{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4060059189796448, "min": 0.38895347714424133, "max": 1.4938462972640991, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12206.162109375, "min": 11525.4697265625, "max": 45317.3203125, "count": 33 }, "Pyramids.Step.mean": { "value": 989994.0, "min": 29952.0, "max": 989994.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989994.0, "min": 29952.0, "max": 989994.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5402843356132507, "min": -0.12726302444934845, "max": 0.5408269762992859, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 147.49761962890625, "min": -30.543127059936523, "max": 148.7274169921875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.08557944744825363, "min": -0.05794571340084076, "max": 0.2352677583694458, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 23.363189697265625, "min": -14.892047882080078, "max": 61.404884338378906, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07143790309408063, "min": 0.0643910342113784, "max": 0.072798014273859, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0001306433171289, "min": 0.4855815346898704, "max": 1.0745404994066157, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015626810832137922, "min": 0.00011726431928949405, "max": 0.01765570354666929, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21877535164993092, "min": 0.0015244361507634227, "max": 0.2471798496533701, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.536076059435715e-06, "min": 7.536076059435715e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001055050648321, "min": 0.0001055050648321, "max": 0.0035088866303711994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251199285714285, "min": 0.10251199285714285, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4351679, "min": 1.3691136000000002, "max": 2.5696288000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026094808642857144, "min": 0.00026094808642857144, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036532732100000003, "min": 0.0036532732100000003, "max": 0.11698591711999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012456392869353294, "min": 0.012456392869353294, "max": 0.3294225335121155, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17438949644565582, "min": 0.17438949644565582, "max": 2.305957794189453, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 354.719512195122, "min": 346.53932584269666, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29087.0, "min": 15984.0, "max": 32304.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6209086247800308, "min": -1.0000000521540642, "max": 1.6209086247800308, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 131.2935986071825, "min": -32.000001668930054, "max": 144.665798291564, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6209086247800308, "min": -1.0000000521540642, "max": 1.6209086247800308, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 131.2935986071825, "min": -32.000001668930054, "max": 144.665798291564, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04553977876612744, "min": 0.04553977876612744, "max": 6.897034697234631, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.6887220800563227, "min": 3.6887220800563227, "max": 110.35255515575409, "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": "1686584126", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1686586479" }, "total": 2353.682177957, "count": 1, "self": 0.9142714239997076, "children": { "run_training.setup": { "total": 0.07639235000010558, "count": 1, "self": 0.07639235000010558 }, "TrainerController.start_learning": { "total": 2352.691514183, "count": 1, "self": 1.6857892400139463, "children": { "TrainerController._reset_env": { "total": 4.6419321979999495, "count": 1, "self": 4.6419321979999495 }, "TrainerController.advance": { "total": 2346.204608934986, "count": 63661, "self": 1.6932031859960261, "children": { "env_step": { "total": 1659.193904825001, "count": 63661, "self": 1531.1257454320762, "children": { "SubprocessEnvManager._take_step": { "total": 127.09734540501586, "count": 63661, "self": 5.470583340067151, "children": { "TorchPolicy.evaluate": { "total": 121.62676206494871, "count": 62553, "self": 121.62676206494871 } } }, "workers": { "total": 0.9708139879089686, "count": 63661, "self": 0.0, "children": { "worker_root": { "total": 2346.620035356012, "count": 63661, "is_parallel": true, "self": 944.1939448089051, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001993071000015334, "count": 1, "is_parallel": true, "self": 0.0006092969999826892, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013837740000326448, "count": 8, "is_parallel": true, "self": 0.0013837740000326448 } } }, "UnityEnvironment.step": { "total": 0.05750171800013959, "count": 1, "is_parallel": true, "self": 0.0006757470000593457, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005528980000235606, "count": 1, "is_parallel": true, "self": 0.0005528980000235606 }, "communicator.exchange": { "total": 0.05419097899994085, "count": 1, "is_parallel": true, "self": 0.05419097899994085 }, "steps_from_proto": { "total": 0.0020820940001158306, "count": 1, "is_parallel": true, "self": 0.0004135730002872151, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016685209998286155, "count": 8, "is_parallel": true, "self": 0.0016685209998286155 } } } } } } }, "UnityEnvironment.step": { "total": 1402.426090547107, "count": 63660, "is_parallel": true, "self": 36.27569683209231, "children": { "UnityEnvironment._generate_step_input": { "total": 24.600180334012748, "count": 63660, "is_parallel": true, "self": 24.600180334012748 }, "communicator.exchange": { "total": 1229.7264607520042, "count": 63660, "is_parallel": true, "self": 1229.7264607520042 }, "steps_from_proto": { "total": 111.82375262899768, "count": 63660, "is_parallel": true, "self": 22.300824728821453, "children": { "_process_rank_one_or_two_observation": { "total": 89.52292790017623, "count": 509280, "is_parallel": true, "self": 89.52292790017623 } } } } } } } } } } }, "trainer_advance": { "total": 685.3175009239892, "count": 63661, "self": 3.134231234989784, "children": { "process_trajectory": { "total": 117.4458383730032, "count": 63661, "self": 117.14049285100305, "children": { "RLTrainer._checkpoint": { "total": 0.3053455220001524, "count": 2, "self": 0.3053455220001524 } } }, "_update_policy": { "total": 564.7374313159962, "count": 443, "self": 361.6502136129975, "children": { "TorchPPOOptimizer.update": { "total": 203.08721770299871, "count": 22833, "self": 203.08721770299871 } } } } } } }, "trainer_threads": { "total": 1.3179997040424496e-06, "count": 1, "self": 1.3179997040424496e-06 }, "TrainerController._save_models": { "total": 0.15918249200012724, "count": 1, "self": 0.0019052160000683216, "children": { "RLTrainer._checkpoint": { "total": 0.15727727600005892, "count": 1, "self": 0.15727727600005892 } } } } } } }