Reinforcement Learning
ml-agents
TensorBoard
ONNX
Pyramids
deep-reinforcement-learning
ML-Agents-Pyramids
Instructions to use qisunhui/ppo-Pyramids with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ml-agents
How to use qisunhui/ppo-Pyramids with ml-agents:
mlagents-load-from-hf --repo-id="qisunhui/ppo-Pyramids" --local-dir="./downloads"
- Notebooks
- Google Colab
- Kaggle
Download run_logs/timers.json from qisunhui/ppo-Pyramids: direct link, hf CLI and curl.
- Browser
- Download file 18.8 kB
-
https://huggingface.co/qisunhui/ppo-Pyramids/resolve/main/run_logs/timers.json
- Command line
-
hf download hf://qisunhui/ppo-Pyramids/run_logs/timers.json
-
curl -L -o timers.json https://huggingface.co/qisunhui/ppo-Pyramids/resolve/main/run_logs/timers.json
18.8 kB
| { | |
| "name": "root", | |
| "gauges": { | |
| "Pyramids.Policy.Entropy.mean": { | |
| "value": 0.18374475836753845, | |
| "min": 0.17183971405029297, | |
| "max": 1.4280521869659424, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.Entropy.sum": { | |
| "value": 5559.38134765625, | |
| "min": 5130.4462890625, | |
| "max": 43321.390625, | |
| "count": 100 | |
| }, | |
| "Pyramids.Step.mean": { | |
| "value": 2999877.0, | |
| "min": 29945.0, | |
| "max": 2999877.0, | |
| "count": 100 | |
| }, | |
| "Pyramids.Step.sum": { | |
| "value": 2999877.0, | |
| "min": 29945.0, | |
| "max": 2999877.0, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": 0.7599660158157349, | |
| "min": -0.10714023560285568, | |
| "max": 0.7685180306434631, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": 225.70989990234375, | |
| "min": -25.71365737915039, | |
| "max": 229.78689575195312, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.mean": { | |
| "value": 0.006078632548451424, | |
| "min": -0.020444566383957863, | |
| "max": 0.2987949252128601, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.sum": { | |
| "value": 1.8053538799285889, | |
| "min": -5.6427001953125, | |
| "max": 71.11318969726562, | |
| "count": 100 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.mean": { | |
| "value": 0.07113803252965832, | |
| "min": 0.06449606490440644, | |
| "max": 0.07427641625246438, | |
| "count": 100 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.sum": { | |
| "value": 1.067070487944875, | |
| "min": 0.4876896097955706, | |
| "max": 1.0757345844758675, | |
| "count": 100 | |
| }, | |
| "Pyramids.Losses.ValueLoss.mean": { | |
| "value": 0.016347435175622295, | |
| "min": 0.00043755506995136903, | |
| "max": 0.018192860467284584, | |
| "count": 100 | |
| }, | |
| "Pyramids.Losses.ValueLoss.sum": { | |
| "value": 0.2452115276343344, | |
| "min": 0.005688215909367797, | |
| "max": 0.2547000465419842, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.LearningRate.mean": { | |
| "value": 1.513806162097777e-06, | |
| "min": 1.513806162097777e-06, | |
| "max": 0.00029838354339596195, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.LearningRate.sum": { | |
| "value": 2.2707092431466653e-05, | |
| "min": 2.2707092431466653e-05, | |
| "max": 0.004027532157489333, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.Epsilon.mean": { | |
| "value": 0.10050456888888888, | |
| "min": 0.10050456888888888, | |
| "max": 0.19946118095238097, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.Epsilon.sum": { | |
| "value": 1.5075685333333333, | |
| "min": 1.3962282666666668, | |
| "max": 2.8425106666666675, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.Beta.mean": { | |
| "value": 6.0406431999999965e-05, | |
| "min": 6.0406431999999965e-05, | |
| "max": 0.009946171977142856, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.Beta.sum": { | |
| "value": 0.0009060964799999995, | |
| "min": 0.0009060964799999995, | |
| "max": 0.1342668156, | |
| "count": 100 | |
| }, | |
| "Pyramids.Losses.RNDLoss.mean": { | |
| "value": 0.004124905448406935, | |
| "min": 0.0037137633189558983, | |
| "max": 0.4133046269416809, | |
| "count": 100 | |
| }, | |
| "Pyramids.Losses.RNDLoss.sum": { | |
| "value": 0.06187358498573303, | |
| "min": 0.052209965884685516, | |
| "max": 2.893132448196411, | |
| "count": 100 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.mean": { | |
| "value": 250.91869918699186, | |
| "min": 231.34453781512605, | |
| "max": 999.0, | |
| "count": 100 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.sum": { | |
| "value": 30863.0, | |
| "min": 17639.0, | |
| "max": 33348.0, | |
| "count": 100 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.mean": { | |
| "value": 1.7328146164252507, | |
| "min": -0.9999000519514084, | |
| "max": 1.7686554443936389, | |
| "count": 100 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.sum": { | |
| "value": 213.13619782030582, | |
| "min": -29.99700155854225, | |
| "max": 215.3763976469636, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.mean": { | |
| "value": 1.7328146164252507, | |
| "min": -0.9999000519514084, | |
| "max": 1.7686554443936389, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.sum": { | |
| "value": 213.13619782030582, | |
| "min": -29.99700155854225, | |
| "max": 215.3763976469636, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.RndReward.mean": { | |
| "value": 0.010948674463038995, | |
| "min": 0.009630730946473934, | |
| "max": 7.6778076692587796, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.RndReward.sum": { | |
| "value": 1.3466869589537964, | |
| "min": 1.055497848548839, | |
| "max": 138.20053804665804, | |
| "count": 100 | |
| }, | |
| "Pyramids.IsTraining.mean": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 100 | |
| }, | |
| "Pyramids.IsTraining.sum": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 100 | |
| } | |
| }, | |
| "metadata": { | |
| "timer_format_version": "0.1.0", | |
| "start_time_seconds": "1793605317", | |
| "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", | |
| "command_line_arguments": "/usr/local/envs/mlagents/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --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": "1793611823" | |
| }, | |
| "total": 6505.90495412, | |
| "count": 1, | |
| "self": 0.4799104499998066, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.019432605000019976, | |
| "count": 1, | |
| "self": 0.019432605000019976 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 6505.405611065, | |
| "count": 1, | |
| "self": 3.9405569082118745, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 2.239629534999949, | |
| "count": 1, | |
| "self": 2.239629534999949 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 6499.143322590787, | |
| "count": 193716, | |
| "self": 4.078284601592713, | |
| "children": { | |
| "env_step": { | |
| "total": 4672.065325293928, | |
| "count": 193716, | |
| "self": 4234.743513359564, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 434.9467947943331, | |
| "count": 193716, | |
| "self": 13.33751270807079, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 421.6092820862623, | |
| "count": 187563, | |
| "self": 421.6092820862623 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 2.3750171400315594, | |
| "count": 193716, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 6495.240261095854, | |
| "count": 193716, | |
| "is_parallel": true, | |
| "self": 2573.5316859321624, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0, | |
| "count": 0, | |
| "is_parallel": true, | |
| "self": 0.0, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.001815997999983665, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0005856440002389718, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0012303539997446933, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0012303539997446933 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 0.05151961999990817, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0005868619996363122, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 0.0004982770001333847, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0004982770001333847 | |
| }, | |
| "communicator.exchange": { | |
| "total": 0.04869294499985699, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.04869294499985699 | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.001741536000281485, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.00036984199959988473, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0013716940006816003, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0013716940006816003 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 3921.708575163692, | |
| "count": 193715, | |
| "is_parallel": true, | |
| "self": 95.19337373293683, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 66.57719882007041, | |
| "count": 193715, | |
| "is_parallel": true, | |
| "self": 66.57719882007041 | |
| }, | |
| "communicator.exchange": { | |
| "total": 3464.9220287217468, | |
| "count": 193715, | |
| "is_parallel": true, | |
| "self": 3464.9220287217468 | |
| }, | |
| "steps_from_proto": { | |
| "total": 295.0159738889379, | |
| "count": 193715, | |
| "is_parallel": true, | |
| "self": 61.11826279652223, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 233.89771109241565, | |
| "count": 1549720, | |
| "is_parallel": true, | |
| "self": 233.89771109241565 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 1822.9997126952662, | |
| "count": 193716, | |
| "self": 7.84343938541997, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 325.7166797988252, | |
| "count": 193716, | |
| "self": 325.1929505948274, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.5237292039978456, | |
| "count": 6, | |
| "self": 0.5237292039978456 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 1489.439593511021, | |
| "count": 1407, | |
| "self": 800.9731534519715, | |
| "children": { | |
| "TorchPPOOptimizer.update": { | |
| "total": 688.4664400590495, | |
| "count": 68418, | |
| "self": 688.4664400590495 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 8.790011634118855e-07, | |
| "count": 1, | |
| "self": 8.790011634118855e-07 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.08210115200017754, | |
| "count": 1, | |
| "self": 0.00133034700047574, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.0807708049997018, | |
| "count": 1, | |
| "self": 0.0807708049997018 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |