{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.44057920575141907, "min": 0.44057920575141907, "max": 1.4788461923599243, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13337.2138671875, "min": 13337.2138671875, "max": 44862.27734375, "count": 33 }, "Pyramids.Step.mean": { "value": 989971.0, "min": 29952.0, "max": 989971.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989971.0, "min": 29952.0, "max": 989971.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.06502872705459595, "min": -0.15998154878616333, "max": 0.06502872705459595, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 16.062095642089844, "min": -37.915626525878906, "max": 16.062095642089844, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0010095644975081086, "min": -0.0010095644975081086, "max": 0.36991962790489197, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.24936243891716003, "min": -0.24936243891716003, "max": 87.67095184326172, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0714678846426254, "min": 0.0661468210869417, "max": 0.07441532265662158, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0005503849967556, "min": 0.5012955397271133, "max": 1.041942974617568, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.00584085914498432, "min": 0.00012682544908647475, "max": 0.007199648298672869, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.08177202802978048, "min": 0.001521905389037697, "max": 0.10079507618142017, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.3703046861214305e-06, "min": 7.3703046861214305e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010318426560570002, "min": 0.00010318426560570002, "max": 0.0034927453357515995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10245673571428572, "min": 0.10245673571428572, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4343943000000001, "min": 1.3691136000000002, "max": 2.4642484000000002, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000255427897857143, "min": 0.000255427897857143, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035759905700000014, "min": 0.0035759905700000014, "max": 0.11643841516, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011636259034276009, "min": 0.011636259034276009, "max": 0.4041307270526886, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16290763020515442, "min": 0.16290763020515442, "max": 2.8289151191711426, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 805.1621621621622, "min": 730.525, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29791.0, "min": 15984.0, "max": 32561.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.059454014575159225, "min": -1.0000000521540642, "max": 0.3191599616780877, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 2.1997985392808914, "min": -32.000001668930054, "max": 12.766398467123508, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.059454014575159225, "min": -1.0000000521540642, "max": 0.3191599616780877, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 2.1997985392808914, "min": -32.000001668930054, "max": 12.766398467123508, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.09556672518846353, "min": 0.09556672518846353, "max": 7.906540432944894, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.5359688319731504, "min": 3.5359688319731504, "max": 126.5046469271183, "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": "1736434862", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1736436911" }, "total": 2049.1311384339997, "count": 1, "self": 0.5398503189994699, "children": { "run_training.setup": { "total": 0.08098940099989704, "count": 1, "self": 0.08098940099989704 }, "TrainerController.start_learning": { "total": 2048.5102987140003, "count": 1, "self": 1.270376165995458, "children": { "TrainerController._reset_env": { "total": 3.0744189530000767, "count": 1, "self": 3.0744189530000767 }, "TrainerController.advance": { "total": 2044.025273499005, "count": 63213, "self": 1.3889812640704804, "children": { "env_step": { "total": 1351.5680194359516, "count": 63213, "self": 1205.0238568449763, "children": { "SubprocessEnvManager._take_step": { "total": 145.79169416299374, "count": 63213, "self": 4.457561764972979, "children": { "TorchPolicy.evaluate": { "total": 141.33413239802076, "count": 62556, "self": 141.33413239802076 } } }, "workers": { "total": 0.7524684279815119, "count": 63213, "self": 0.0, "children": { "worker_root": { "total": 2043.7552434330405, "count": 63213, "is_parallel": true, "self": 949.1042328610201, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0035118170003443083, "count": 1, "is_parallel": true, "self": 0.0014756230016246263, "children": { "_process_rank_one_or_two_observation": { "total": 0.002036193998719682, "count": 8, "is_parallel": true, "self": 0.002036193998719682 } } }, "UnityEnvironment.step": { "total": 0.060358078999797726, "count": 1, "is_parallel": true, "self": 0.0006235119994926208, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004316559998187586, "count": 1, "is_parallel": true, "self": 0.0004316559998187586 }, "communicator.exchange": { "total": 0.0576651800001855, "count": 1, "is_parallel": true, "self": 0.0576651800001855 }, "steps_from_proto": { "total": 0.001637731000300846, "count": 1, "is_parallel": true, "self": 0.00034677899930102285, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012909520009998232, "count": 8, "is_parallel": true, "self": 0.0012909520009998232 } } } } } } }, "UnityEnvironment.step": { "total": 1094.6510105720204, "count": 63212, "is_parallel": true, "self": 32.25946131885121, "children": { "UnityEnvironment._generate_step_input": { "total": 22.272855520068788, "count": 63212, "is_parallel": true, "self": 22.272855520068788 }, "communicator.exchange": { "total": 945.9495453710647, "count": 63212, "is_parallel": true, "self": 945.9495453710647 }, "steps_from_proto": { "total": 94.16914836203568, "count": 63212, "is_parallel": true, "self": 18.53186691997098, "children": { "_process_rank_one_or_two_observation": { "total": 75.6372814420647, "count": 505696, "is_parallel": true, "self": 75.6372814420647 } } } } } } } } } } }, "trainer_advance": { "total": 691.0682727989829, "count": 63213, "self": 2.515144006956234, "children": { "process_trajectory": { "total": 128.4836339230319, "count": 63213, "self": 128.23866385603242, "children": { "RLTrainer._checkpoint": { "total": 0.24497006699948543, "count": 2, "self": 0.24497006699948543 } } }, "_update_policy": { "total": 560.0694948689948, "count": 444, "self": 317.0751977850332, "children": { "TorchPPOOptimizer.update": { "total": 242.99429708396156, "count": 22803, "self": 242.99429708396156 } } } } } } }, "trainer_threads": { "total": 1.3730004866374657e-06, "count": 1, "self": 1.3730004866374657e-06 }, "TrainerController._save_models": { "total": 0.14022872299938172, "count": 1, "self": 0.003546908999851439, "children": { "RLTrainer._checkpoint": { "total": 0.13668181399953028, "count": 1, "self": 0.13668181399953028 } } } } } } }