Hugging Face's logo

zhiliang1
/
ppo-Pyramids

Reinforcement Learning
ml-agents
TensorBoard
ONNX
Pyramids
deep-reinforcement-learning
ML-Agents-Pyramids
Model card Files
xet
 Metrics Community
zhiliang1 commited on
Commit
f262d74
·
verified ·
1 Parent(s): a18a288

Upload PPO Pyramids (RND) trained agent

Browse files
Files changed (13) hide show
  1. Pyramids.onnx +3 -0
  2. Pyramids/Pyramids-1000017.onnx +3 -0
  3. Pyramids/Pyramids-399936.onnx +3 -0
  4. Pyramids/Pyramids-599997.onnx +3 -0
  5. Pyramids/Pyramids-799948.onnx +3 -0
  6. Pyramids/Pyramids-999889.onnx +3 -0
  7. Pyramids/events.out.tfevents.1781485889.MS-QOIFGSYDRYQW.793.0 +3 -0
  8. README.md +35 -0
  9. config.json +1 -0
  10. configuration.yaml +92 -0
  11. run_logs/Player-0.log +51 -0
  12. run_logs/timers.json +398 -0
  13. run_logs/training_status.json +65 -0
Pyramids.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93ffa2b1c89e51ca1d75d1b83f51d51a7ace6b4dea0246d0d0855bfbdc2e4cb9
3
+ size 1420238
Pyramids/Pyramids-1000017.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93ffa2b1c89e51ca1d75d1b83f51d51a7ace6b4dea0246d0d0855bfbdc2e4cb9
3
+ size 1420238
Pyramids/Pyramids-399936.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:543abdda71bbb9730d6a3f3d7445c72933411efe859349e9a3fed78e6fbefa66
3
+ size 1420238
Pyramids/Pyramids-599997.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:250b7cc4dde0399ea75ce14b3ca6d421c3cb0d42a54438f97ca05bde1f0e7055
3
+ size 1420238
Pyramids/Pyramids-799948.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a2147343ccc8ea78c5a03146540b4d51a91bb0c052cb8056059eab2705ed19b
3
+ size 1420238
Pyramids/Pyramids-999889.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93ffa2b1c89e51ca1d75d1b83f51d51a7ace6b4dea0246d0d0855bfbdc2e4cb9
3
+ size 1420238
Pyramids/events.out.tfevents.1781485889.MS-QOIFGSYDRYQW.793.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68b9cb9d782b293e3c3328afe18150378333dd2e2f7a338ead46d66458ca7bbe
3
+ size 295634
README.md ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: ml-agents
3
+ tags:
4
+ - Pyramids
5
+ - deep-reinforcement-learning
6
+ - reinforcement-learning
7
+ - ML-Agents-Pyramids
8
+ ---
9
+
10
+ # **ppo** Agent playing **Pyramids**
11
+ This is a trained model of a **ppo** agent playing **Pyramids**
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: zhiliang1/ppo-Pyramids
33
+ 3. Step 2: Select your *.nn /*.onnx file
34
+ 4. Click on Watch the agent play 👀
35
+
config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 200000, "network_settings": {"normalize": false, "hidden_units": 512, "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}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 1000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "/mnt/d/space/hf-rl/unit5/envs/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 180, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids1", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ default_settings: null
2
+ behaviors:
3
+ Pyramids:
4
+ trainer_type: ppo
5
+ hyperparameters:
6
+ batch_size: 128
7
+ buffer_size: 2048
8
+ learning_rate: 0.0003
9
+ beta: 0.01
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: 200000
18
+ network_settings:
19
+ normalize: false
20
+ hidden_units: 512
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
+ rnd:
39
+ gamma: 0.99
40
+ strength: 0.01
41
+ network_settings:
42
+ normalize: false
43
+ hidden_units: 64
44
+ num_layers: 3
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: 5
53
+ even_checkpoints: false
54
+ max_steps: 1000000
55
+ time_horizon: 128
56
+ summary_freq: 30000
57
+ threaded: false
58
+ self_play: null
59
+ behavioral_cloning: null
60
+ env_settings:
61
+ env_path: /mnt/d/space/hf-rl/unit5/envs/linux/Pyramids/Pyramids
62
+ env_args: null
63
+ base_port: 5005
64
+ num_envs: 1
65
+ num_areas: 1
66
+ timeout_wait: 180
67
+ seed: -1
68
+ max_lifetime_restarts: 10
69
+ restarts_rate_limit_n: 1
70
+ restarts_rate_limit_period_s: 60
71
+ engine_settings:
72
+ width: 84
73
+ height: 84
74
+ quality_level: 5
75
+ time_scale: 20
76
+ target_frame_rate: -1
77
+ capture_frame_rate: 60
78
+ no_graphics: true
79
+ no_graphics_monitor: false
80
+ environment_parameters: null
81
+ checkpoint_settings:
82
+ run_id: Pyramids1
83
+ initialize_from: null
84
+ load_model: false
85
+ resume: false
86
+ force: true
87
+ train_model: false
88
+ inference: false
89
+ results_dir: results
90
+ torch_settings:
91
+ device: null
92
+ debug: false
run_logs/Player-0.log ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Mono path[0] = '/mnt/d/space/hf-rl/unit5/envs/linux/Pyramids/Pyramids_Data/Managed'
2
+ Mono config path = '/mnt/d/space/hf-rl/unit5/envs/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
3
+ Found 2 interfaces on host : 0) 10.255.255.254 1) 172.29.223.232
4
+ Multi-casting "[IP] 10.255.255.254 [Port] 55005 [Flags] 2 [Guid] 4212683554 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.29.223.232) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
5
+ Preloaded 'lib_burst_generated.so'
6
+ Preloaded 'libgrpc_csharp_ext.x64.so'
7
+ Initialize engine version: 2021.3.5f1 (40eb3a945986)
8
+ [Subsystems] Discovering subsystems at path /mnt/d/space/hf-rl/unit5/envs/linux/Pyramids/Pyramids_Data/UnitySubsystems
9
+ Forcing GfxDevice: Null
10
+ GfxDevice: creating device client; threaded=0; jobified=0
11
+ NullGfxDevice:
12
+ Version: NULL 1.0 [1.0]
13
+ Renderer: Null Device
14
+ Vendor: Unity Technologies
15
+ Begin MonoManager ReloadAssembly
16
+ - Completed reload, in 2.756 seconds
17
+ ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
18
+ ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
19
+ ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
20
+ WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
21
+ WARNING: Shader Did you use #pragma only_renderers and omit this platform?
22
+ WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
23
+ ERROR: Shader Autodesk Interactive shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
24
+ WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
25
+ WARNING: Shader Did you use #pragma only_renderers and omit this platform?
26
+ WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
27
+ WARNING: Shader Unsupported: 'Legacy Shaders/Diffuse' - All subshaders removed
28
+ WARNING: Shader Did you use #pragma only_renderers and omit this platform?
29
+ WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
30
+ ERROR: Shader Legacy Shaders/Diffuse shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
31
+ WARNING: Shader Unsupported: 'Legacy Shaders/Diffuse' - All subshaders removed
32
+ WARNING: Shader Did you use #pragma only_renderers and omit this platform?
33
+ WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
34
+ WARNING: Shader Unsupported: 'ML-Agents/GridPattern' - All subshaders removed
35
+ WARNING: Shader Did you use #pragma only_renderers and omit this platform?
36
+ WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
37
+ ERROR: Shader ML-Agents/GridPattern shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
38
+ WARNING: Shader Unsupported: 'ML-Agents/GridPattern' - 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
+ 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: 5.275615 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 18 worker threads for Enlighten.
run_logs/timers.json ADDED
@@ -0,0 +1,398 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "root",
3
+ "gauges": {
4
+ "Pyramids.Policy.Entropy.mean": {
5
+ "value": 0.4627936780452728,
6
+ "min": 0.4609237313270569,
7
+ "max": 1.4670432806015015,
8
+ "count": 33
9
+ },
10
+ "Pyramids.Policy.Entropy.sum": {
11
+ "value": 13965.26171875,
12
+ "min": 13694.9658203125,
13
+ "max": 44504.2265625,
14
+ "count": 33
15
+ },
16
+ "Pyramids.Step.mean": {
17
+ "value": 989951.0,
18
+ "min": 29952.0,
19
+ "max": 989951.0,
20
+ "count": 33
21
+ },
22
+ "Pyramids.Step.sum": {
23
+ "value": 989951.0,
24
+ "min": 29952.0,
25
+ "max": 989951.0,
26
+ "count": 33
27
+ },
28
+ "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 0.47099894285202026,
30
+ "min": -0.10116783529520035,
31
+ "max": 0.5975823998451233,
32
+ "count": 33
33
+ },
34
+ "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 126.69871520996094,
36
+ "min": -24.38144874572754,
37
+ "max": 166.72549438476562,
38
+ "count": 33
39
+ },
40
+ "Pyramids.Policy.RndValueEstimate.mean": {
41
+ "value": 0.032067522406578064,
42
+ "min": -0.009064771234989166,
43
+ "max": 0.3494204878807068,
44
+ "count": 33
45
+ },
46
+ "Pyramids.Policy.RndValueEstimate.sum": {
47
+ "value": 8.626163482666016,
48
+ "min": -2.5834598541259766,
49
+ "max": 83.86091613769531,
50
+ "count": 33
51
+ },
52
+ "Pyramids.Losses.PolicyLoss.mean": {
53
+ "value": 0.06879097547928159,
54
+ "min": 0.06395186080159428,
55
+ "max": 0.07368961878207966,
56
+ "count": 33
57
+ },
58
+ "Pyramids.Losses.PolicyLoss.sum": {
59
+ "value": 0.9630736567099423,
60
+ "min": 0.4905884915637655,
61
+ "max": 1.046715185220819,
62
+ "count": 33
63
+ },
64
+ "Pyramids.Losses.ValueLoss.mean": {
65
+ "value": 0.013607813684627346,
66
+ "min": 0.00010716248847572122,
67
+ "max": 0.016594731883428877,
68
+ "count": 33
69
+ },
70
+ "Pyramids.Losses.ValueLoss.sum": {
71
+ "value": 0.19050939158478283,
72
+ "min": 0.001500274838660097,
73
+ "max": 0.22457158137209868,
74
+ "count": 33
75
+ },
76
+ "Pyramids.Policy.LearningRate.mean": {
77
+ "value": 7.3316261275857155e-06,
78
+ "min": 7.3316261275857155e-06,
79
+ "max": 0.00029515063018788575,
80
+ "count": 33
81
+ },
82
+ "Pyramids.Policy.LearningRate.sum": {
83
+ "value": 0.00010264276578620002,
84
+ "min": 0.00010264276578620002,
85
+ "max": 0.0033822440725854,
86
+ "count": 33
87
+ },
88
+ "Pyramids.Policy.Epsilon.mean": {
89
+ "value": 0.10244384285714285,
90
+ "min": 0.10244384285714285,
91
+ "max": 0.19838354285714285,
92
+ "count": 33
93
+ },
94
+ "Pyramids.Policy.Epsilon.sum": {
95
+ "value": 1.4342138,
96
+ "min": 1.3691136000000002,
97
+ "max": 2.5274146000000006,
98
+ "count": 33
99
+ },
100
+ "Pyramids.Policy.Beta.mean": {
101
+ "value": 0.0002541399014285715,
102
+ "min": 0.0002541399014285715,
103
+ "max": 0.00983851593142857,
104
+ "count": 33
105
+ },
106
+ "Pyramids.Policy.Beta.sum": {
107
+ "value": 0.003557958620000001,
108
+ "min": 0.003557958620000001,
109
+ "max": 0.11276871854000001,
110
+ "count": 33
111
+ },
112
+ "Pyramids.Losses.RNDLoss.mean": {
113
+ "value": 0.012034490704536438,
114
+ "min": 0.011664292775094509,
115
+ "max": 0.5429760217666626,
116
+ "count": 33
117
+ },
118
+ "Pyramids.Losses.RNDLoss.sum": {
119
+ "value": 0.16848286986351013,
120
+ "min": 0.16330009698867798,
121
+ "max": 3.8008322715759277,
122
+ "count": 33
123
+ },
124
+ "Pyramids.Environment.EpisodeLength.mean": {
125
+ "value": 370.1578947368421,
126
+ "min": 309.46067415730334,
127
+ "max": 999.0,
128
+ "count": 33
129
+ },
130
+ "Pyramids.Environment.EpisodeLength.sum": {
131
+ "value": 28132.0,
132
+ "min": 15984.0,
133
+ "max": 32954.0,
134
+ "count": 33
135
+ },
136
+ "Pyramids.Environment.CumulativeReward.mean": {
137
+ "value": 1.5245552441399348,
138
+ "min": -1.0000000521540642,
139
+ "max": 1.6873888729347124,
140
+ "count": 33
141
+ },
142
+ "Pyramids.Environment.CumulativeReward.sum": {
143
+ "value": 115.86619855463505,
144
+ "min": -32.000001668930054,
145
+ "max": 151.8649985641241,
146
+ "count": 33
147
+ },
148
+ "Pyramids.Policy.ExtrinsicReward.mean": {
149
+ "value": 1.5245552441399348,
150
+ "min": -1.0000000521540642,
151
+ "max": 1.6873888729347124,
152
+ "count": 33
153
+ },
154
+ "Pyramids.Policy.ExtrinsicReward.sum": {
155
+ "value": 115.86619855463505,
156
+ "min": -32.000001668930054,
157
+ "max": 151.8649985641241,
158
+ "count": 33
159
+ },
160
+ "Pyramids.Policy.RndReward.mean": {
161
+ "value": 0.046563367092235956,
162
+ "min": 0.03925282833774367,
163
+ "max": 11.243016171269119,
164
+ "count": 33
165
+ },
166
+ "Pyramids.Policy.RndReward.sum": {
167
+ "value": 3.5388158990099328,
168
+ "min": 3.5327545503969304,
169
+ "max": 179.8882587403059,
170
+ "count": 33
171
+ },
172
+ "Pyramids.IsTraining.mean": {
173
+ "value": 1.0,
174
+ "min": 1.0,
175
+ "max": 1.0,
176
+ "count": 33
177
+ },
178
+ "Pyramids.IsTraining.sum": {
179
+ "value": 1.0,
180
+ "min": 1.0,
181
+ "max": 1.0,
182
+ "count": 33
183
+ }
184
+ },
185
+ "metadata": {
186
+ "timer_format_version": "0.1.0",
187
+ "start_time_seconds": "1781485881",
188
+ "python_version": "3.10.12 (main, Mar 3 2026, 11:56:32) [GCC 11.4.0]",
189
+ "command_line_arguments": "/mnt/d/space/hf-rl/bonus-unit1/.venv-wsl/bin/mlagents-learn /mnt/d/space/hf-rl/bonus-unit1/vendor/ml-agents/config/ppo/PyramidsRND.yaml --env=/mnt/d/space/hf-rl/unit5/envs/linux/Pyramids/Pyramids --run-id=Pyramids1 --no-graphics --num-envs=1 --timeout-wait=180 --force",
190
+ "mlagents_version": "1.2.0.dev0",
191
+ "mlagents_envs_version": "1.2.0.dev0",
192
+ "communication_protocol_version": "1.5.0",
193
+ "pytorch_version": "2.7.1+cu126",
194
+ "numpy_version": "1.23.5",
195
+ "end_time_seconds": "1781489831"
196
+ },
197
+ "total": 3609.453242256,
198
+ "count": 1,
199
+ "self": 10.022552974999599,
200
+ "children": {
201
+ "run_training.setup": {
202
+ "total": 0.26663304800000276,
203
+ "count": 1,
204
+ "self": 0.26663304800000276
205
+ },
206
+ "TrainerController.start_learning": {
207
+ "total": 3599.1640562330003,
208
+ "count": 1,
209
+ "self": 1.4115560490313328,
210
+ "children": {
211
+ "TrainerController._reset_env": {
212
+ "total": 30.301432078999994,
213
+ "count": 1,
214
+ "self": 30.301432078999994
215
+ },
216
+ "TrainerController.advance": {
217
+ "total": 3567.051907325969,
218
+ "count": 63713,
219
+ "self": 1.4789411080660102,
220
+ "children": {
221
+ "env_step": {
222
+ "total": 2275.047270172955,
223
+ "count": 63713,
224
+ "self": 1937.007651836906,
225
+ "children": {
226
+ "SubprocessEnvManager._take_step": {
227
+ "total": 337.176277736035,
228
+ "count": 63713,
229
+ "self": 5.020477708085764,
230
+ "children": {
231
+ "TorchPolicy.evaluate": {
232
+ "total": 332.1558000279492,
233
+ "count": 62557,
234
+ "self": 332.1558000279492
235
+ }
236
+ }
237
+ },
238
+ "workers": {
239
+ "total": 0.8633406000139701,
240
+ "count": 63713,
241
+ "self": 0.0,
242
+ "children": {
243
+ "worker_root": {
244
+ "total": 3592.9451779260157,
245
+ "count": 63713,
246
+ "is_parallel": true,
247
+ "self": 1771.6236680289658,
248
+ "children": {
249
+ "run_training.setup": {
250
+ "total": 0.0,
251
+ "count": 0,
252
+ "is_parallel": true,
253
+ "self": 0.0,
254
+ "children": {
255
+ "steps_from_proto": {
256
+ "total": 0.009187221999994222,
257
+ "count": 1,
258
+ "is_parallel": true,
259
+ "self": 0.0034824009999852024,
260
+ "children": {
261
+ "_process_rank_one_or_two_observation": {
262
+ "total": 0.005704821000009019,
263
+ "count": 8,
264
+ "is_parallel": true,
265
+ "self": 0.005704821000009019
266
+ }
267
+ }
268
+ },
269
+ "UnityEnvironment.step": {
270
+ "total": 0.07209176899999648,
271
+ "count": 1,
272
+ "is_parallel": true,
273
+ "self": 0.0004161669999689366,
274
+ "children": {
275
+ "UnityEnvironment._generate_step_input": {
276
+ "total": 0.0006842040000094585,
277
+ "count": 1,
278
+ "is_parallel": true,
279
+ "self": 0.0006842040000094585
280
+ },
281
+ "communicator.exchange": {
282
+ "total": 0.06980034800000112,
283
+ "count": 1,
284
+ "is_parallel": true,
285
+ "self": 0.06980034800000112
286
+ },
287
+ "steps_from_proto": {
288
+ "total": 0.0011910500000169577,
289
+ "count": 1,
290
+ "is_parallel": true,
291
+ "self": 0.0002942700000119203,
292
+ "children": {
293
+ "_process_rank_one_or_two_observation": {
294
+ "total": 0.0008967800000050374,
295
+ "count": 8,
296
+ "is_parallel": true,
297
+ "self": 0.0008967800000050374
298
+ }
299
+ }
300
+ }
301
+ }
302
+ }
303
+ }
304
+ },
305
+ "UnityEnvironment.step": {
306
+ "total": 1821.32150989705,
307
+ "count": 63712,
308
+ "is_parallel": true,
309
+ "self": 28.41476359915214,
310
+ "children": {
311
+ "UnityEnvironment._generate_step_input": {
312
+ "total": 19.253633228977293,
313
+ "count": 63712,
314
+ "is_parallel": true,
315
+ "self": 19.253633228977293
316
+ },
317
+ "communicator.exchange": {
318
+ "total": 1685.6341891638988,
319
+ "count": 63712,
320
+ "is_parallel": true,
321
+ "self": 1685.6341891638988
322
+ },
323
+ "steps_from_proto": {
324
+ "total": 88.01892390502167,
325
+ "count": 63712,
326
+ "is_parallel": true,
327
+ "self": 20.555391886965822,
328
+ "children": {
329
+ "_process_rank_one_or_two_observation": {
330
+ "total": 67.46353201805584,
331
+ "count": 509696,
332
+ "is_parallel": true,
333
+ "self": 67.46353201805584
334
+ }
335
+ }
336
+ }
337
+ }
338
+ }
339
+ }
340
+ }
341
+ }
342
+ }
343
+ }
344
+ },
345
+ "trainer_advance": {
346
+ "total": 1290.5256960449478,
347
+ "count": 63713,
348
+ "self": 2.2441690699620267,
349
+ "children": {
350
+ "process_trajectory": {
351
+ "total": 191.43753943798595,
352
+ "count": 63713,
353
+ "self": 189.23052914998584,
354
+ "children": {
355
+ "RLTrainer._checkpoint": {
356
+ "total": 2.207010288000106,
357
+ "count": 5,
358
+ "self": 2.207010288000106
359
+ }
360
+ }
361
+ },
362
+ "_update_policy": {
363
+ "total": 1096.8439875369997,
364
+ "count": 447,
365
+ "self": 409.2008528670044,
366
+ "children": {
367
+ "TorchPPOOptimizer.update": {
368
+ "total": 687.6431346699953,
369
+ "count": 22842,
370
+ "self": 687.6431346699953
371
+ }
372
+ }
373
+ }
374
+ }
375
+ }
376
+ }
377
+ },
378
+ "trainer_threads": {
379
+ "total": 8.000001798791345e-07,
380
+ "count": 1,
381
+ "self": 8.000001798791345e-07
382
+ },
383
+ "TrainerController._save_models": {
384
+ "total": 0.3991599790001601,
385
+ "count": 1,
386
+ "self": 0.04514143900041745,
387
+ "children": {
388
+ "RLTrainer._checkpoint": {
389
+ "total": 0.35401853999974264,
390
+ "count": 1,
391
+ "self": 0.35401853999974264
392
+ }
393
+ }
394
+ }
395
+ }
396
+ }
397
+ }
398
+ }
run_logs/training_status.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "Pyramids": {
3
+ "checkpoints": [
4
+ {
5
+ "steps": 399936,
6
+ "file_path": "results/Pyramids1/Pyramids/Pyramids-399936.onnx",
7
+ "reward": null,
8
+ "creation_time": 1781487454.5311334,
9
+ "auxillary_file_paths": [
10
+ "results/Pyramids1/Pyramids/Pyramids-399936.pt"
11
+ ]
12
+ },
13
+ {
14
+ "steps": 599997,
15
+ "file_path": "results/Pyramids1/Pyramids/Pyramids-599997.onnx",
16
+ "reward": 1.4227499663829803,
17
+ "creation_time": 1781488243.445235,
18
+ "auxillary_file_paths": [
19
+ "results/Pyramids1/Pyramids/Pyramids-599997.pt"
20
+ ]
21
+ },
22
+ {
23
+ "steps": 799948,
24
+ "file_path": "results/Pyramids1/Pyramids/Pyramids-799948.onnx",
25
+ "reward": null,
26
+ "creation_time": 1781489034.1746535,
27
+ "auxillary_file_paths": [
28
+ "results/Pyramids1/Pyramids/Pyramids-799948.pt"
29
+ ]
30
+ },
31
+ {
32
+ "steps": 999889,
33
+ "file_path": "results/Pyramids1/Pyramids/Pyramids-999889.onnx",
34
+ "reward": 1.4239999651908875,
35
+ "creation_time": 1781489821.3621013,
36
+ "auxillary_file_paths": [
37
+ "results/Pyramids1/Pyramids/Pyramids-999889.pt"
38
+ ]
39
+ },
40
+ {
41
+ "steps": 1000017,
42
+ "file_path": "results/Pyramids1/Pyramids/Pyramids-1000017.onnx",
43
+ "reward": 1.4239999651908875,
44
+ "creation_time": 1781489821.7283435,
45
+ "auxillary_file_paths": [
46
+ "results/Pyramids1/Pyramids/Pyramids-1000017.pt"
47
+ ]
48
+ }
49
+ ],
50
+ "final_checkpoint": {
51
+ "steps": 1000017,
52
+ "file_path": "results/Pyramids1/Pyramids.onnx",
53
+ "reward": 1.4239999651908875,
54
+ "creation_time": 1781489821.7283435,
55
+ "auxillary_file_paths": [
56
+ "results/Pyramids1/Pyramids/Pyramids-1000017.pt"
57
+ ]
58
+ }
59
+ },
60
+ "metadata": {
61
+ "stats_format_version": "0.3.0",
62
+ "mlagents_version": "1.2.0.dev0",
63
+ "torch_version": "2.7.1+cu126"
64
+ }
65
+ }