Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Instructions to use alan1009/ppo-SnowballTarget with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ml-agents
How to use alan1009/ppo-SnowballTarget with ml-agents:
mlagents-load-from-hf --repo-id="alan1009/ppo-SnowballTarget" --local-dir="./downloads"
- Notebooks
- Google Colab
- Kaggle
Download run_logs/timers.json from alan1009/ppo-SnowballTarget: direct link, hf CLI and curl.
- Browser
- Download file 17.6 kB
-
https://huggingface.co/alan1009/ppo-SnowballTarget/resolve/main/run_logs/timers.json
- Command line
-
hf download hf://alan1009/ppo-SnowballTarget/run_logs/timers.json
-
curl -L -o timers.json https://huggingface.co/alan1009/ppo-SnowballTarget/resolve/main/run_logs/timers.json
17.6 kB
| { | |
| "name": "root", | |
| "gauges": { | |
| "SnowballTarget.Policy.Entropy.mean": { | |
| "value": 0.8763613700866699, | |
| "min": 0.8653143048286438, | |
| "max": 2.8560047149658203, | |
| "count": 20 | |
| }, | |
| "SnowballTarget.Policy.Entropy.sum": { | |
| "value": 8328.9384765625, | |
| "min": 8328.9384765625, | |
| "max": 29154.095703125, | |
| "count": 20 | |
| }, | |
| "SnowballTarget.Step.mean": { | |
| "value": 199984.0, | |
| "min": 9952.0, | |
| "max": 199984.0, | |
| "count": 20 | |
| }, | |
| "SnowballTarget.Step.sum": { | |
| "value": 199984.0, | |
| "min": 9952.0, | |
| "max": 199984.0, | |
| "count": 20 | |
| }, | |
| "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": 13.17044734954834, | |
| "min": 0.39326608180999756, | |
| "max": 13.17044734954834, | |
| "count": 20 | |
| }, | |
| "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": 2568.2373046875, | |
| "min": 76.29361724853516, | |
| "max": 2678.818359375, | |
| "count": 20 | |
| }, | |
| "SnowballTarget.Losses.PolicyLoss.mean": { | |
| "value": 0.07472464077599236, | |
| "min": 0.0640327573587438, | |
| "max": 0.07687365257102191, | |
| "count": 20 | |
| }, | |
| "SnowballTarget.Losses.PolicyLoss.sum": { | |
| "value": 0.29889856310396945, | |
| "min": 0.265216122004466, | |
| "max": 0.3757726814861492, | |
| "count": 20 | |
| }, | |
| "SnowballTarget.Losses.ValueLoss.mean": { | |
| "value": 0.1983431511942078, | |
| "min": 0.13683716360223935, | |
| "max": 0.2843097903418775, | |
| "count": 20 | |
| }, | |
| "SnowballTarget.Losses.ValueLoss.sum": { | |
| "value": 0.7933726047768312, | |
| "min": 0.5473486544089574, | |
| "max": 1.346312566130769, | |
| "count": 20 | |
| }, | |
| "SnowballTarget.Policy.LearningRate.mean": { | |
| "value": 8.082097306000005e-06, | |
| "min": 8.082097306000005e-06, | |
| "max": 0.000291882002706, | |
| "count": 20 | |
| }, | |
| "SnowballTarget.Policy.LearningRate.sum": { | |
| "value": 3.232838922400002e-05, | |
| "min": 3.232838922400002e-05, | |
| "max": 0.00138516003828, | |
| "count": 20 | |
| }, | |
| "SnowballTarget.Policy.Epsilon.mean": { | |
| "value": 0.10269400000000001, | |
| "min": 0.10269400000000001, | |
| "max": 0.19729400000000002, | |
| "count": 20 | |
| }, | |
| "SnowballTarget.Policy.Epsilon.sum": { | |
| "value": 0.41077600000000003, | |
| "min": 0.41077600000000003, | |
| "max": 0.96172, | |
| "count": 20 | |
| }, | |
| "SnowballTarget.Policy.Beta.mean": { | |
| "value": 0.0001444306000000001, | |
| "min": 0.0001444306000000001, | |
| "max": 0.0048649706, | |
| "count": 20 | |
| }, | |
| "SnowballTarget.Policy.Beta.sum": { | |
| "value": 0.0005777224000000004, | |
| "min": 0.0005777224000000004, | |
| "max": 0.023089828, | |
| "count": 20 | |
| }, | |
| "SnowballTarget.Environment.EpisodeLength.mean": { | |
| "value": 199.0, | |
| "min": 199.0, | |
| "max": 199.0, | |
| "count": 20 | |
| }, | |
| "SnowballTarget.Environment.EpisodeLength.sum": { | |
| "value": 8756.0, | |
| "min": 8756.0, | |
| "max": 10945.0, | |
| "count": 20 | |
| }, | |
| "SnowballTarget.Environment.CumulativeReward.mean": { | |
| "value": 25.772727272727273, | |
| "min": 3.6363636363636362, | |
| "max": 26.163636363636364, | |
| "count": 20 | |
| }, | |
| "SnowballTarget.Environment.CumulativeReward.sum": { | |
| "value": 1134.0, | |
| "min": 160.0, | |
| "max": 1439.0, | |
| "count": 20 | |
| }, | |
| "SnowballTarget.Policy.ExtrinsicReward.mean": { | |
| "value": 25.772727272727273, | |
| "min": 3.6363636363636362, | |
| "max": 26.163636363636364, | |
| "count": 20 | |
| }, | |
| "SnowballTarget.Policy.ExtrinsicReward.sum": { | |
| "value": 1134.0, | |
| "min": 160.0, | |
| "max": 1439.0, | |
| "count": 20 | |
| }, | |
| "SnowballTarget.IsTraining.mean": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 20 | |
| }, | |
| "SnowballTarget.IsTraining.sum": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 20 | |
| } | |
| }, | |
| "metadata": { | |
| "timer_format_version": "0.1.0", | |
| "start_time_seconds": "1793010956", | |
| "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", | |
| "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", | |
| "mlagents_version": "1.2.0.dev0", | |
| "mlagents_envs_version": "1.2.0.dev0", | |
| "communication_protocol_version": "1.5.0", | |
| "pytorch_version": "2.8.0+cu128", | |
| "numpy_version": "1.23.5", | |
| "end_time_seconds": "1793011108" | |
| }, | |
| "total": 151.57435959300005, | |
| "count": 1, | |
| "self": 0.16666539100003774, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.010721636999960538, | |
| "count": 1, | |
| "self": 0.010721636999960538 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 151.39697256500006, | |
| "count": 1, | |
| "self": 0.13991932902285953, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 1.073680362999994, | |
| "count": 1, | |
| "self": 1.073680362999994 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 150.1558987589773, | |
| "count": 18192, | |
| "self": 0.1339520469772424, | |
| "children": { | |
| "env_step": { | |
| "total": 106.83127794899872, | |
| "count": 18192, | |
| "self": 84.19677061399557, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 22.54165505500339, | |
| "count": 18192, | |
| "self": 0.5012301860041362, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 22.040424868999253, | |
| "count": 18192, | |
| "self": 22.040424868999253 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 0.09285227999976087, | |
| "count": 18192, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 151.0682693469863, | |
| "count": 18192, | |
| "is_parallel": true, | |
| "self": 76.00899289699794, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0, | |
| "count": 0, | |
| "is_parallel": true, | |
| "self": 0.0, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.0007365300000401476, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.00019731000031697477, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0005392199997231728, | |
| "count": 10, | |
| "is_parallel": true, | |
| "self": 0.0005392199997231728 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 0.014948945000014646, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0001550999999153646, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 0.0001636690000168528, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0001636690000168528 | |
| }, | |
| "communicator.exchange": { | |
| "total": 0.013228587000071457, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.013228587000071457 | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.001401589000010972, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.00012173999982678652, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0012798490001841856, | |
| "count": 10, | |
| "is_parallel": true, | |
| "self": 0.0012798490001841856 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 75.05927644998837, | |
| "count": 18191, | |
| "is_parallel": true, | |
| "self": 2.2827324939866003, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 1.1279647499856083, | |
| "count": 18191, | |
| "is_parallel": true, | |
| "self": 1.1279647499856083 | |
| }, | |
| "communicator.exchange": { | |
| "total": 65.09833116401023, | |
| "count": 18191, | |
| "is_parallel": true, | |
| "self": 65.09833116401023 | |
| }, | |
| "steps_from_proto": { | |
| "total": 6.550248042005933, | |
| "count": 18191, | |
| "is_parallel": true, | |
| "self": 1.1870320420232474, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 5.363215999982685, | |
| "count": 181910, | |
| "is_parallel": true, | |
| "self": 5.363215999982685 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 43.19066876300133, | |
| "count": 18192, | |
| "self": 0.1575712899999644, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 9.518529729001898, | |
| "count": 18192, | |
| "self": 9.38935658100172, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.1291731480001772, | |
| "count": 4, | |
| "self": 0.1291731480001772 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 33.514567743999464, | |
| "count": 90, | |
| "self": 15.276627411003005, | |
| "children": { | |
| "TorchPPOOptimizer.update": { | |
| "total": 18.23794033299646, | |
| "count": 4587, | |
| "self": 18.23794033299646 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 6.299999313341687e-07, | |
| "count": 1, | |
| "self": 6.299999313341687e-07 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.027473483999983728, | |
| "count": 1, | |
| "self": 0.0003039499999886175, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.02716953399999511, | |
| "count": 1, | |
| "self": 0.02716953399999511 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |