liadraz commited on
Commit
c2576fe
1 Parent(s): 4d731e1

added model

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: liadraz/ppo-SnowballTarget
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:c94e244ddf255e9aa65e6faeec0ac6597b21111e83de6b3d3549f403a1ca0c82
3
+ size 646532
SnowballTarget/SnowballTarget-149960.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33c48ee4321dbe2bd6a61b4948571332adfc3987e3f4abba5f33f1957f13ac29
3
+ size 646532
SnowballTarget/SnowballTarget-149960.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c6ccfc5d385b9913e8628bce836adb37159eec151cb5268248048ceae6c5768
3
+ size 3843968
SnowballTarget/SnowballTarget-199960.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c94e244ddf255e9aa65e6faeec0ac6597b21111e83de6b3d3549f403a1ca0c82
3
+ size 646532
SnowballTarget/SnowballTarget-199960.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2afcd99e301c2411339656794ce24d7992cfce580c0619486d9734a674fe0c77
3
+ size 3843968
SnowballTarget/SnowballTarget-200112.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c94e244ddf255e9aa65e6faeec0ac6597b21111e83de6b3d3549f403a1ca0c82
3
+ size 646532
SnowballTarget/SnowballTarget-200112.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:572f1dd2a8b3fdb5cd64fa402fb5f8915f1ef5c0bed3fe98aab7a6ce6413b544
3
+ size 3843968
SnowballTarget/SnowballTarget-26312.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16837111e0bcad1963f8e5e8c280c6479c81b4051982777ed56a99584d5dffb5
3
+ size 646532
SnowballTarget/SnowballTarget-26312.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9077b9495323cf08e1a355e4eda049e101f1fe38e966f77de8711178b31828ce
3
+ size 3843968
SnowballTarget/SnowballTarget-49976.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d65e710bd04cc20070404b16721442053ad4d9b6a309b486d4fd50b0aed124b1
3
+ size 646532
SnowballTarget/SnowballTarget-49976.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d26b18f633d0340f8d3ea502d39b93e2406278b81ffe79393672062da44fef9
3
+ size 3843968
SnowballTarget/SnowballTarget-99936.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0a3859b88a7e4e436009791fa77fd6d652ad7fbe5b8b85fb04b12713c1b2dfc
3
+ size 646532
SnowballTarget/SnowballTarget-99936.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6283a22764866986883248a22cee412f2a309e226ef0f9d4787582090b9c2de0
3
+ size 3843968
SnowballTarget/checkpoint.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:572f1dd2a8b3fdb5cd64fa402fb5f8915f1ef5c0bed3fe98aab7a6ce6413b544
3
+ size 3843968
SnowballTarget/events.out.tfevents.1692816502.ca1698f6b1b7.3968.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bca20105134b15613220f80b7cc6e74d2e8f662251c1320ee029f5d0aa4ca812
3
+ size 12637
SnowballTarget/events.out.tfevents.1692816670.ca1698f6b1b7.4735.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87ddd65bac7485261c87e7f1d30e07bdefb55d58f3a01ee810f628ee3df70f1a
3
+ size 16616
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": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 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": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: 50000
18
+ network_settings:
19
+ normalize: false
20
+ hidden_units: 256
21
+ num_layers: 2
22
+ vis_encode_type: simple
23
+ memory: null
24
+ goal_conditioning_type: hyper
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: 200000
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
+ seed: -1
54
+ max_lifetime_restarts: 10
55
+ restarts_rate_limit_n: 1
56
+ restarts_rate_limit_period_s: 60
57
+ engine_settings:
58
+ width: 84
59
+ height: 84
60
+ quality_level: 5
61
+ time_scale: 20
62
+ target_frame_rate: -1
63
+ capture_frame_rate: 60
64
+ no_graphics: true
65
+ environment_parameters: null
66
+ checkpoint_settings:
67
+ run_id: SnowballTarget1
68
+ initialize_from: null
69
+ load_model: false
70
+ resume: true
71
+ force: false
72
+ train_model: false
73
+ inference: false
74
+ results_dir: results
75
+ torch_settings:
76
+ device: null
77
+ 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 0.082 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: 0.698996 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]: 4661 frames, [16.0 KB-32.0 KB]: 79 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 36
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]: 4741 frames
176
+ Requested Block Size 16.0 MB
177
+ Peak Block count 1
178
+ Peak Allocated memory 6.5 MB
179
+ Peak Large allocation bytes 0 B
180
+ [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 4741 frames
182
+ Requested Block Size 16.0 MB
183
+ Peak Block count 1
184
+ Peak Allocated memory 17.8 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]: 3842 frames, [64.0 KB-128.0 KB]: 899 frames
214
+ Requested Block Size 16.0 MB
215
+ Peak Block count 1
216
+ Peak Allocated memory 67.3 KB
217
+ Peak Large allocation bytes 0 B
218
+ [ALLOC_GFX_THREAD]
219
+ Peak usage frame count: [32.0 KB-64.0 KB]: 4741 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]: 4741 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]: 4740 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]: 4741 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]: 4741 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 +1,377 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "root",
3
+ "gauges": {
4
+ "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.8687857389450073,
6
+ "min": 0.8687857389450073,
7
+ "max": 2.6227786540985107,
8
+ "count": 18
9
+ },
10
+ "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 8304.72265625,
12
+ "min": 8304.72265625,
13
+ "max": 24682.32421875,
14
+ "count": 18
15
+ },
16
+ "SnowballTarget.Step.mean": {
17
+ "value": 199960.0,
18
+ "min": 29984.0,
19
+ "max": 199960.0,
20
+ "count": 18
21
+ },
22
+ "SnowballTarget.Step.sum": {
23
+ "value": 199960.0,
24
+ "min": 29984.0,
25
+ "max": 199960.0,
26
+ "count": 18
27
+ },
28
+ "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 12.608823776245117,
30
+ "min": 2.579326868057251,
31
+ "max": 12.608823776245117,
32
+ "count": 18
33
+ },
34
+ "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2458.720703125,
36
+ "min": 172.8148956298828,
37
+ "max": 2535.80615234375,
38
+ "count": 18
39
+ },
40
+ "SnowballTarget.Environment.EpisodeLength.mean": {
41
+ "value": 199.0,
42
+ "min": 199.0,
43
+ "max": 199.0,
44
+ "count": 18
45
+ },
46
+ "SnowballTarget.Environment.EpisodeLength.sum": {
47
+ "value": 8756.0,
48
+ "min": 2189.0,
49
+ "max": 10945.0,
50
+ "count": 18
51
+ },
52
+ "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.06342106889682256,
54
+ "min": 0.06342106889682256,
55
+ "max": 0.07515152978286256,
56
+ "count": 18
57
+ },
58
+ "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.25368427558729023,
60
+ "min": 0.07160567258627755,
61
+ "max": 0.3757576489143128,
62
+ "count": 18
63
+ },
64
+ "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.20883192932781053,
66
+ "min": 0.19779164382055697,
67
+ "max": 0.2749632154025283,
68
+ "count": 18
69
+ },
70
+ "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.8353277173112421,
72
+ "min": 0.2718317747736971,
73
+ "max": 1.3748160770126416,
74
+ "count": 18
75
+ },
76
+ "SnowballTarget.Policy.LearningRate.mean": {
77
+ "value": 8.214097262000005e-06,
78
+ "min": 8.214097262000005e-06,
79
+ "max": 0.00025736401421199996,
80
+ "count": 18
81
+ },
82
+ "SnowballTarget.Policy.LearningRate.sum": {
83
+ "value": 3.285638904800002e-05,
84
+ "min": 3.285638904800002e-05,
85
+ "max": 0.00123732008756,
86
+ "count": 18
87
+ },
88
+ "SnowballTarget.Policy.Epsilon.mean": {
89
+ "value": 0.10273800000000001,
90
+ "min": 0.10273800000000001,
91
+ "max": 0.18578800000000004,
92
+ "count": 18
93
+ },
94
+ "SnowballTarget.Policy.Epsilon.sum": {
95
+ "value": 0.41095200000000004,
96
+ "min": 0.18578800000000004,
97
+ "max": 0.9124400000000001,
98
+ "count": 18
99
+ },
100
+ "SnowballTarget.Policy.Beta.mean": {
101
+ "value": 0.0001466262000000001,
102
+ "min": 0.0001466262000000001,
103
+ "max": 0.0042908212,
104
+ "count": 18
105
+ },
106
+ "SnowballTarget.Policy.Beta.sum": {
107
+ "value": 0.0005865048000000004,
108
+ "min": 0.0005865048000000004,
109
+ "max": 0.020630756,
110
+ "count": 18
111
+ },
112
+ "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 25.454545454545453,
114
+ "min": 7.909090909090909,
115
+ "max": 25.454545454545453,
116
+ "count": 18
117
+ },
118
+ "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1120.0,
120
+ "min": 87.0,
121
+ "max": 1359.0,
122
+ "count": 18
123
+ },
124
+ "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 25.454545454545453,
126
+ "min": 7.909090909090909,
127
+ "max": 25.454545454545453,
128
+ "count": 18
129
+ },
130
+ "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1120.0,
132
+ "min": 87.0,
133
+ "max": 1359.0,
134
+ "count": 18
135
+ },
136
+ "SnowballTarget.IsTraining.mean": {
137
+ "value": 1.0,
138
+ "min": 1.0,
139
+ "max": 1.0,
140
+ "count": 18
141
+ },
142
+ "SnowballTarget.IsTraining.sum": {
143
+ "value": 1.0,
144
+ "min": 1.0,
145
+ "max": 1.0,
146
+ "count": 18
147
+ }
148
+ },
149
+ "metadata": {
150
+ "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1692816669",
152
+ "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
153
+ "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume",
154
+ "mlagents_version": "0.31.0.dev0",
155
+ "mlagents_envs_version": "0.31.0.dev0",
156
+ "communication_protocol_version": "1.5.0",
157
+ "pytorch_version": "1.11.0+cu102",
158
+ "numpy_version": "1.21.2",
159
+ "end_time_seconds": "1692817078"
160
+ },
161
+ "total": 409.725161716,
162
+ "count": 1,
163
+ "self": 0.4358088129997668,
164
+ "children": {
165
+ "run_training.setup": {
166
+ "total": 0.03939240900012919,
167
+ "count": 1,
168
+ "self": 0.03939240900012919
169
+ },
170
+ "TrainerController.start_learning": {
171
+ "total": 409.2499604940001,
172
+ "count": 1,
173
+ "self": 0.48618473099691073,
174
+ "children": {
175
+ "TrainerController._reset_env": {
176
+ "total": 5.233312679999926,
177
+ "count": 1,
178
+ "self": 5.233312679999926
179
+ },
180
+ "TrainerController.advance": {
181
+ "total": 403.3927433660033,
182
+ "count": 15803,
183
+ "self": 0.22470167300343746,
184
+ "children": {
185
+ "env_step": {
186
+ "total": 403.16804169299985,
187
+ "count": 15803,
188
+ "self": 291.23483566800815,
189
+ "children": {
190
+ "SubprocessEnvManager._take_step": {
191
+ "total": 111.69486024400476,
192
+ "count": 15803,
193
+ "self": 1.4851255690232392,
194
+ "children": {
195
+ "TorchPolicy.evaluate": {
196
+ "total": 110.20973467498152,
197
+ "count": 15803,
198
+ "self": 110.20973467498152
199
+ }
200
+ }
201
+ },
202
+ "workers": {
203
+ "total": 0.23834578098694692,
204
+ "count": 15803,
205
+ "self": 0.0,
206
+ "children": {
207
+ "worker_root": {
208
+ "total": 407.9182839439993,
209
+ "count": 15803,
210
+ "is_parallel": true,
211
+ "self": 193.33293445200252,
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": 0.0027271930000551947,
221
+ "count": 1,
222
+ "is_parallel": true,
223
+ "self": 0.0006626520000736491,
224
+ "children": {
225
+ "_process_rank_one_or_two_observation": {
226
+ "total": 0.0020645409999815456,
227
+ "count": 10,
228
+ "is_parallel": true,
229
+ "self": 0.0020645409999815456
230
+ }
231
+ }
232
+ },
233
+ "UnityEnvironment.step": {
234
+ "total": 0.08112083999981223,
235
+ "count": 1,
236
+ "is_parallel": true,
237
+ "self": 0.0006179699998938304,
238
+ "children": {
239
+ "UnityEnvironment._generate_step_input": {
240
+ "total": 0.00041931200007638836,
241
+ "count": 1,
242
+ "is_parallel": true,
243
+ "self": 0.00041931200007638836
244
+ },
245
+ "communicator.exchange": {
246
+ "total": 0.07792154999992817,
247
+ "count": 1,
248
+ "is_parallel": true,
249
+ "self": 0.07792154999992817
250
+ },
251
+ "steps_from_proto": {
252
+ "total": 0.0021620079999138397,
253
+ "count": 1,
254
+ "is_parallel": true,
255
+ "self": 0.0005079440002191404,
256
+ "children": {
257
+ "_process_rank_one_or_two_observation": {
258
+ "total": 0.0016540639996946993,
259
+ "count": 10,
260
+ "is_parallel": true,
261
+ "self": 0.0016540639996946993
262
+ }
263
+ }
264
+ }
265
+ }
266
+ }
267
+ }
268
+ },
269
+ "UnityEnvironment.step": {
270
+ "total": 214.5853494919968,
271
+ "count": 15802,
272
+ "is_parallel": true,
273
+ "self": 8.957819087994494,
274
+ "children": {
275
+ "UnityEnvironment._generate_step_input": {
276
+ "total": 4.497118653010602,
277
+ "count": 15802,
278
+ "is_parallel": true,
279
+ "self": 4.497118653010602
280
+ },
281
+ "communicator.exchange": {
282
+ "total": 169.9384629499839,
283
+ "count": 15802,
284
+ "is_parallel": true,
285
+ "self": 169.9384629499839
286
+ },
287
+ "steps_from_proto": {
288
+ "total": 31.19194880100781,
289
+ "count": 15802,
290
+ "is_parallel": true,
291
+ "self": 5.786408259057453,
292
+ "children": {
293
+ "_process_rank_one_or_two_observation": {
294
+ "total": 25.40554054195036,
295
+ "count": 158020,
296
+ "is_parallel": true,
297
+ "self": 25.40554054195036
298
+ }
299
+ }
300
+ }
301
+ }
302
+ }
303
+ }
304
+ }
305
+ }
306
+ }
307
+ }
308
+ }
309
+ }
310
+ },
311
+ "trainer_threads": {
312
+ "total": 0.0001401260001330229,
313
+ "count": 1,
314
+ "self": 0.0001401260001330229,
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": 399.85658967214727,
324
+ "count": 393732,
325
+ "is_parallel": true,
326
+ "self": 9.073231241175108,
327
+ "children": {
328
+ "process_trajectory": {
329
+ "total": 221.7125994919727,
330
+ "count": 393732,
331
+ "is_parallel": true,
332
+ "self": 220.46351121297266,
333
+ "children": {
334
+ "RLTrainer._checkpoint": {
335
+ "total": 1.2490882790000342,
336
+ "count": 4,
337
+ "is_parallel": true,
338
+ "self": 1.2490882790000342
339
+ }
340
+ }
341
+ },
342
+ "_update_policy": {
343
+ "total": 169.07075893899946,
344
+ "count": 78,
345
+ "is_parallel": true,
346
+ "self": 61.56930568899725,
347
+ "children": {
348
+ "TorchPPOOptimizer.update": {
349
+ "total": 107.50145325000221,
350
+ "count": 3975,
351
+ "is_parallel": true,
352
+ "self": 107.50145325000221
353
+ }
354
+ }
355
+ }
356
+ }
357
+ }
358
+ }
359
+ }
360
+ }
361
+ },
362
+ "TrainerController._save_models": {
363
+ "total": 0.13757959099984873,
364
+ "count": 1,
365
+ "self": 0.001011767999671065,
366
+ "children": {
367
+ "RLTrainer._checkpoint": {
368
+ "total": 0.13656782300017767,
369
+ "count": 1,
370
+ "self": 0.13656782300017767
371
+ }
372
+ }
373
+ }
374
+ }
375
+ }
376
+ }
377
+ }
run_logs/training_status.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "SnowballTarget": {
3
+ "checkpoints": [
4
+ {
5
+ "steps": 26312,
6
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-26312.onnx",
7
+ "reward": null,
8
+ "creation_time": 1692816569.753852,
9
+ "auxillary_file_paths": [
10
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-26312.pt"
11
+ ]
12
+ },
13
+ {
14
+ "steps": 49976,
15
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49976.onnx",
16
+ "reward": 12.454545454545455,
17
+ "creation_time": 1692816729.9257433,
18
+ "auxillary_file_paths": [
19
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-49976.pt"
20
+ ]
21
+ },
22
+ {
23
+ "steps": 99936,
24
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99936.onnx",
25
+ "reward": 20.363636363636363,
26
+ "creation_time": 1692816846.3690047,
27
+ "auxillary_file_paths": [
28
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-99936.pt"
29
+ ]
30
+ },
31
+ {
32
+ "steps": 149960,
33
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149960.onnx",
34
+ "reward": 23.545454545454547,
35
+ "creation_time": 1692816964.3796234,
36
+ "auxillary_file_paths": [
37
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-149960.pt"
38
+ ]
39
+ },
40
+ {
41
+ "steps": 199960,
42
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199960.onnx",
43
+ "reward": 25.0,
44
+ "creation_time": 1692817078.170386,
45
+ "auxillary_file_paths": [
46
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-199960.pt"
47
+ ]
48
+ },
49
+ {
50
+ "steps": 200112,
51
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
52
+ "reward": 24.454545454545453,
53
+ "creation_time": 1692817078.3485012,
54
+ "auxillary_file_paths": [
55
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
56
+ ]
57
+ }
58
+ ],
59
+ "final_checkpoint": {
60
+ "steps": 200112,
61
+ "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
62
+ "reward": 24.454545454545453,
63
+ "creation_time": 1692817078.3485012,
64
+ "auxillary_file_paths": [
65
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
66
+ ]
67
+ }
68
+ },
69
+ "metadata": {
70
+ "stats_format_version": "0.3.0",
71
+ "mlagents_version": "0.31.0.dev0",
72
+ "torch_version": "1.11.0+cu102"
73
+ }
74
+ }