{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.43083107471466064, "min": 0.3981855511665344, "max": 1.4289121627807617, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13049.01171875, "min": 12085.7275390625, "max": 43347.48046875, "count": 33 }, "Pyramids.Step.mean": { "value": 989942.0, "min": 29952.0, "max": 989942.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989942.0, "min": 29952.0, "max": 989942.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6190477609634399, "min": -0.10079826414585114, "max": 0.6200735569000244, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 173.95242309570312, "min": -24.292381286621094, "max": 174.86074829101562, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.014901435934007168, "min": -0.014901435934007168, "max": 0.6269429326057434, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -4.18730354309082, "min": -4.18730354309082, "max": 148.58547973632812, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06687174659973683, "min": 0.06418245596883242, "max": 0.07245598959775522, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9362044523963156, "min": 0.4804594342144549, "max": 1.069854908653617, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01575316770909356, "min": 0.0008986748910626606, "max": 0.016419820684989518, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22054434792730984, "min": 0.010867195543215037, "max": 0.22987748958985324, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.578933188007141e-06, "min": 7.578933188007141e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010610506463209998, "min": 0.00010610506463209998, "max": 0.0032581230139591, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252627857142858, "min": 0.10252627857142858, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4353679000000001, "min": 1.3691136000000002, "max": 2.5724521000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002623752292857143, "min": 0.0002623752292857143, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00367325321, "min": 0.00367325321, "max": 0.10863548591, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013314975425601006, "min": 0.013314975425601006, "max": 0.6574302911758423, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18640965223312378, "min": 0.18640965223312378, "max": 4.6020121574401855, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 313.65168539325845, "min": 306.95959595959596, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27915.0, "min": 15984.0, "max": 32404.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6189123438148016, "min": -1.0000000521540642, "max": 1.6672299811989069, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 144.08319859951735, "min": -32.000001668930054, "max": 166.7229981198907, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6189123438148016, "min": -1.0000000521540642, "max": 1.6672299811989069, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 144.08319859951735, "min": -32.000001668930054, "max": 166.7229981198907, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04325541687358872, "min": 0.04325541687358872, "max": 13.750736119225621, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.849732101749396, "min": 3.849732101749396, "max": 220.01177790760994, "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": "1692383383", "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": "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": "1692385706" }, "total": 2323.402815269, "count": 1, "self": 0.49258284799998364, "children": { "run_training.setup": { "total": 0.06530417299995861, "count": 1, "self": 0.06530417299995861 }, "TrainerController.start_learning": { "total": 2322.844928248, "count": 1, "self": 1.5242480409929158, "children": { "TrainerController._reset_env": { "total": 4.099963133000074, "count": 1, "self": 4.099963133000074 }, "TrainerController.advance": { "total": 2317.1216916600074, "count": 63699, "self": 1.5180404750985872, "children": { "env_step": { "total": 1627.2399673430066, "count": 63699, "self": 1507.060417740924, "children": { "SubprocessEnvManager._take_step": { "total": 119.25463239602823, "count": 63699, "self": 5.275179992027688, "children": { "TorchPolicy.evaluate": { "total": 113.97945240400054, "count": 62560, "self": 113.97945240400054 } } }, "workers": { "total": 0.9249172060542605, "count": 63699, "self": 0.0, "children": { "worker_root": { "total": 2316.8853771641, "count": 63699, "is_parallel": true, "self": 939.0218060091311, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017933340000126918, "count": 1, "is_parallel": true, "self": 0.0005732220001846144, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012201119998280774, "count": 8, "is_parallel": true, "self": 0.0012201119998280774 } } }, "UnityEnvironment.step": { "total": 0.05423486899985619, "count": 1, "is_parallel": true, "self": 0.0005871639998531464, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005917339999541582, "count": 1, "is_parallel": true, "self": 0.0005917339999541582 }, "communicator.exchange": { "total": 0.05103085500013549, "count": 1, "is_parallel": true, "self": 0.05103085500013549 }, "steps_from_proto": { "total": 0.002025115999913396, "count": 1, "is_parallel": true, "self": 0.00041759100008675887, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016075249998266372, "count": 8, "is_parallel": true, "self": 0.0016075249998266372 } } } } } } }, "UnityEnvironment.step": { "total": 1377.8635711549691, "count": 63698, "is_parallel": true, "self": 35.65490820897253, "children": { "UnityEnvironment._generate_step_input": { "total": 25.302191144976632, "count": 63698, "is_parallel": true, "self": 25.302191144976632 }, "communicator.exchange": { "total": 1200.7388982500258, "count": 63698, "is_parallel": true, "self": 1200.7388982500258 }, "steps_from_proto": { "total": 116.16757355099412, "count": 63698, "is_parallel": true, "self": 23.5056570470947, "children": { "_process_rank_one_or_two_observation": { "total": 92.66191650389942, "count": 509584, "is_parallel": true, "self": 92.66191650389942 } } } } } } } } } } }, "trainer_advance": { "total": 688.3636838419025, "count": 63699, "self": 2.894726266882799, "children": { "process_trajectory": { "total": 123.21074955501672, "count": 63699, "self": 122.98778262001679, "children": { "RLTrainer._checkpoint": { "total": 0.22296693499993125, "count": 2, "self": 0.22296693499993125 } } }, "_update_policy": { "total": 562.2582080200029, "count": 443, "self": 367.99845530098673, "children": { "TorchPPOOptimizer.update": { "total": 194.2597527190162, "count": 22845, "self": 194.2597527190162 } } } } } } }, "trainer_threads": { "total": 1.0739995559561066e-06, "count": 1, "self": 1.0739995559561066e-06 }, "TrainerController._save_models": { "total": 0.09902434000014182, "count": 1, "self": 0.0013762280000264582, "children": { "RLTrainer._checkpoint": { "total": 0.09764811200011536, "count": 1, "self": 0.09764811200011536 } } } } } } }