{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3061213195323944, "min": 0.3061213195323944, "max": 1.4441807270050049, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9134.66015625, "min": 9134.66015625, "max": 43810.66796875, "count": 33 }, "Pyramids.Step.mean": { "value": 989898.0, "min": 29952.0, "max": 989898.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989898.0, "min": 29952.0, "max": 989898.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5396508574485779, "min": -0.11383025348186493, "max": 0.5906095504760742, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 151.10223388671875, "min": -27.433090209960938, "max": 167.1425018310547, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.2598167061805725, "min": -0.03338294476270676, "max": 0.6891530752182007, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 72.7486801147461, "min": -9.247076034545898, "max": 163.32928466796875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06465266173749809, "min": 0.06414707229058776, "max": 0.07328151535666393, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9051372643249732, "min": 0.4842742405843188, "max": 1.0858455710860617, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.020232916632223697, "min": 0.0003047445616984755, "max": 0.020921840086505585, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.28326083285113174, "min": 0.004266423863778657, "max": 0.28326083285113174, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.685283152557147e-06, "min": 7.685283152557147e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010759396413580004, "min": 0.00010759396413580004, "max": 0.0036335755888081997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10256172857142856, "min": 0.10256172857142856, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4358642, "min": 1.3691136000000002, "max": 2.6111918, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026591668428571446, "min": 0.00026591668428571446, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003722833580000002, "min": 0.003722833580000002, "max": 0.12113806082, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011001910082995892, "min": 0.011001910082995892, "max": 0.7126246094703674, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15402674674987793, "min": 0.15402674674987793, "max": 4.988372325897217, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 345.0736842105263, "min": 324.55434782608694, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32782.0, "min": 15984.0, "max": 32782.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5496294521971752, "min": -1.0000000521540642, "max": 1.653704328543466, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 147.21479795873165, "min": -32.000001668930054, "max": 152.14079822599888, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5496294521971752, "min": -1.0000000521540642, "max": 1.653704328543466, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 147.21479795873165, "min": -32.000001668930054, "max": 152.14079822599888, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03901682363066357, "min": 0.03901682363066357, "max": 14.822170786559582, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.706598244913039, "min": 3.3740520171122625, "max": 237.1547325849533, "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": "1707813689", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1707815885" }, "total": 2196.086510121, "count": 1, "self": 0.7455338720001237, "children": { "run_training.setup": { "total": 0.047829677999970954, "count": 1, "self": 0.047829677999970954 }, "TrainerController.start_learning": { "total": 2195.293146571, "count": 1, "self": 1.3625771070146584, "children": { "TrainerController._reset_env": { "total": 3.170692761000055, "count": 1, "self": 3.170692761000055 }, "TrainerController.advance": { "total": 2190.674498571985, "count": 63799, "self": 1.467631035984141, "children": { "env_step": { "total": 1574.4078550599888, "count": 63799, "self": 1442.522015806024, "children": { "SubprocessEnvManager._take_step": { "total": 131.04601647602294, "count": 63799, "self": 4.757640104028042, "children": { "TorchPolicy.evaluate": { "total": 126.2883763719949, "count": 62559, "self": 126.2883763719949 } } }, "workers": { "total": 0.8398227779418903, "count": 63799, "self": 0.0, "children": { "worker_root": { "total": 2190.1750259579608, "count": 63799, "is_parallel": true, "self": 866.5415567639902, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005113473000164959, "count": 1, "is_parallel": true, "self": 0.0036644240001351136, "children": { "_process_rank_one_or_two_observation": { "total": 0.001449049000029845, "count": 8, "is_parallel": true, "self": 0.001449049000029845 } } }, "UnityEnvironment.step": { "total": 0.05182992999993985, "count": 1, "is_parallel": true, "self": 0.0006085570000777807, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005520939998859831, "count": 1, "is_parallel": true, "self": 0.0005520939998859831 }, "communicator.exchange": { "total": 0.04890513300006205, "count": 1, "is_parallel": true, "self": 0.04890513300006205 }, "steps_from_proto": { "total": 0.0017641459999140352, "count": 1, "is_parallel": true, "self": 0.0003959040000154346, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013682419998986006, "count": 8, "is_parallel": true, "self": 0.0013682419998986006 } } } } } } }, "UnityEnvironment.step": { "total": 1323.6334691939705, "count": 63798, "is_parallel": true, "self": 35.711922957887964, "children": { "UnityEnvironment._generate_step_input": { "total": 26.233798669038833, "count": 63798, "is_parallel": true, "self": 26.233798669038833 }, "communicator.exchange": { "total": 1158.21579475205, "count": 63798, "is_parallel": true, "self": 1158.21579475205 }, "steps_from_proto": { "total": 103.47195281499376, "count": 63798, "is_parallel": true, "self": 20.602213439034358, "children": { "_process_rank_one_or_two_observation": { "total": 82.8697393759594, "count": 510384, "is_parallel": true, "self": 82.8697393759594 } } } } } } } } } } }, "trainer_advance": { "total": 614.7990124760122, "count": 63799, "self": 2.638793346047578, "children": { "process_trajectory": { "total": 127.00826077896204, "count": 63799, "self": 126.79568569296157, "children": { "RLTrainer._checkpoint": { "total": 0.21257508600047004, "count": 2, "self": 0.21257508600047004 } } }, "_update_policy": { "total": 485.1519583510026, "count": 451, "self": 285.1203084829947, "children": { "TorchPPOOptimizer.update": { "total": 200.0316498680079, "count": 22839, "self": 200.0316498680079 } } } } } } }, "trainer_threads": { "total": 8.120000529743265e-07, "count": 1, "self": 8.120000529743265e-07 }, "TrainerController._save_models": { "total": 0.08537731899969003, "count": 1, "self": 0.001298200999826804, "children": { "RLTrainer._checkpoint": { "total": 0.08407911799986323, "count": 1, "self": 0.08407911799986323 } } } } } } }