{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3002696931362152, "min": 0.3002696931362152, "max": 1.4377026557922363, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 8969.65625, "min": 8969.65625, "max": 43614.1484375, "count": 33 }, "Pyramids.Step.mean": { "value": 989887.0, "min": 29952.0, "max": 989887.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989887.0, "min": 29952.0, "max": 989887.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5403516888618469, "min": -0.10925205796957016, "max": 0.6929113864898682, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 148.05636596679688, "min": -26.32974624633789, "max": 199.5584716796875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01231175847351551, "min": -0.013837632723152637, "max": 0.3435705602169037, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.3734219074249268, "min": -3.833024263381958, "max": 81.55667114257812, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06427401011890088, "min": 0.06427401011890088, "max": 0.07227989902818938, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.8998361416646123, "min": 0.49983938209994844, "max": 1.0723164843026702, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015112614030899226, "min": 0.00016609076866669177, "max": 0.017512871685993196, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21157659643258916, "min": 0.002325270761333685, "max": 0.2578015065325114, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.649668878714281e-06, "min": 7.649668878714281e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010709536430199995, "min": 0.00010709536430199995, "max": 0.0033820304726565995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10254985714285715, "min": 0.10254985714285715, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4356980000000001, "min": 1.3886848, "max": 2.5273434, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026473072857142847, "min": 0.00026473072857142847, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003706230199999999, "min": 0.003706230199999999, "max": 0.11276160566, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011497552506625652, "min": 0.011497552506625652, "max": 0.4114600121974945, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16096574068069458, "min": 0.16096574068069458, "max": 2.8802201747894287, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 350.42857142857144, "min": 270.6818181818182, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29436.0, "min": 15984.0, "max": 33930.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.558122336426202, "min": -1.0000000521540642, "max": 1.711134536428885, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 132.44039859622717, "min": -31.99920167028904, "max": 188.22479900717735, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.558122336426202, "min": -1.0000000521540642, "max": 1.711134536428885, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 132.44039859622717, "min": -31.99920167028904, "max": 188.22479900717735, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.041927368141477926, "min": 0.03521672754815716, "max": 8.130270268768072, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.563826292025624, "min": 3.535276971786516, "max": 130.08432430028915, "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": "1739089169", "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": "1739091449" }, "total": 2280.1270405590003, "count": 1, "self": 0.47581156200021724, "children": { "run_training.setup": { "total": 0.020833099999890692, "count": 1, "self": 0.020833099999890692 }, "TrainerController.start_learning": { "total": 2279.630395897, "count": 1, "self": 1.2546496149916493, "children": { "TrainerController._reset_env": { "total": 2.244552578999901, "count": 1, "self": 2.244552578999901 }, "TrainerController.advance": { "total": 2276.048420231008, "count": 64172, "self": 1.2652237081360909, "children": { "env_step": { "total": 1597.4764056549689, "count": 64172, "self": 1450.898730378025, "children": { "SubprocessEnvManager._take_step": { "total": 145.85359402900303, "count": 64172, "self": 4.41883026296091, "children": { "TorchPolicy.evaluate": { "total": 141.43476376604212, "count": 62554, "self": 141.43476376604212 } } }, "workers": { "total": 0.7240812479408305, "count": 64172, "self": 0.0, "children": { "worker_root": { "total": 2274.7388905220723, "count": 64172, "is_parallel": true, "self": 932.545053053098, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002440462000322441, "count": 1, "is_parallel": true, "self": 0.0007683210005779983, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016721409997444425, "count": 8, "is_parallel": true, "self": 0.0016721409997444425 } } }, "UnityEnvironment.step": { "total": 0.046360442000150215, "count": 1, "is_parallel": true, "self": 0.0005045630000495294, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043536000021049404, "count": 1, "is_parallel": true, "self": 0.00043536000021049404 }, "communicator.exchange": { "total": 0.04385723199993663, "count": 1, "is_parallel": true, "self": 0.04385723199993663 }, "steps_from_proto": { "total": 0.0015632869999535615, "count": 1, "is_parallel": true, "self": 0.0003305669997644145, "children": { "_process_rank_one_or_two_observation": { "total": 0.001232720000189147, "count": 8, "is_parallel": true, "self": 0.001232720000189147 } } } } } } }, "UnityEnvironment.step": { "total": 1342.1938374689744, "count": 64171, "is_parallel": true, "self": 30.7239853710671, "children": { "UnityEnvironment._generate_step_input": { "total": 22.801280685951497, "count": 64171, "is_parallel": true, "self": 22.801280685951497 }, "communicator.exchange": { "total": 1197.5109295420293, "count": 64171, "is_parallel": true, "self": 1197.5109295420293 }, "steps_from_proto": { "total": 91.15764186992647, "count": 64171, "is_parallel": true, "self": 17.60759595896343, "children": { "_process_rank_one_or_two_observation": { "total": 73.55004591096304, "count": 513368, "is_parallel": true, "self": 73.55004591096304 } } } } } } } } } } }, "trainer_advance": { "total": 677.3067908679031, "count": 64172, "self": 2.363703259909471, "children": { "process_trajectory": { "total": 126.7164957479904, "count": 64172, "self": 126.51262594698983, "children": { "RLTrainer._checkpoint": { "total": 0.20386980100056462, "count": 2, "self": 0.20386980100056462 } } }, "_update_policy": { "total": 548.2265918600033, "count": 447, "self": 302.7540072559823, "children": { "TorchPPOOptimizer.update": { "total": 245.472584604021, "count": 22884, "self": 245.472584604021 } } } } } } }, "trainer_threads": { "total": 8.400002116104588e-07, "count": 1, "self": 8.400002116104588e-07 }, "TrainerController._save_models": { "total": 0.08277263200034213, "count": 1, "self": 0.0015467150005861185, "children": { "RLTrainer._checkpoint": { "total": 0.08122591699975601, "count": 1, "self": 0.08122591699975601 } } } } } } }