{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3991127908229828, "min": 0.3991127908229828, "max": 1.4637213945388794, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12018.083984375, "min": 12018.083984375, "max": 44403.453125, "count": 33 }, "Pyramids.Step.mean": { "value": 989992.0, "min": 29952.0, "max": 989992.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989992.0, "min": 29952.0, "max": 989992.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5676408410072327, "min": -0.08447328954935074, "max": 0.5676408410072327, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 158.37179565429688, "min": -20.442535400390625, "max": 158.37179565429688, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.011805189773440361, "min": -0.10470158606767654, "max": 0.3197105824947357, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.2936480045318604, "min": -26.28009796142578, "max": 75.77140808105469, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07017225179744403, "min": 0.06644044555240505, "max": 0.07458126262356111, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0525837769616604, "min": 0.518626815186487, "max": 1.0543431792723235, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015739185541063194, "min": 0.00037691465546681006, "max": 0.017461014986431964, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23608778311594789, "min": 0.0030153172437344805, "max": 0.24445420981004748, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.543677485473336e-06, "min": 7.543677485473336e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011315516228210004, "min": 0.00011315516228210004, "max": 0.0032563547145485, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251452666666667, "min": 0.10251452666666667, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5377179, "min": 1.3691136000000002, "max": 2.4442667, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002612012140000001, "min": 0.0002612012140000001, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0039180182100000014, "min": 0.0039180182100000014, "max": 0.10856660485000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00862602237612009, "min": 0.00862602237612009, "max": 0.45726922154426575, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12939032912254333, "min": 0.12351499497890472, "max": 3.2008845806121826, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 312.8817204301075, "min": 312.8817204301075, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29098.0, "min": 15984.0, "max": 32317.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6225892266919535, "min": -1.0000000521540642, "max": 1.6225892266919535, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 150.90079808235168, "min": -32.000001668930054, "max": 150.90079808235168, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6225892266919535, "min": -1.0000000521540642, "max": 1.6225892266919535, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 150.90079808235168, "min": -32.000001668930054, "max": 150.90079808235168, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.028253270969857584, "min": 0.028253270969857584, "max": 9.648655518889427, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.627554200196755, "min": 2.627554200196755, "max": 154.37848830223083, "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": "1731145139", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]", "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 --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1731147458" }, "total": 2319.606238372, "count": 1, "self": 0.4765932799996335, "children": { "run_training.setup": { "total": 0.05626469100025133, "count": 1, "self": 0.05626469100025133 }, "TrainerController.start_learning": { "total": 2319.073380401, "count": 1, "self": 1.4343267450030908, "children": { "TrainerController._reset_env": { "total": 2.3490275199997086, "count": 1, "self": 2.3490275199997086 }, "TrainerController.advance": { "total": 2315.2023649159964, "count": 63731, "self": 1.435216054976081, "children": { "env_step": { "total": 1601.182134029049, "count": 63731, "self": 1445.6492696309642, "children": { "SubprocessEnvManager._take_step": { "total": 154.68778051207846, "count": 63731, "self": 4.753815979143383, "children": { "TorchPolicy.evaluate": { "total": 149.93396453293508, "count": 62548, "self": 149.93396453293508 } } }, "workers": { "total": 0.8450838860062504, "count": 63731, "self": 0.0, "children": { "worker_root": { "total": 2313.8987823520038, "count": 63731, "is_parallel": true, "self": 986.5229785569741, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020879499998045503, "count": 1, "is_parallel": true, "self": 0.0006366259995047585, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014513240002997918, "count": 8, "is_parallel": true, "self": 0.0014513240002997918 } } }, "UnityEnvironment.step": { "total": 0.04745848799984742, "count": 1, "is_parallel": true, "self": 0.0006814709995524026, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004692320003414352, "count": 1, "is_parallel": true, "self": 0.0004692320003414352 }, "communicator.exchange": { "total": 0.044661017000180436, "count": 1, "is_parallel": true, "self": 0.044661017000180436 }, "steps_from_proto": { "total": 0.0016467679997731466, "count": 1, "is_parallel": true, "self": 0.0003580500001589826, "children": { "_process_rank_one_or_two_observation": { "total": 0.001288717999614164, "count": 8, "is_parallel": true, "self": 0.001288717999614164 } } } } } } }, "UnityEnvironment.step": { "total": 1327.3758037950297, "count": 63730, "is_parallel": true, "self": 33.805882306995954, "children": { "UnityEnvironment._generate_step_input": { "total": 23.420137023970256, "count": 63730, "is_parallel": true, "self": 23.420137023970256 }, "communicator.exchange": { "total": 1172.0424838559975, "count": 63730, "is_parallel": true, "self": 1172.0424838559975 }, "steps_from_proto": { "total": 98.107300608066, "count": 63730, "is_parallel": true, "self": 20.165324701886675, "children": { "_process_rank_one_or_two_observation": { "total": 77.94197590617932, "count": 509840, "is_parallel": true, "self": 77.94197590617932 } } } } } } } } } } }, "trainer_advance": { "total": 712.5850148319714, "count": 63731, "self": 2.6681153329845984, "children": { "process_trajectory": { "total": 135.11775962898628, "count": 63731, "self": 134.8343134169868, "children": { "RLTrainer._checkpoint": { "total": 0.2834462119994896, "count": 2, "self": 0.2834462119994896 } } }, "_update_policy": { "total": 574.7991398700005, "count": 441, "self": 323.3975627110044, "children": { "TorchPPOOptimizer.update": { "total": 251.40157715899613, "count": 22836, "self": 251.40157715899613 } } } } } } }, "trainer_threads": { "total": 9.660006980993785e-07, "count": 1, "self": 9.660006980993785e-07 }, "TrainerController._save_models": { "total": 0.08766025400018407, "count": 1, "self": 0.0016986649998216308, "children": { "RLTrainer._checkpoint": { "total": 0.08596158900036244, "count": 1, "self": 0.08596158900036244 } } } } } } }