Reinforcement Learning
ml-agents
TensorBoard
ONNX
Pyramids
deep-reinforcement-learning
ML-Agents-Pyramids
Instructions to use MafeLeon9/ppo-Pyramids with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ml-agents
How to use MafeLeon9/ppo-Pyramids with ml-agents:
mlagents-load-from-hf --repo-id="MafeLeon9/ppo-Pyramids" --local-dir="./download: string[]s"
- Notebooks
- Google Colab
- Kaggle
| { | |
| "name": "root", | |
| "gauges": { | |
| "Pyramids.Policy.Entropy.mean": { | |
| "value": 0.6916899681091309, | |
| "min": 0.6896134614944458, | |
| "max": 1.404939889907837, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Entropy.sum": { | |
| "value": 20651.095703125, | |
| "min": 20645.70703125, | |
| "max": 42620.2578125, | |
| "count": 33 | |
| }, | |
| "Pyramids.Step.mean": { | |
| "value": 989969.0, | |
| "min": 29952.0, | |
| "max": 989969.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Step.sum": { | |
| "value": 989969.0, | |
| "min": 29952.0, | |
| "max": 989969.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": 0.31611189246177673, | |
| "min": -0.10733319073915482, | |
| "max": 0.37801045179367065, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": 82.50520324707031, | |
| "min": -25.867298126220703, | |
| "max": 99.416748046875, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.mean": { | |
| "value": 0.3483024835586548, | |
| "min": -0.09128698706626892, | |
| "max": 0.3483024835586548, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.sum": { | |
| "value": 90.90695190429688, | |
| "min": -23.825902938842773, | |
| "max": 90.90695190429688, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.mean": { | |
| "value": 0.06843751064679097, | |
| "min": 0.06354434896734082, | |
| "max": 0.07154199718080013, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.sum": { | |
| "value": 0.9581251490550737, | |
| "min": 0.496360123701609, | |
| "max": 1.0469425394024026, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.ValueLoss.mean": { | |
| "value": 0.035062337706525185, | |
| "min": 0.00012994433957645536, | |
| "max": 0.035062337706525185, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.ValueLoss.sum": { | |
| "value": 0.4908727278913526, | |
| "min": 0.001429387735341009, | |
| "max": 0.4908727278913526, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.LearningRate.mean": { | |
| "value": 7.504404641421429e-06, | |
| "min": 7.504404641421429e-06, | |
| "max": 0.00029515063018788575, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.LearningRate.sum": { | |
| "value": 0.0001050616649799, | |
| "min": 0.0001050616649799, | |
| "max": 0.0035068715310428993, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Epsilon.mean": { | |
| "value": 0.10250143571428572, | |
| "min": 0.10250143571428572, | |
| "max": 0.19838354285714285, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Epsilon.sum": { | |
| "value": 1.4350201, | |
| "min": 1.3691136000000002, | |
| "max": 2.5689571, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Beta.mean": { | |
| "value": 0.00025989342785714286, | |
| "min": 0.00025989342785714286, | |
| "max": 0.00983851593142857, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Beta.sum": { | |
| "value": 0.0036385079900000004, | |
| "min": 0.0036385079900000004, | |
| "max": 0.11691881428999998, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.RNDLoss.mean": { | |
| "value": 0.006524231750518084, | |
| "min": 0.006524231750518084, | |
| "max": 0.37675079703330994, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.RNDLoss.sum": { | |
| "value": 0.09133924543857574, | |
| "min": 0.09133924543857574, | |
| "max": 2.6372556686401367, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.mean": { | |
| "value": 538.5, | |
| "min": 441.1764705882353, | |
| "max": 999.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.sum": { | |
| "value": 31233.0, | |
| "min": 15984.0, | |
| "max": 33166.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.mean": { | |
| "value": 1.1855620459235947, | |
| "min": -1.0000000521540642, | |
| "max": 1.4411293864250183, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.sum": { | |
| "value": 68.7625986635685, | |
| "min": -32.000001668930054, | |
| "max": 97.99679827690125, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.mean": { | |
| "value": 1.1855620459235947, | |
| "min": -1.0000000521540642, | |
| "max": 1.4411293864250183, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.sum": { | |
| "value": 68.7625986635685, | |
| "min": -32.000001668930054, | |
| "max": 97.99679827690125, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndReward.mean": { | |
| "value": 0.036870385544246126, | |
| "min": 0.034126756638322736, | |
| "max": 7.385277417488396, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndReward.sum": { | |
| "value": 2.1384823615662754, | |
| "min": 2.1384823615662754, | |
| "max": 118.16443867981434, | |
| "count": 33 | |
| }, | |
| "Pyramids.IsTraining.mean": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.IsTraining.sum": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 33 | |
| } | |
| }, | |
| "metadata": { | |
| "timer_format_version": "0.1.0", | |
| "start_time_seconds": "1779569996", | |
| "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/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": "1779572312" | |
| }, | |
| "total": 2315.68318777, | |
| "count": 1, | |
| "self": 0.47869547400023293, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.025474621999819647, | |
| "count": 1, | |
| "self": 0.025474621999819647 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 2315.179017674, | |
| "count": 1, | |
| "self": 1.3191176609834656, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 2.1344262929997058, | |
| "count": 1, | |
| "self": 2.1344262929997058 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 2311.6334760770173, | |
| "count": 63389, | |
| "self": 1.36978233699665, | |
| "children": { | |
| "env_step": { | |
| "total": 1651.4449260729607, | |
| "count": 63389, | |
| "self": 1498.9938342809642, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 151.6651077259512, | |
| "count": 63389, | |
| "self": 4.689672805921418, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 146.97543492002978, | |
| "count": 62555, | |
| "self": 146.97543492002978 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 0.7859840660453301, | |
| "count": 63389, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 2309.1481035489646, | |
| "count": 63389, | |
| "is_parallel": true, | |
| "self": 927.4330123310774, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0, | |
| "count": 0, | |
| "is_parallel": true, | |
| "self": 0.0, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.0018030420001196035, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0006154849997983547, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0011875570003212488, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0011875570003212488 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 0.04957516000013129, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0005180429993743019, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 0.00047247200018318836, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.00047247200018318836 | |
| }, | |
| "communicator.exchange": { | |
| "total": 0.04695112700028403, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.04695112700028403 | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.0016335180002897687, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0003383029998076381, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0012952150004821306, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0012952150004821306 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 1381.7150912178872, | |
| "count": 63388, | |
| "is_parallel": true, | |
| "self": 33.977917631835226, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 23.496554147999632, | |
| "count": 63388, | |
| "is_parallel": true, | |
| "self": 23.496554147999632 | |
| }, | |
| "communicator.exchange": { | |
| "total": 1213.901346200062, | |
| "count": 63388, | |
| "is_parallel": true, | |
| "self": 1213.901346200062 | |
| }, | |
| "steps_from_proto": { | |
| "total": 110.33927323799026, | |
| "count": 63388, | |
| "is_parallel": true, | |
| "self": 23.034061066912273, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 87.30521217107798, | |
| "count": 507104, | |
| "is_parallel": true, | |
| "self": 87.30521217107798 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 658.81876766706, | |
| "count": 63389, | |
| "self": 2.5081541831946197, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 125.63649684586653, | |
| "count": 63389, | |
| "self": 125.44765676086581, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.18884008500072014, | |
| "count": 2, | |
| "self": 0.18884008500072014 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 530.6741166379988, | |
| "count": 446, | |
| "self": 293.93877528097664, | |
| "children": { | |
| "TorchPPOOptimizer.update": { | |
| "total": 236.7353413570222, | |
| "count": 22842, | |
| "self": 236.7353413570222 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 8.869992598192766e-07, | |
| "count": 1, | |
| "self": 8.869992598192766e-07 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.09199675600029877, | |
| "count": 1, | |
| "self": 0.00116375000015978, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.090833006000139, | |
| "count": 1, | |
| "self": 0.090833006000139 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |