{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.1358981728553772, "min": 0.13466499745845795, "max": 1.450836420059204, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4089.9912109375, "min": 4020.55810546875, "max": 44012.57421875, "count": 100 }, "Pyramids.Step.mean": { "value": 2999934.0, "min": 29952.0, "max": 2999934.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999934.0, "min": 29952.0, "max": 2999934.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8356802463531494, "min": -0.09969067573547363, "max": 0.8914013504981995, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 251.5397491455078, "min": -23.626689910888672, "max": 278.43890380859375, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.005530583672225475, "min": -0.016728952527046204, "max": 0.317399263381958, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.664705753326416, "min": -5.001956939697266, "max": 76.49322509765625, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07005138902191081, "min": 0.06386500202158156, "max": 0.07433712469678394, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9807194463067513, "min": 0.5110337513695664, "max": 1.1005704609657792, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015402836039382249, "min": 0.0001605486660100961, "max": 0.01600621628278445, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21563970455135148, "min": 0.0019265839921211532, "max": 0.23396815127760456, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5850351859738115e-06, "min": 1.5850351859738115e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.219049260363336e-05, "min": 2.219049260363336e-05, "max": 0.0040724305425232, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1005283119047619, "min": 0.1005283119047619, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4073963666666667, "min": 1.3962282666666668, "max": 2.8574768, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.277835928571435e-05, "min": 6.277835928571435e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.000878897030000001, "min": 0.000878897030000001, "max": 0.13576193232, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005908165592700243, "min": 0.005122434347867966, "max": 0.45508870482444763, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.08271431922912598, "min": 0.07171408087015152, "max": 3.1856210231781006, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 215.7762237762238, "min": 201.77631578947367, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30856.0, "min": 15984.0, "max": 34322.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.742255929154116, "min": -1.0000000521540642, "max": 1.7871555424398846, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 249.14259786903858, "min": -31.998801663517952, "max": 271.32939741015434, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.742255929154116, "min": -1.0000000521540642, "max": 1.7871555424398846, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 249.14259786903858, "min": -31.998801663517952, "max": 271.32939741015434, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.013234981449418197, "min": 0.011958091610435267, "max": 9.599285267293453, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.892602347266802, "min": 1.5905029099958483, "max": 153.58856427669525, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1793597515", "python_version": "3.9.9 | packaged by conda-forge | (main, Dec 20 2021, 02:40:17) \n[GCC 9.4.0]", "command_line_arguments": "/content/mlagents-py399/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "0.28.0", "mlagents_envs_version": "0.28.0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.23.5", "end_time_seconds": "1793606061" }, "total": 8545.482196024, "count": 1, "self": 0.5329924459983886, "children": { "run_training.setup": { "total": 0.013998961000652344, "count": 1, "self": 0.013998961000652344 }, "TrainerController.start_learning": { "total": 8544.935204617, "count": 1, "self": 4.738722593019702, "children": { "TrainerController._reset_env": { "total": 4.8618648310002754, "count": 1, "self": 4.8618648310002754 }, "TrainerController.advance": { "total": 8535.24097805898, "count": 195339, "self": 4.864380838160287, "children": { "env_step": { "total": 6374.300150093504, "count": 195339, "self": 6005.3720111879775, "children": { "SubprocessEnvManager._take_step": { "total": 366.1706310383879, "count": 195339, "self": 15.45396303261441, "children": { "TorchPolicy.evaluate": { "total": 350.7166680057735, "count": 187561, "self": 115.93137370636396, "children": { "TorchPolicy.sample_actions": { "total": 234.78529429940954, "count": 187561, "self": 234.78529429940954 } } } } }, "workers": { "total": 2.7575078671388837, "count": 195339, "self": 0.0, "children": { "worker_root": { "total": 8525.241081208747, "count": 195339, "is_parallel": true, "self": 2888.4337730210764, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001931554000293545, "count": 1, "is_parallel": true, "self": 0.0007145519994082861, "children": { "_process_rank_one_or_two_observation": { "total": 0.001217002000885259, "count": 8, "is_parallel": true, "self": 0.001217002000885259 } } }, "UnityEnvironment.step": { "total": 0.0548489309994693, "count": 1, "is_parallel": true, "self": 0.0006338069997582352, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005455319997054175, "count": 1, "is_parallel": true, "self": 0.0005455319997054175 }, "communicator.exchange": { "total": 0.05190514900004928, "count": 1, "is_parallel": true, "self": 0.05190514900004928 }, "steps_from_proto": { "total": 0.0017644429999563727, "count": 1, "is_parallel": true, "self": 0.0004568109998217551, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013076320001346176, "count": 8, "is_parallel": true, "self": 0.0013076320001346176 } } } } } } }, "UnityEnvironment.step": { "total": 5636.807308187671, "count": 195338, "is_parallel": true, "self": 112.25912909114595, "children": { "UnityEnvironment._generate_step_input": { "total": 74.9427940849564, "count": 195338, "is_parallel": true, "self": 74.9427940849564 }, "communicator.exchange": { "total": 5110.860743173564, "count": 195338, "is_parallel": true, "self": 5110.860743173564 }, "steps_from_proto": { "total": 338.744641838005, "count": 195338, "is_parallel": true, "self": 85.12946103095146, "children": { "_process_rank_one_or_two_observation": { "total": 253.61518080705355, "count": 1562704, "is_parallel": true, "self": 253.61518080705355 } } } } } } } } } } }, "trainer_advance": { "total": 2156.076447127317, "count": 195339, "self": 8.782029191497713, "children": { "process_trajectory": { "total": 519.3042306118323, "count": 195339, "self": 518.6424742818317, "children": { "RLTrainer._checkpoint": { "total": 0.6617563300005713, "count": 6, "self": 0.6617563300005713 } } }, "_update_policy": { "total": 1627.990187323987, "count": 1391, "self": 538.5040113813329, "children": { "TorchPPOOptimizer.update": { "total": 1089.486175942654, "count": 68382, "self": 1089.486175942654 } } } } } } }, "trainer_threads": { "total": 1.2119999155402184e-06, "count": 1, "self": 1.2119999155402184e-06 }, "TrainerController._save_models": { "total": 0.09363792200019816, "count": 1, "self": 0.0011710779999702936, "children": { "RLTrainer._checkpoint": { "total": 0.09246684400022787, "count": 1, "self": 0.09246684400022787 } } } } } } }