{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4956691265106201, "min": 0.48527559638023376, "max": 1.4303313493728638, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14933.51953125, "min": 14589.3251953125, "max": 43390.53125, "count": 33 }, "Pyramids.Step.mean": { "value": 989989.0, "min": 29952.0, "max": 989989.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989989.0, "min": 29952.0, "max": 989989.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3862021863460541, "min": -0.11838216334581375, "max": 0.5079175233840942, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 105.43319702148438, "min": -28.530101776123047, "max": 139.6773223876953, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.006067958194762468, "min": -0.008438055403530598, "max": 0.3793957531452179, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.6565525531768799, "min": -2.269836902618408, "max": 91.05497741699219, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07165024691752882, "min": 0.0665335889262635, "max": 0.07469579702592455, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0747537037629322, "min": 0.4968595442112238, "max": 1.0747537037629322, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01673758753006243, "min": 0.0009009111378021687, "max": 0.018051888208529685, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.25106381295093644, "min": 0.006640117139084751, "max": 0.27077832312794525, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.405417531559999e-06, "min": 7.405417531559999e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011108126297339999, "min": 0.00011108126297339999, "max": 0.0033775126741624993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10246844000000001, "min": 0.10246844000000001, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5370266000000001, "min": 1.3691136000000002, "max": 2.4841975, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025659715600000004, "min": 0.00025659715600000004, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038489573400000004, "min": 0.0038489573400000004, "max": 0.11260116625, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01177037600427866, "min": 0.01177037600427866, "max": 0.5231417417526245, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17655563354492188, "min": 0.1650601029396057, "max": 3.661992311477661, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 436.7027027027027, "min": 366.1923076923077, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32316.0, "min": 15984.0, "max": 32316.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4281134903430939, "min": -1.0000000521540642, "max": 1.5312204926441877, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 105.68039828538895, "min": -32.000001668930054, "max": 120.57139771431684, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4281134903430939, "min": -1.0000000521540642, "max": 1.5312204926441877, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 105.68039828538895, "min": -32.000001668930054, "max": 120.57139771431684, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05341564198150425, "min": 0.046876817942474086, "max": 10.282869195565581, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.9527575066313148, "min": 3.3751308918581344, "max": 164.5259071290493, "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": "1698541016", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1698543245" }, "total": 2229.5882760819995, "count": 1, "self": 0.6343897709994053, "children": { "run_training.setup": { "total": 0.08272715199996128, "count": 1, "self": 0.08272715199996128 }, "TrainerController.start_learning": { "total": 2228.871159159, "count": 1, "self": 1.3437376750384828, "children": { "TrainerController._reset_env": { "total": 3.6894625200000064, "count": 1, "self": 3.6894625200000064 }, "TrainerController.advance": { "total": 2223.7602144029615, "count": 63643, "self": 1.45191175292166, "children": { "env_step": { "total": 1596.8874674360432, "count": 63643, "self": 1463.6657320040915, "children": { "SubprocessEnvManager._take_step": { "total": 132.38083946901293, "count": 63643, "self": 4.591594407957018, "children": { "TorchPolicy.evaluate": { "total": 127.78924506105591, "count": 62542, "self": 127.78924506105591 } } }, "workers": { "total": 0.8408959629387027, "count": 63643, "self": 0.0, "children": { "worker_root": { "total": 2224.112693270989, "count": 63643, "is_parallel": true, "self": 879.8230499589451, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002590962000112995, "count": 1, "is_parallel": true, "self": 0.0007657989997369441, "children": { "_process_rank_one_or_two_observation": { "total": 0.001825163000376051, "count": 8, "is_parallel": true, "self": 0.001825163000376051 } } }, "UnityEnvironment.step": { "total": 0.051381299000013314, "count": 1, "is_parallel": true, "self": 0.000549176000049556, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046566200012421177, "count": 1, "is_parallel": true, "self": 0.00046566200012421177 }, "communicator.exchange": { "total": 0.04864198599989322, "count": 1, "is_parallel": true, "self": 0.04864198599989322 }, "steps_from_proto": { "total": 0.0017244749999463238, "count": 1, "is_parallel": true, "self": 0.0003790300006585312, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013454449992877926, "count": 8, "is_parallel": true, "self": 0.0013454449992877926 } } } } } } }, "UnityEnvironment.step": { "total": 1344.2896433120438, "count": 63642, "is_parallel": true, "self": 35.319668073042976, "children": { "UnityEnvironment._generate_step_input": { "total": 26.252472011976124, "count": 63642, "is_parallel": true, "self": 26.252472011976124 }, "communicator.exchange": { "total": 1178.320788153013, "count": 63642, "is_parallel": true, "self": 1178.320788153013 }, "steps_from_proto": { "total": 104.39671507401181, "count": 63642, "is_parallel": true, "self": 21.27357998918842, "children": { "_process_rank_one_or_two_observation": { "total": 83.12313508482339, "count": 509136, "is_parallel": true, "self": 83.12313508482339 } } } } } } } } } } }, "trainer_advance": { "total": 625.420835213997, "count": 63643, "self": 2.566342287959742, "children": { "process_trajectory": { "total": 125.38592060603537, "count": 63643, "self": 125.17516795503593, "children": { "RLTrainer._checkpoint": { "total": 0.21075265099943863, "count": 2, "self": 0.21075265099943863 } } }, "_update_policy": { "total": 497.46857232000184, "count": 446, "self": 294.5221889500151, "children": { "TorchPPOOptimizer.update": { "total": 202.94638336998673, "count": 22809, "self": 202.94638336998673 } } } } } } }, "trainer_threads": { "total": 1.0939997991954442e-06, "count": 1, "self": 1.0939997991954442e-06 }, "TrainerController._save_models": { "total": 0.0777434669998911, "count": 1, "self": 0.0014997539997239073, "children": { "RLTrainer._checkpoint": { "total": 0.07624371300016719, "count": 1, "self": 0.07624371300016719 } } } } } } }