khatkeashish commited on
Commit
fd07c5a
·
1 Parent(s): dcfcba2

First Push

Browse files
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: khatkeashish/ppo-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 sha256:414d0ae56e1e7ac71f6ac9e94564aca0bb6d57956065ecc701dee5c4bd8983cf
3
+ size 646532
SnowballTarget/SnowballTarget-149984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50e8410fdc405bf14c1c32b4c222ce2f4b088f7fd87a13104b0e2e238c133fba
3
+ size 646532
SnowballTarget/SnowballTarget-149984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3945c2f0fa8de8639d11c1a2dbbc265a612c89c15e0c628a08ce7119b383f12c
3
+ size 3843968
SnowballTarget/SnowballTarget-199984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:414d0ae56e1e7ac71f6ac9e94564aca0bb6d57956065ecc701dee5c4bd8983cf
3
+ size 646532
SnowballTarget/SnowballTarget-199984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:feb5ae881a3e4fbca5fcf178119191d1c7773064f335c094db93243b4a772628
3
+ size 3843968
SnowballTarget/SnowballTarget-200112.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:414d0ae56e1e7ac71f6ac9e94564aca0bb6d57956065ecc701dee5c4bd8983cf
3
+ size 646532
SnowballTarget/SnowballTarget-200112.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:139ec0a76de9555f60dde6f5df0a07b953bd6e3546a9f13c2398ee7e8c90fcd8
3
+ size 3843968
SnowballTarget/SnowballTarget-49936.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab838473598a85bee754189756f4d3bb6472175774f239336521ae7765234ad9
3
+ size 646532
SnowballTarget/SnowballTarget-49936.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd62a959729ed37d902cb8352d1eb8ef5682ff5272e4ac42c8bb3f79cc972ff3
3
+ size 3843968
SnowballTarget/SnowballTarget-99960.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0a5d28fe7355b6af1641abe00407cc07957fc7f6528114a00f4a7817ae6d8d2
3
+ size 646532
SnowballTarget/SnowballTarget-99960.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e44f0997e3b24edd5f3d00cf4fe076d15a1138456958cbc58163171bb2fffd76
3
+ size 3843968
SnowballTarget/checkpoint.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:139ec0a76de9555f60dde6f5df0a07b953bd6e3546a9f13c2398ee7e8c90fcd8
3
+ size 3843968
SnowballTarget/events.out.tfevents.1675610817.ash.47811.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2eaaccffd8e4692a5bc00073d2a4b875d6b848bbbceb6f04ebbb04779d6e0bcd
3
+ size 23385
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"}, "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, "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 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ network_settings:
18
+ normalize: false
19
+ hidden_units: 256
20
+ num_layers: 2
21
+ vis_encode_type: simple
22
+ memory: null
23
+ goal_conditioning_type: hyper
24
+ deterministic: false
25
+ reward_signals:
26
+ extrinsic:
27
+ gamma: 0.99
28
+ strength: 1.0
29
+ network_settings:
30
+ normalize: false
31
+ hidden_units: 128
32
+ num_layers: 2
33
+ vis_encode_type: simple
34
+ memory: null
35
+ goal_conditioning_type: hyper
36
+ deterministic: false
37
+ init_path: null
38
+ keep_checkpoints: 10
39
+ checkpoint_interval: 50000
40
+ max_steps: 200000
41
+ time_horizon: 64
42
+ summary_freq: 10000
43
+ threaded: true
44
+ self_play: null
45
+ behavioral_cloning: null
46
+ env_settings:
47
+ env_path: ./training-envs-executables/linux/SnowballTarget/SnowballTarget
48
+ env_args: null
49
+ base_port: 5005
50
+ num_envs: 1
51
+ num_areas: 1
52
+ seed: -1
53
+ max_lifetime_restarts: 10
54
+ restarts_rate_limit_n: 1
55
+ restarts_rate_limit_period_s: 60
56
+ engine_settings:
57
+ width: 84
58
+ height: 84
59
+ quality_level: 5
60
+ time_scale: 20
61
+ target_frame_rate: -1
62
+ capture_frame_rate: 60
63
+ no_graphics: true
64
+ environment_parameters: null
65
+ checkpoint_settings:
66
+ run_id: SnowballTarget1
67
+ initialize_from: null
68
+ load_model: false
69
+ resume: false
70
+ force: false
71
+ train_model: false
72
+ inference: false
73
+ results_dir: results
74
+ torch_settings:
75
+ device: null
76
+ debug: false
run_logs/Player-0.log ADDED
@@ -0,0 +1,292 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Mono path[0] = '/home/ash/ak/code/Courses/RL/hugging_face/unit_5/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/Managed'
2
+ Mono config path = '/home/ash/ak/code/Courses/RL/hugging_face/unit_5/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: /home/ash/.config/unity3d/Hugging Face
6
+ PlayerPrefs - Creating folder: /home/ash/.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 /home/ash/ak/code/Courses/RL/hugging_face/unit_5/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
+ Begin MonoManager ReloadAssembly
17
+ - Completed reload, in 0.092 seconds
18
+ ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
19
+ ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
20
+ ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
21
+ WARNING: Shader Unsupported: 'Standard' - All subshaders removed
22
+ WARNING: Shader Did you use #pragma only_renderers and omit this platform?
23
+ WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
24
+ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
25
+ WARNING: Shader Unsupported: 'Standard' - All subshaders removed
26
+ WARNING: Shader Did you use #pragma only_renderers and omit this platform?
27
+ WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
28
+ UnloadTime: 0.619794 ms
29
+ ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
30
+ requesting resize 84 x 84
31
+ Setting up 6 worker threads for Enlighten.
32
+ Memory Statistics:
33
+ [ALLOC_TEMP_TLS] TLS Allocator
34
+ StackAllocators :
35
+ [ALLOC_TEMP_MAIN]
36
+ Peak usage frame count: [8.0 KB-16.0 KB]: 5370 frames, [16.0 KB-32.0 KB]: 91 frames, [2.0 MB-4.0 MB]: 1 frames
37
+ Initial Block Size 4.0 MB
38
+ Current Block Size 4.0 MB
39
+ Peak Allocated Bytes 2.0 MB
40
+ Overflow Count 0
41
+ [ALLOC_TEMP_Loading.AsyncRead]
42
+ Initial Block Size 64.0 KB
43
+ Current Block Size 64.0 KB
44
+ Peak Allocated Bytes 278 B
45
+ Overflow Count 0
46
+ [ALLOC_TEMP_Loading.PreloadManager]
47
+ Initial Block Size 256.0 KB
48
+ Current Block Size 304.0 KB
49
+ Peak Allocated Bytes 229.0 KB
50
+ Overflow Count 4
51
+ [ALLOC_TEMP_Background Job.Worker 8]
52
+ Initial Block Size 32.0 KB
53
+ Current Block Size 32.0 KB
54
+ Peak Allocated Bytes 0 B
55
+ Overflow Count 0
56
+ [ALLOC_TEMP_Job.Worker 6]
57
+ Initial Block Size 256.0 KB
58
+ Current Block Size 256.0 KB
59
+ Peak Allocated Bytes 3.6 KB
60
+ Overflow Count 0
61
+ [ALLOC_TEMP_Job.Worker 0]
62
+ Initial Block Size 256.0 KB
63
+ Current Block Size 256.0 KB
64
+ Peak Allocated Bytes 3.6 KB
65
+ Overflow Count 0
66
+ [ALLOC_TEMP_Background Job.Worker 10]
67
+ Initial Block Size 32.0 KB
68
+ Current Block Size 32.0 KB
69
+ Peak Allocated Bytes 0 B
70
+ Overflow Count 0
71
+ [ALLOC_TEMP_Background Job.Worker 9]
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_Job.Worker 5]
77
+ Initial Block Size 256.0 KB
78
+ Current Block Size 256.0 KB
79
+ Peak Allocated Bytes 3.6 KB
80
+ Overflow Count 0
81
+ [ALLOC_TEMP_Background Job.Worker 14]
82
+ Initial Block Size 32.0 KB
83
+ Current Block Size 32.0 KB
84
+ Peak Allocated Bytes 0 B
85
+ Overflow Count 0
86
+ [ALLOC_TEMP_Background Job.Worker 6]
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_Job.Worker 4]
92
+ Initial Block Size 256.0 KB
93
+ Current Block Size 256.0 KB
94
+ Peak Allocated Bytes 3.6 KB
95
+ Overflow Count 0
96
+ [ALLOC_TEMP_Job.Worker 3]
97
+ Initial Block Size 256.0 KB
98
+ Current Block Size 256.0 KB
99
+ Peak Allocated Bytes 3.6 KB
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] x 6
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] x 11
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_Job.Worker 9]
142
+ Initial Block Size 256.0 KB
143
+ Current Block Size 256.0 KB
144
+ Peak Allocated Bytes 3.6 KB
145
+ Overflow Count 0
146
+ [ALLOC_TEMP_Background Job.Worker 13]
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_Job.Worker 8]
152
+ Initial Block Size 256.0 KB
153
+ Current Block Size 256.0 KB
154
+ Peak Allocated Bytes 3.6 KB
155
+ Overflow Count 0
156
+ [ALLOC_TEMP_Job.Worker 7]
157
+ Initial Block Size 256.0 KB
158
+ Current Block Size 256.0 KB
159
+ Peak Allocated Bytes 3.6 KB
160
+ Overflow Count 0
161
+ [ALLOC_TEMP_Job.Worker 1]
162
+ Initial Block Size 256.0 KB
163
+ Current Block Size 256.0 KB
164
+ Peak Allocated Bytes 3.6 KB
165
+ Overflow Count 0
166
+ [ALLOC_TEMP_Job.Worker 2]
167
+ Initial Block Size 256.0 KB
168
+ Current Block Size 256.0 KB
169
+ Peak Allocated Bytes 3.6 KB
170
+ Overflow Count 0
171
+ [ALLOC_TEMP_Background Job.Worker 3]
172
+ Initial Block Size 32.0 KB
173
+ Current Block Size 32.0 KB
174
+ Peak Allocated Bytes 0 B
175
+ Overflow Count 0
176
+ [ALLOC_TEMP_Background Job.Worker 11]
177
+ Initial Block Size 32.0 KB
178
+ Current Block Size 32.0 KB
179
+ Peak Allocated Bytes 0 B
180
+ Overflow Count 0
181
+ [ALLOC_TEMP_Job.Worker 10]
182
+ Initial Block Size 256.0 KB
183
+ Current Block Size 256.0 KB
184
+ Peak Allocated Bytes 3.6 KB
185
+ Overflow Count 0
186
+ [ALLOC_TEMP_Background Job.Worker 0]
187
+ Initial Block Size 32.0 KB
188
+ Current Block Size 32.0 KB
189
+ Peak Allocated Bytes 0 B
190
+ Overflow Count 0
191
+ [ALLOC_TEMP_Background Job.Worker 4]
192
+ Initial Block Size 32.0 KB
193
+ Current Block Size 32.0 KB
194
+ Peak Allocated Bytes 0 B
195
+ Overflow Count 0
196
+ [ALLOC_TEMP_BatchDeleteObjects]
197
+ Initial Block Size 64.0 KB
198
+ Current Block Size 64.0 KB
199
+ Peak Allocated Bytes 0 B
200
+ Overflow Count 0
201
+ [ALLOC_DEFAULT] Dual Thread Allocator
202
+ Peak main deferred allocation count 41
203
+ [ALLOC_BUCKET]
204
+ Large Block size 4.0 MB
205
+ Used Block count 1
206
+ Peak Allocated bytes 1.0 MB
207
+ [ALLOC_DEFAULT_MAIN]
208
+ Peak usage frame count: [4.0 MB-8.0 MB]: 5462 frames
209
+ Requested Block Size 16.0 MB
210
+ Peak Block count 1
211
+ Peak Allocated memory 6.8 MB
212
+ Peak Large allocation bytes 0 B
213
+ [ALLOC_DEFAULT_THREAD]
214
+ Peak usage frame count: [16.0 MB-32.0 MB]: 5462 frames
215
+ Requested Block Size 16.0 MB
216
+ Peak Block count 1
217
+ Peak Allocated memory 17.6 MB
218
+ Peak Large allocation bytes 16.0 MB
219
+ [ALLOC_TEMP_JOB_1_FRAME]
220
+ Initial Block Size 2.0 MB
221
+ Used Block Count 1
222
+ Overflow Count (too large) 0
223
+ Overflow Count (full) 0
224
+ [ALLOC_TEMP_JOB_2_FRAMES]
225
+ Initial Block Size 2.0 MB
226
+ Used Block Count 1
227
+ Overflow Count (too large) 0
228
+ Overflow Count (full) 0
229
+ [ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
230
+ Initial Block Size 2.0 MB
231
+ Used Block Count 2
232
+ Overflow Count (too large) 0
233
+ Overflow Count (full) 0
234
+ [ALLOC_TEMP_JOB_ASYNC (Background)]
235
+ Initial Block Size 1.0 MB
236
+ Used Block Count 3
237
+ Overflow Count (too large) 0
238
+ Overflow Count (full) 0
239
+ [ALLOC_GFX] Dual Thread Allocator
240
+ Peak main deferred allocation count 0
241
+ [ALLOC_BUCKET]
242
+ Large Block size 4.0 MB
243
+ Used Block count 1
244
+ Peak Allocated bytes 1.0 MB
245
+ [ALLOC_GFX_MAIN]
246
+ Peak usage frame count: [32.0 KB-64.0 KB]: 4811 frames, [64.0 KB-128.0 KB]: 651 frames
247
+ Requested Block Size 16.0 MB
248
+ Peak Block count 1
249
+ Peak Allocated memory 67.3 KB
250
+ Peak Large allocation bytes 0 B
251
+ [ALLOC_GFX_THREAD]
252
+ Peak usage frame count: [32.0 KB-64.0 KB]: 5462 frames
253
+ Requested Block Size 16.0 MB
254
+ Peak Block count 1
255
+ Peak Allocated memory 39.6 KB
256
+ Peak Large allocation bytes 0 B
257
+ [ALLOC_CACHEOBJECTS] Dual Thread Allocator
258
+ Peak main deferred allocation count 0
259
+ [ALLOC_BUCKET]
260
+ Large Block size 4.0 MB
261
+ Used Block count 1
262
+ Peak Allocated bytes 1.0 MB
263
+ [ALLOC_CACHEOBJECTS_MAIN]
264
+ Peak usage frame count: [0.5 MB-1.0 MB]: 5462 frames
265
+ Requested Block Size 4.0 MB
266
+ Peak Block count 1
267
+ Peak Allocated memory 0.6 MB
268
+ Peak Large allocation bytes 0 B
269
+ [ALLOC_CACHEOBJECTS_THREAD]
270
+ Peak usage frame count: [0.5 MB-1.0 MB]: 5461 frames, [2.0 MB-4.0 MB]: 1 frames
271
+ Requested Block Size 4.0 MB
272
+ Peak Block count 1
273
+ Peak Allocated memory 2.2 MB
274
+ Peak Large allocation bytes 0 B
275
+ [ALLOC_TYPETREE] Dual Thread Allocator
276
+ Peak main deferred allocation count 0
277
+ [ALLOC_BUCKET]
278
+ Large Block size 4.0 MB
279
+ Used Block count 1
280
+ Peak Allocated bytes 1.0 MB
281
+ [ALLOC_TYPETREE_MAIN]
282
+ Peak usage frame count: [0-1.0 KB]: 5462 frames
283
+ Requested Block Size 2.0 MB
284
+ Peak Block count 1
285
+ Peak Allocated memory 1.0 KB
286
+ Peak Large allocation bytes 0 B
287
+ [ALLOC_TYPETREE_THREAD]
288
+ Peak usage frame count: [1.0 KB-2.0 KB]: 5462 frames
289
+ Requested Block Size 2.0 MB
290
+ Peak Block count 1
291
+ Peak Allocated memory 1.7 KB
292
+ Peak Large allocation bytes 0 B
run_logs/timers.json ADDED
@@ -0,0 +1,377 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "root",
3
+ "gauges": {
4
+ "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.7883507609367371,
6
+ "min": 0.7883507609367371,
7
+ "max": 2.8738811016082764,
8
+ "count": 20
9
+ },
10
+ "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 7561.8603515625,
12
+ "min": 7561.8603515625,
13
+ "max": 29526.25390625,
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": 12.996211051940918,
30
+ "min": 0.2577475309371948,
31
+ "max": 12.996211051940918,
32
+ "count": 20
33
+ },
34
+ "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2534.26123046875,
36
+ "min": 50.003021240234375,
37
+ "max": 2645.0625,
38
+ "count": 20
39
+ },
40
+ "SnowballTarget.Environment.EpisodeLength.mean": {
41
+ "value": 199.0,
42
+ "min": 199.0,
43
+ "max": 199.0,
44
+ "count": 20
45
+ },
46
+ "SnowballTarget.Environment.EpisodeLength.sum": {
47
+ "value": 10945.0,
48
+ "min": 8756.0,
49
+ "max": 10945.0,
50
+ "count": 20
51
+ },
52
+ "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.06989642114472101,
54
+ "min": 0.061533780614434576,
55
+ "max": 0.0777204619810743,
56
+ "count": 20
57
+ },
58
+ "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.27958568457888405,
60
+ "min": 0.2461351224577383,
61
+ "max": 0.3615940351737663,
62
+ "count": 20
63
+ },
64
+ "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.1872509928310619,
66
+ "min": 0.10276488784938029,
67
+ "max": 0.26974370064688663,
68
+ "count": 20
69
+ },
70
+ "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.7490039713242476,
72
+ "min": 0.41105955139752115,
73
+ "max": 1.348718503234433,
74
+ "count": 20
75
+ },
76
+ "SnowballTarget.Policy.LearningRate.mean": {
77
+ "value": 8.082097306000005e-06,
78
+ "min": 8.082097306000005e-06,
79
+ "max": 0.000291882002706,
80
+ "count": 20
81
+ },
82
+ "SnowballTarget.Policy.LearningRate.sum": {
83
+ "value": 3.232838922400002e-05,
84
+ "min": 3.232838922400002e-05,
85
+ "max": 0.00138516003828,
86
+ "count": 20
87
+ },
88
+ "SnowballTarget.Policy.Epsilon.mean": {
89
+ "value": 0.10269400000000001,
90
+ "min": 0.10269400000000001,
91
+ "max": 0.19729400000000002,
92
+ "count": 20
93
+ },
94
+ "SnowballTarget.Policy.Epsilon.sum": {
95
+ "value": 0.41077600000000003,
96
+ "min": 0.41077600000000003,
97
+ "max": 0.96172,
98
+ "count": 20
99
+ },
100
+ "SnowballTarget.Policy.Beta.mean": {
101
+ "value": 0.0001444306000000001,
102
+ "min": 0.0001444306000000001,
103
+ "max": 0.0048649706,
104
+ "count": 20
105
+ },
106
+ "SnowballTarget.Policy.Beta.sum": {
107
+ "value": 0.0005777224000000004,
108
+ "min": 0.0005777224000000004,
109
+ "max": 0.023089828,
110
+ "count": 20
111
+ },
112
+ "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 25.454545454545453,
114
+ "min": 3.022727272727273,
115
+ "max": 25.954545454545453,
116
+ "count": 20
117
+ },
118
+ "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1120.0,
120
+ "min": 133.0,
121
+ "max": 1400.0,
122
+ "count": 20
123
+ },
124
+ "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 25.454545454545453,
126
+ "min": 3.022727272727273,
127
+ "max": 25.954545454545453,
128
+ "count": 20
129
+ },
130
+ "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1120.0,
132
+ "min": 133.0,
133
+ "max": 1400.0,
134
+ "count": 20
135
+ },
136
+ "SnowballTarget.IsTraining.mean": {
137
+ "value": 1.0,
138
+ "min": 1.0,
139
+ "max": 1.0,
140
+ "count": 20
141
+ },
142
+ "SnowballTarget.IsTraining.sum": {
143
+ "value": 1.0,
144
+ "min": 1.0,
145
+ "max": 1.0,
146
+ "count": 20
147
+ }
148
+ },
149
+ "metadata": {
150
+ "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1675610817",
152
+ "python_version": "3.10.4 (main, Feb 5 2023, 16:54:05) [GCC 12.2.0]",
153
+ "command_line_arguments": "/home/ash/ak/code/Courses/RL/hugging_face/venv/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
154
+ "mlagents_version": "0.30.0",
155
+ "mlagents_envs_version": "0.30.0",
156
+ "communication_protocol_version": "1.5.0",
157
+ "pytorch_version": "1.11.0+cu102",
158
+ "numpy_version": "1.21.2",
159
+ "end_time_seconds": "1675611168"
160
+ },
161
+ "total": 350.8939326119944,
162
+ "count": 1,
163
+ "self": 0.27065492999827256,
164
+ "children": {
165
+ "run_training.setup": {
166
+ "total": 0.020594925998011604,
167
+ "count": 1,
168
+ "self": 0.020594925998011604
169
+ },
170
+ "TrainerController.start_learning": {
171
+ "total": 350.6026827559981,
172
+ "count": 1,
173
+ "self": 0.4724938456492964,
174
+ "children": {
175
+ "TrainerController._reset_env": {
176
+ "total": 3.092906905003474,
177
+ "count": 1,
178
+ "self": 3.092906905003474
179
+ },
180
+ "TrainerController.advance": {
181
+ "total": 346.9285684993447,
182
+ "count": 18206,
183
+ "self": 0.24283364262373652,
184
+ "children": {
185
+ "env_step": {
186
+ "total": 346.68573485672096,
187
+ "count": 18206,
188
+ "self": 252.42335820887092,
189
+ "children": {
190
+ "SubprocessEnvManager._take_step": {
191
+ "total": 94.00843801227165,
192
+ "count": 18206,
193
+ "self": 1.2415540480287746,
194
+ "children": {
195
+ "TorchPolicy.evaluate": {
196
+ "total": 92.76688396424288,
197
+ "count": 18206,
198
+ "self": 92.76688396424288
199
+ }
200
+ }
201
+ },
202
+ "workers": {
203
+ "total": 0.25393863557837903,
204
+ "count": 18206,
205
+ "self": 0.0,
206
+ "children": {
207
+ "worker_root": {
208
+ "total": 349.97738286581443,
209
+ "count": 18206,
210
+ "is_parallel": true,
211
+ "self": 183.6330502773053,
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": 0.0015517079955316149,
221
+ "count": 1,
222
+ "is_parallel": true,
223
+ "self": 0.0005038059971411712,
224
+ "children": {
225
+ "_process_rank_one_or_two_observation": {
226
+ "total": 0.0010479019983904436,
227
+ "count": 10,
228
+ "is_parallel": true,
229
+ "self": 0.0010479019983904436
230
+ }
231
+ }
232
+ },
233
+ "UnityEnvironment.step": {
234
+ "total": 0.030766636002226733,
235
+ "count": 1,
236
+ "is_parallel": true,
237
+ "self": 0.00062792599783279,
238
+ "children": {
239
+ "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0004250089987181127,
241
+ "count": 1,
242
+ "is_parallel": true,
243
+ "self": 0.0004250089987181127
244
+ },
245
+ "communicator.exchange": {
246
+ "total": 0.027227089005464222,
247
+ "count": 1,
248
+ "is_parallel": true,
249
+ "self": 0.027227089005464222
250
+ },
251
+ "steps_from_proto": {
252
+ "total": 0.0024866120002116077,
253
+ "count": 1,
254
+ "is_parallel": true,
255
+ "self": 0.00037349799822550267,
256
+ "children": {
257
+ "_process_rank_one_or_two_observation": {
258
+ "total": 0.002113114001986105,
259
+ "count": 10,
260
+ "is_parallel": true,
261
+ "self": 0.002113114001986105
262
+ }
263
+ }
264
+ }
265
+ }
266
+ }
267
+ }
268
+ },
269
+ "UnityEnvironment.step": {
270
+ "total": 166.34433258850913,
271
+ "count": 18205,
272
+ "is_parallel": true,
273
+ "self": 8.045762701331114,
274
+ "children": {
275
+ "UnityEnvironment._generate_step_input": {
276
+ "total": 4.209461102516798,
277
+ "count": 18205,
278
+ "is_parallel": true,
279
+ "self": 4.209461102516798
280
+ },
281
+ "communicator.exchange": {
282
+ "total": 127.46449394080992,
283
+ "count": 18205,
284
+ "is_parallel": true,
285
+ "self": 127.46449394080992
286
+ },
287
+ "steps_from_proto": {
288
+ "total": 26.624614843851305,
289
+ "count": 18205,
290
+ "is_parallel": true,
291
+ "self": 5.246420289062371,
292
+ "children": {
293
+ "_process_rank_one_or_two_observation": {
294
+ "total": 21.378194554788934,
295
+ "count": 182050,
296
+ "is_parallel": true,
297
+ "self": 21.378194554788934
298
+ }
299
+ }
300
+ }
301
+ }
302
+ }
303
+ }
304
+ }
305
+ }
306
+ }
307
+ }
308
+ }
309
+ }
310
+ },
311
+ "trainer_threads": {
312
+ "total": 8.489600440952927e-05,
313
+ "count": 1,
314
+ "self": 8.489600440952927e-05,
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": 346.0045031357731,
324
+ "count": 175403,
325
+ "is_parallel": true,
326
+ "self": 3.083280578284757,
327
+ "children": {
328
+ "process_trajectory": {
329
+ "total": 190.16999289850355,
330
+ "count": 175403,
331
+ "is_parallel": true,
332
+ "self": 189.4802967345022,
333
+ "children": {
334
+ "RLTrainer._checkpoint": {
335
+ "total": 0.6896961640013615,
336
+ "count": 4,
337
+ "is_parallel": true,
338
+ "self": 0.6896961640013615
339
+ }
340
+ }
341
+ },
342
+ "_update_policy": {
343
+ "total": 152.7512296589848,
344
+ "count": 90,
345
+ "is_parallel": true,
346
+ "self": 48.96175902758114,
347
+ "children": {
348
+ "TorchPPOOptimizer.update": {
349
+ "total": 103.78947063140367,
350
+ "count": 4587,
351
+ "is_parallel": true,
352
+ "self": 103.78947063140367
353
+ }
354
+ }
355
+ }
356
+ }
357
+ }
358
+ }
359
+ }
360
+ }
361
+ },
362
+ "TrainerController._save_models": {
363
+ "total": 0.10862860999623081,
364
+ "count": 1,
365
+ "self": 0.0006953650008654222,
366
+ "children": {
367
+ "RLTrainer._checkpoint": {
368
+ "total": 0.10793324499536538,
369
+ "count": 1,
370
+ "self": 0.10793324499536538
371
+ }
372
+ }
373
+ }
374
+ }
375
+ }
376
+ }
377
+ }
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": 12.818181818181818,
8
+ "creation_time": 1675610906.2787719,
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": 22.363636363636363,
17
+ "creation_time": 1675610993.631904,
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": 25.818181818181817,
26
+ "creation_time": 1675611081.0266747,
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": 25.363636363636363,
35
+ "creation_time": 1675611167.692788,
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": 25.363636363636363,
44
+ "creation_time": 1675611167.8216197,
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": 25.363636363636363,
54
+ "creation_time": 1675611167.8216197,
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": "0.30.0",
63
+ "torch_version": "1.11.0+cu102"
64
+ }
65
+ }