| { | |
| "name": "root", | |
| "gauges": { | |
| "Pyramids.Policy.Entropy.mean": { | |
| "value": 0.5916886925697327, | |
| "min": 0.5885145664215088, | |
| "max": 1.505496859550476, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Entropy.sum": { | |
| "value": 17845.330078125, | |
| "min": 17354.1171875, | |
| "max": 45670.75390625, | |
| "count": 33 | |
| }, | |
| "Pyramids.Step.mean": { | |
| "value": 989945.0, | |
| "min": 29952.0, | |
| "max": 989945.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Step.sum": { | |
| "value": 989945.0, | |
| "min": 29952.0, | |
| "max": 989945.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": 0.30596616864204407, | |
| "min": -0.1004587784409523, | |
| "max": 0.30596616864204407, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": 80.46910095214844, | |
| "min": -24.110107421875, | |
| "max": 80.46910095214844, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.mean": { | |
| "value": 0.2756027281284332, | |
| "min": -0.40640828013420105, | |
| "max": 0.2756027281284332, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.sum": { | |
| "value": 72.4835205078125, | |
| "min": -104.85333251953125, | |
| "max": 72.4835205078125, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.mean": { | |
| "value": 0.07299499735258994, | |
| "min": 0.0650588906809025, | |
| "max": 0.07391508124888248, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.sum": { | |
| "value": 1.0949249602888491, | |
| "min": 0.49850405713418844, | |
| "max": 1.0949249602888491, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.ValueLoss.mean": { | |
| "value": 0.04544123583412395, | |
| "min": 0.00013786267628415727, | |
| "max": 0.04544123583412395, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.ValueLoss.sum": { | |
| "value": 0.6816185375118592, | |
| "min": 0.0017922147916940444, | |
| "max": 0.6816185375118592, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.LearningRate.mean": { | |
| "value": 7.507937497386668e-06, | |
| "min": 7.507937497386668e-06, | |
| "max": 0.00029515063018788575, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.LearningRate.sum": { | |
| "value": 0.00011261906246080001, | |
| "min": 0.00011261906246080001, | |
| "max": 0.0032552912149029995, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Epsilon.mean": { | |
| "value": 0.10250261333333334, | |
| "min": 0.10250261333333334, | |
| "max": 0.19838354285714285, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Epsilon.sum": { | |
| "value": 1.5375392, | |
| "min": 1.3886848, | |
| "max": 2.3850969999999996, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Beta.mean": { | |
| "value": 0.0002600110720000001, | |
| "min": 0.0002600110720000001, | |
| "max": 0.00983851593142857, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Beta.sum": { | |
| "value": 0.0039001660800000015, | |
| "min": 0.0039001660800000015, | |
| "max": 0.1085311903, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.RNDLoss.mean": { | |
| "value": 0.009679129347205162, | |
| "min": 0.009679129347205162, | |
| "max": 0.3335517942905426, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.RNDLoss.sum": { | |
| "value": 0.14518694579601288, | |
| "min": 0.1375589519739151, | |
| "max": 2.334862470626831, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.mean": { | |
| "value": 513.8412698412699, | |
| "min": 513.8412698412699, | |
| "max": 999.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.sum": { | |
| "value": 32372.0, | |
| "min": 15984.0, | |
| "max": 33213.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.mean": { | |
| "value": 1.2003491784608553, | |
| "min": -1.0000000521540642, | |
| "max": 1.2003491784608553, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.sum": { | |
| "value": 75.62199824303389, | |
| "min": -30.496001675724983, | |
| "max": 75.62199824303389, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.mean": { | |
| "value": 1.2003491784608553, | |
| "min": -1.0000000521540642, | |
| "max": 1.2003491784608553, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.sum": { | |
| "value": 75.62199824303389, | |
| "min": -30.496001675724983, | |
| "max": 75.62199824303389, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndReward.mean": { | |
| "value": 0.05182602661033531, | |
| "min": 0.05182602661033531, | |
| "max": 6.687497523613274, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndReward.sum": { | |
| "value": 3.2650396764511243, | |
| "min": 2.9489239331742283, | |
| "max": 106.99996037781239, | |
| "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": "1742036000", | |
| "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": "2.6.0+cu124", | |
| "numpy_version": "1.23.5", | |
| "end_time_seconds": "1742038165" | |
| }, | |
| "total": 2165.0283848970003, | |
| "count": 1, | |
| "self": 0.47580551200007903, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.02015908699991087, | |
| "count": 1, | |
| "self": 0.02015908699991087 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 2164.532420298, | |
| "count": 1, | |
| "self": 1.337727658994936, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 2.4738161359998685, | |
| "count": 1, | |
| "self": 2.4738161359998685 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 2160.6320544590053, | |
| "count": 63320, | |
| "self": 1.409046139905513, | |
| "children": { | |
| "env_step": { | |
| "total": 1485.1224861160858, | |
| "count": 63320, | |
| "self": 1328.0283551931361, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 156.2966909189638, | |
| "count": 63320, | |
| "self": 4.741240599965295, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 151.5554503189985, | |
| "count": 62562, | |
| "self": 151.5554503189985 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 0.797440003985912, | |
| "count": 63320, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 2159.524144812988, | |
| "count": 63320, | |
| "is_parallel": true, | |
| "self": 943.8024561050256, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0, | |
| "count": 0, | |
| "is_parallel": true, | |
| "self": 0.0, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.002355125999883967, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0007959319998462888, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.001559194000037678, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.001559194000037678 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 0.09869333500000721, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.000559686000315196, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 0.00042618799989213585, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.00042618799989213585 | |
| }, | |
| "communicator.exchange": { | |
| "total": 0.09594364299982772, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.09594364299982772 | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.0017638179999721615, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.000404335000212086, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0013594829997600755, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0013594829997600755 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 1215.7216887079626, | |
| "count": 63319, | |
| "is_parallel": true, | |
| "self": 31.730198557964968, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 23.250416356030428, | |
| "count": 63319, | |
| "is_parallel": true, | |
| "self": 23.250416356030428 | |
| }, | |
| "communicator.exchange": { | |
| "total": 1062.9444731569745, | |
| "count": 63319, | |
| "is_parallel": true, | |
| "self": 1062.9444731569745 | |
| }, | |
| "steps_from_proto": { | |
| "total": 97.79660063699271, | |
| "count": 63319, | |
| "is_parallel": true, | |
| "self": 19.896709771073574, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 77.89989086591913, | |
| "count": 506552, | |
| "is_parallel": true, | |
| "self": 77.89989086591913 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 674.1005222030137, | |
| "count": 63320, | |
| "self": 2.4676304970641922, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 126.26876715295066, | |
| "count": 63320, | |
| "self": 126.06463618395128, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.20413096899937955, | |
| "count": 2, | |
| "self": 0.20413096899937955 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 545.3641245529989, | |
| "count": 440, | |
| "self": 299.7092829199678, | |
| "children": { | |
| "TorchPPOOptimizer.update": { | |
| "total": 245.65484163303108, | |
| "count": 22815, | |
| "self": 245.65484163303108 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 9.269997462979518e-07, | |
| "count": 1, | |
| "self": 9.269997462979518e-07 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.08882111699995221, | |
| "count": 1, | |
| "self": 0.00174159200014401, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.0870795249998082, | |
| "count": 1, | |
| "self": 0.0870795249998082 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |