Reinforcement Learning
ml-agents
TensorBoard
ONNX
Pyramids
deep-reinforcement-learning
ML-Agents-Pyramids
Instructions to use ButtaByte/MLAgents-Pyramids with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ml-agents
How to use ButtaByte/MLAgents-Pyramids with ml-agents:
mlagents-load-from-hf --repo-id="ButtaByte/MLAgents-Pyramids" --local-dir="./download: string[]s"
- Notebooks
- Google Colab
- Kaggle
| { | |
| "name": "root", | |
| "gauges": { | |
| "Pyramids.Policy.Entropy.mean": { | |
| "value": 0.3496977686882019, | |
| "min": 0.3496977686882019, | |
| "max": 1.438382863998413, | |
| "count": 31 | |
| }, | |
| "Pyramids.Policy.Entropy.sum": { | |
| "value": 17339.4140625, | |
| "min": 5891.6162109375, | |
| "max": 65113.05078125, | |
| "count": 31 | |
| }, | |
| "Pyramids.IsTraining.mean": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 31 | |
| }, | |
| "Pyramids.IsTraining.sum": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 31 | |
| }, | |
| "Pyramids.Step.mean": { | |
| "value": 2999827.0, | |
| "min": 1549982.0, | |
| "max": 2999827.0, | |
| "count": 30 | |
| }, | |
| "Pyramids.Step.sum": { | |
| "value": 2999827.0, | |
| "min": 1549982.0, | |
| "max": 2999827.0, | |
| "count": 30 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": 0.47240471839904785, | |
| "min": 0.01659783348441124, | |
| "max": 0.5946049094200134, | |
| "count": 30 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": 115.26675415039062, | |
| "min": 3.468947172164917, | |
| "max": 152.21885681152344, | |
| "count": 30 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.mean": { | |
| "value": -0.016628071665763855, | |
| "min": -0.03436597064137459, | |
| "max": 0.06806575506925583, | |
| "count": 30 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.sum": { | |
| "value": -4.057249546051025, | |
| "min": -8.041637420654297, | |
| "max": 14.429940223693848, | |
| "count": 30 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.mean": { | |
| "value": 0.06902246359267881, | |
| "min": 0.06464286143901217, | |
| "max": 0.07600686806628652, | |
| "count": 30 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.sum": { | |
| "value": 1.5875166626316128, | |
| "min": 0.9893171148157742, | |
| "max": 1.737136769766449, | |
| "count": 30 | |
| }, | |
| "Pyramids.Losses.ValueLoss.mean": { | |
| "value": 0.0113997588012218, | |
| "min": 0.0035444383079130362, | |
| "max": 0.012698868781017206, | |
| "count": 30 | |
| }, | |
| "Pyramids.Losses.ValueLoss.sum": { | |
| "value": 0.2621944524281014, | |
| "min": 0.05299955189413608, | |
| "max": 0.30391888244704723, | |
| "count": 30 | |
| }, | |
| "Pyramids.Policy.LearningRate.mean": { | |
| "value": 2.4657600476782597e-06, | |
| "min": 2.4657600476782597e-06, | |
| "max": 0.00014728039376369525, | |
| "count": 30 | |
| }, | |
| "Pyramids.Policy.LearningRate.sum": { | |
| "value": 5.671248109659997e-05, | |
| "min": 5.671248109659997e-05, | |
| "max": 0.003278460107180367, | |
| "count": 30 | |
| }, | |
| "Pyramids.Policy.Epsilon.mean": { | |
| "value": 0.10082188695652175, | |
| "min": 0.10082188695652175, | |
| "max": 0.1490934476190476, | |
| "count": 30 | |
| }, | |
| "Pyramids.Policy.Epsilon.sum": { | |
| "value": 2.3189034000000004, | |
| "min": 2.0873082666666667, | |
| "max": 3.392819633333334, | |
| "count": 30 | |
| }, | |
| "Pyramids.Policy.Beta.mean": { | |
| "value": 9.21065069565217e-05, | |
| "min": 9.21065069565217e-05, | |
| "max": 0.004914435417142857, | |
| "count": 30 | |
| }, | |
| "Pyramids.Policy.Beta.sum": { | |
| "value": 0.002118449659999999, | |
| "min": 0.002118449659999999, | |
| "max": 0.10940268136999999, | |
| "count": 30 | |
| }, | |
| "Pyramids.Losses.RNDLoss.mean": { | |
| "value": 2.134653550456278e-05, | |
| "min": 2.134653550456278e-05, | |
| "max": 3.62854843842797e-05, | |
| "count": 30 | |
| }, | |
| "Pyramids.Losses.RNDLoss.sum": { | |
| "value": 0.0004909703275188804, | |
| "min": 0.0004909703275188804, | |
| "max": 0.0008047671290114522, | |
| "count": 30 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.mean": { | |
| "value": 406.9583333333333, | |
| "min": 347.3943661971831, | |
| "max": 863.5094339622641, | |
| "count": 30 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.sum": { | |
| "value": 48835.0, | |
| "min": 45766.0, | |
| "max": 52823.0, | |
| "count": 30 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.mean": { | |
| "value": 1.31322806876553, | |
| "min": -0.22257740992420125, | |
| "max": 1.546792780538257, | |
| "count": 30 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.sum": { | |
| "value": 158.90059632062912, | |
| "min": -11.796602725982666, | |
| "max": 218.66419652104378, | |
| "count": 30 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.mean": { | |
| "value": 1.31322806876553, | |
| "min": -0.22257740992420125, | |
| "max": 1.546792780538257, | |
| "count": 30 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.sum": { | |
| "value": 158.90059632062912, | |
| "min": -11.796602725982666, | |
| "max": 218.66419652104378, | |
| "count": 30 | |
| }, | |
| "Pyramids.Policy.RndReward.mean": { | |
| "value": 0.000487636625869279, | |
| "min": 0.0004246232857475418, | |
| "max": 0.0017610922478301942, | |
| "count": 30 | |
| }, | |
| "Pyramids.Policy.RndReward.sum": { | |
| "value": 0.05900403173018276, | |
| "min": 0.05814932025288044, | |
| "max": 0.10813312111895357, | |
| "count": 30 | |
| } | |
| }, | |
| "metadata": { | |
| "timer_format_version": "0.1.0", | |
| "start_time_seconds": "1776829921", | |
| "python_version": "3.10.11 (tags/v3.10.11:7d4cc5a, Apr 5 2023, 00:38:17) [MSC v.1929 64 bit (AMD64)]", | |
| "command_line_arguments": "C:\\Users\\tayla\\ml-agents\\mlagents_env\\Scripts\\mlagents-learn config/ppo/PyramidsRND.yaml --env=training-envs-executables/Windows/Pyramids --run-id=First_Training --resume --no-graphics", | |
| "mlagents_version": "1.1.0", | |
| "mlagents_envs_version": "1.1.0", | |
| "communication_protocol_version": "1.5.0", | |
| "pytorch_version": "2.1.1+cpu", | |
| "numpy_version": "1.23.5", | |
| "end_time_seconds": "1776832956" | |
| }, | |
| "total": 3035.3259612000547, | |
| "count": 1, | |
| "self": 0.32805069989990443, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.12268370005767792, | |
| "count": 1, | |
| "self": 0.12268370005767792 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 3034.875226800097, | |
| "count": 1, | |
| "self": 2.0862086954293773, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 4.640463000047021, | |
| "count": 1, | |
| "self": 4.640463000047021 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 3028.049600104685, | |
| "count": 96265, | |
| "self": 1.8950329134240746, | |
| "children": { | |
| "env_step": { | |
| "total": 1656.5996473971754, | |
| "count": 96265, | |
| "self": 1474.43365781405, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 180.61125228798483, | |
| "count": 96265, | |
| "self": 6.827575302799232, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 173.7836769851856, | |
| "count": 93853, | |
| "self": 173.7836769851856 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 1.5547372951405123, | |
| "count": 96265, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 3027.101965487702, | |
| "count": 96265, | |
| "is_parallel": true, | |
| "self": 1727.102127379505, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.0008677999721840024, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.00020379992201924324, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0006640000501647592, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0006640000501647592 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 1299.9989703082247, | |
| "count": 96265, | |
| "is_parallel": true, | |
| "self": 39.529148857924156, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 33.18920588179026, | |
| "count": 96265, | |
| "is_parallel": true, | |
| "self": 33.18920588179026 | |
| }, | |
| "communicator.exchange": { | |
| "total": 1127.3387896807399, | |
| "count": 96265, | |
| "is_parallel": true, | |
| "self": 1127.3387896807399 | |
| }, | |
| "steps_from_proto": { | |
| "total": 99.94182588777039, | |
| "count": 96265, | |
| "is_parallel": true, | |
| "self": 20.24457694659941, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 79.69724894117098, | |
| "count": 770120, | |
| "is_parallel": true, | |
| "self": 79.69724894117098 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 1369.5549197940854, | |
| "count": 96265, | |
| "self": 4.899919007206336, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 162.9425140870735, | |
| "count": 96265, | |
| "self": 162.61296648695134, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.32954760012216866, | |
| "count": 4, | |
| "self": 0.32954760012216866 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 1201.7124866998056, | |
| "count": 680, | |
| "self": 439.2752985031111, | |
| "children": { | |
| "TorchPPOOptimizer.update": { | |
| "total": 762.4371881966945, | |
| "count": 34155, | |
| "self": 762.4371881966945 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 7.00005330145359e-07, | |
| "count": 1, | |
| "self": 7.00005330145359e-07 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.0989542999304831, | |
| "count": 1, | |
| "self": 0.025357199949212372, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.07359709998127073, | |
| "count": 1, | |
| "self": 0.07359709998127073 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |