Reinforcement Learning
ml-agents
TensorBoard
ONNX
Pyramids
deep-reinforcement-learning
ML-Agents-Pyramids
Instructions to use dnarqq/ppo-Pyramids with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ml-agents
How to use dnarqq/ppo-Pyramids with ml-agents:
mlagents-load-from-hf --repo-id="dnarqq/ppo-Pyramids" --local-dir="./download: string[]s"
- Notebooks
- Google Colab
- Kaggle
| { | |
| "name": "root", | |
| "gauges": { | |
| "Pyramids.Policy.Entropy.mean": { | |
| "value": 0.322129487991333, | |
| "min": 0.322129487991333, | |
| "max": 1.507158637046814, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Entropy.sum": { | |
| "value": 9699.962890625, | |
| "min": 9699.962890625, | |
| "max": 45721.1640625, | |
| "count": 33 | |
| }, | |
| "Pyramids.Step.mean": { | |
| "value": 989910.0, | |
| "min": 29952.0, | |
| "max": 989910.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Step.sum": { | |
| "value": 989910.0, | |
| "min": 29952.0, | |
| "max": 989910.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": 0.6654283404350281, | |
| "min": -0.12162134051322937, | |
| "max": 0.6654283404350281, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": 192.3087921142578, | |
| "min": -28.824256896972656, | |
| "max": 192.3087921142578, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.mean": { | |
| "value": 0.008051485754549503, | |
| "min": 0.005244612693786621, | |
| "max": 0.1955219805240631, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.sum": { | |
| "value": 2.3268795013427734, | |
| "min": 1.4999592304229736, | |
| "max": 47.12079620361328, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.mean": { | |
| "value": 0.0718197513896961, | |
| "min": 0.06462203201607779, | |
| "max": 0.07502773609857762, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.sum": { | |
| "value": 1.0054765194557453, | |
| "min": 0.4972768485684607, | |
| "max": 1.0852015428288184, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.ValueLoss.mean": { | |
| "value": 0.016475532296441723, | |
| "min": 0.0006775765604752274, | |
| "max": 0.017533378427158044, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.ValueLoss.sum": { | |
| "value": 0.2306574521501841, | |
| "min": 0.008808495286177956, | |
| "max": 0.2454672979802126, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.LearningRate.mean": { | |
| "value": 7.705340288728571e-06, | |
| "min": 7.705340288728571e-06, | |
| "max": 0.00029515063018788575, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.LearningRate.sum": { | |
| "value": 0.0001078747640422, | |
| "min": 0.0001078747640422, | |
| "max": 0.003508107530630899, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Epsilon.mean": { | |
| "value": 0.10256841428571431, | |
| "min": 0.10256841428571431, | |
| "max": 0.19838354285714285, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Epsilon.sum": { | |
| "value": 1.4359578000000004, | |
| "min": 1.3886848, | |
| "max": 2.5693691000000003, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Beta.mean": { | |
| "value": 0.0002665845871428571, | |
| "min": 0.0002665845871428571, | |
| "max": 0.00983851593142857, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Beta.sum": { | |
| "value": 0.00373218422, | |
| "min": 0.00373218422, | |
| "max": 0.11695997308999999, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.RNDLoss.mean": { | |
| "value": 0.010828888975083828, | |
| "min": 0.010828888975083828, | |
| "max": 0.3384212553501129, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.RNDLoss.sum": { | |
| "value": 0.15160444378852844, | |
| "min": 0.15160444378852844, | |
| "max": 2.3689486980438232, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.mean": { | |
| "value": 279.02777777777777, | |
| "min": 279.02777777777777, | |
| "max": 999.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.sum": { | |
| "value": 30135.0, | |
| "min": 15984.0, | |
| "max": 32784.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.mean": { | |
| "value": 1.6642605365689742, | |
| "min": -1.0000000521540642, | |
| "max": 1.7106237502971497, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.sum": { | |
| "value": 181.40439848601818, | |
| "min": -30.306201703846455, | |
| "max": 181.40439848601818, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.mean": { | |
| "value": 1.6642605365689742, | |
| "min": -1.0000000521540642, | |
| "max": 1.7106237502971497, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.sum": { | |
| "value": 181.40439848601818, | |
| "min": -30.306201703846455, | |
| "max": 181.40439848601818, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndReward.mean": { | |
| "value": 0.031287780978370865, | |
| "min": 0.031287780978370865, | |
| "max": 7.178404874168336, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndReward.sum": { | |
| "value": 3.4103681266424246, | |
| "min": 3.1845385901688132, | |
| "max": 114.85447798669338, | |
| "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": "1690104651", | |
| "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", | |
| "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": "0.31.0.dev0", | |
| "mlagents_envs_version": "0.31.0.dev0", | |
| "communication_protocol_version": "1.5.0", | |
| "pytorch_version": "1.11.0+cu102", | |
| "numpy_version": "1.21.2", | |
| "end_time_seconds": "1690106978" | |
| }, | |
| "total": 2327.142123697, | |
| "count": 1, | |
| "self": 0.47579881900037435, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.03231194399995729, | |
| "count": 1, | |
| "self": 0.03231194399995729 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 2326.6340129339997, | |
| "count": 1, | |
| "self": 1.3428490581013648, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 5.556313808999903, | |
| "count": 1, | |
| "self": 5.556313808999903 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 2319.640301463898, | |
| "count": 64042, | |
| "self": 1.4302620418216065, | |
| "children": { | |
| "env_step": { | |
| "total": 1659.5688652709694, | |
| "count": 64042, | |
| "self": 1553.0644509681001, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 105.6922641699698, | |
| "count": 64042, | |
| "self": 4.721253984011128, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 100.97101018595868, | |
| "count": 62561, | |
| "self": 100.97101018595868 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 0.8121501328994327, | |
| "count": 64042, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 2321.503562342989, | |
| "count": 64042, | |
| "is_parallel": true, | |
| "self": 881.4217742140106, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0, | |
| "count": 0, | |
| "is_parallel": true, | |
| "self": 0.0, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.002452171999948405, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0006822289997217013, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0017699430002267036, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0017699430002267036 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 0.04832729100007782, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0005591050000930409, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 0.0005108129998916411, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0005108129998916411 | |
| }, | |
| "communicator.exchange": { | |
| "total": 0.04550632199993743, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.04550632199993743 | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.0017510510001557122, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.00034772399999383197, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0014033270001618803, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0014033270001618803 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 1440.0817881289784, | |
| "count": 64041, | |
| "is_parallel": true, | |
| "self": 34.32635555296429, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 22.743758521027075, | |
| "count": 64041, | |
| "is_parallel": true, | |
| "self": 22.743758521027075 | |
| }, | |
| "communicator.exchange": { | |
| "total": 1281.5819890810083, | |
| "count": 64041, | |
| "is_parallel": true, | |
| "self": 1281.5819890810083 | |
| }, | |
| "steps_from_proto": { | |
| "total": 101.42968497397874, | |
| "count": 64041, | |
| "is_parallel": true, | |
| "self": 20.17562130699457, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 81.25406366698417, | |
| "count": 512328, | |
| "is_parallel": true, | |
| "self": 81.25406366698417 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 658.6411741511072, | |
| "count": 64042, | |
| "self": 2.374792865042764, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 109.61476486606489, | |
| "count": 64042, | |
| "self": 109.40732821406527, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.2074366519996147, | |
| "count": 2, | |
| "self": 0.2074366519996147 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 546.6516164199995, | |
| "count": 451, | |
| "self": 357.9265664339639, | |
| "children": { | |
| "TorchPPOOptimizer.update": { | |
| "total": 188.72504998603563, | |
| "count": 22806, | |
| "self": 188.72504998603563 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 8.639999578008428e-07, | |
| "count": 1, | |
| "self": 8.639999578008428e-07 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.0945477390000633, | |
| "count": 1, | |
| "self": 0.0013600190000033763, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.09318772000005993, | |
| "count": 1, | |
| "self": 0.09318772000005993 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |