
+ "count": 543778,
379
+ "is_parallel": true,
380
+ "self": 353.0601057139072,
381
+ "children": {
382
+ "RLTrainer._checkpoint": {
383
+ "total": 1.3280135620004785,
384
+ "count": 4,
385
+ "is_parallel": true,
386
+ "self": 1.3280135620004785
387
+ }
388
+ }
389
+ },
390
+ "_update_policy": {
391
+ "total": 384.2353456530002,
392
+ "count": 11,
393
+ "is_parallel": true,
394
+ "self": 200.98167754598535,
395
+ "children": {
396
+ "TorchPPOOptimizer.update": {
397
+ "total": 183.25366810701485,
398
+ "count": 17313,
399
+ "is_parallel": true,
400
+ "self": 183.25366810701485
401
+ }
402
+ }
403
+ }
404
+ }
405
+ }
406
+ }
407
+ }
408
+ }
409
+ },
410
+ "TrainerController._save_models": {
411
+ "total": 0.15070983599980536,
412
+ "count": 1,
413
+ "self": 0.0010795619996315509,
414
+ "children": {
415
+ "RLTrainer._checkpoint": {
416
+ "total": 0.1496302740001738,
417
+ "count": 1,
418
+ "self": 0.1496302740001738
419
+ }
420
+ }
421
+ }
422
+ }
423
+ }
424
+ }
425
+ }
run_logs/training_status.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "SnowballTarget": {
3
+ "checkpoints": [
4
+ {
5
+ "steps": 49936,
6
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
+ "reward": 5.454545454545454,
8
+ "creation_time": 1683811774.2959902,
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",
16
+ "reward": 9.12987012987013,
17
+ "creation_time": 1683811970.7363544,
18
+ "auxillary_file_paths": [
19
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
20
+ ]
21
+ },
22
+ {
23
+ "steps": 149984,
24
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
25
+ "reward": 11.857142857142858,
26
+ "creation_time": 1683812165.6711266,
27
+ "auxillary_file_paths": [
28
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
29
+ ]
30
+ },
31
+ {
32
+ "steps": 199984,
33
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
34
+ "reward": 14.61038961038961,
35
+ "creation_time": 1683812357.8780396,
36
+ "auxillary_file_paths": [
37
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
38
+ ]
39
+ },
40
+ {
41
+ "steps": 200112,
42
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
43
+ "reward": 14.61038961038961,
44
+ "creation_time": 1683812358.059873,
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": 14.61038961038961,
54
+ "creation_time": 1683812358.059873,
55
+ "auxillary_file_paths": [
56
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
+ ]
58
+ }
59
+ },
60
+ "metadata": {
61
+ "stats_format_version": "0.3.0",
62
+ "mlagents_version": "0.31.0.dev0",
63
+ "torch_version": "1.11.0+cu102"
64
+ }
65
+ }