{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.40372198820114136, "min": 0.3707912564277649, "max": 1.4556697607040405, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12163.3359375, "min": 11117.8046875, "max": 44159.19921875, "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": 0.48312079906463623, "min": -0.12045388668775558, "max": 0.5584696531295776, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 128.99325561523438, "min": -29.029386520385742, "max": 158.04690551757812, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01817130297422409, "min": 0.005104883573949337, "max": 0.6336129903793335, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.851737976074219, "min": 1.2506964206695557, "max": 150.16627502441406, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06641971863314716, "min": 0.06579809887279268, "max": 0.07317178811557905, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9962957794972075, "min": 0.505382156863624, "max": 1.0560386154102162, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01461627717007003, "min": 0.00025806463729980973, "max": 0.021735412348069565, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21924415755105045, "min": 0.003612904922197336, "max": 0.22101005170649538, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.514197495300002e-06, "min": 7.514197495300002e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011271296242950003, "min": 0.00011271296242950003, "max": 0.0036325057891648, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250470000000003, "min": 0.10250470000000003, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5375705000000004, "min": 1.3886848, "max": 2.6108352000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026021953000000006, "min": 0.00026021953000000006, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003903292950000001, "min": 0.003903292950000001, "max": 0.12110243648, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.015856942161917686, "min": 0.015856942161917686, "max": 0.6128483414649963, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.23785413801670074, "min": 0.22693490982055664, "max": 4.289938449859619, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 377.9078947368421, "min": 303.1443298969072, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28721.0, "min": 15984.0, "max": 33368.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5170026530822118, "min": -1.0000000521540642, "max": 1.6762309146603358, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 113.77519898116589, "min": -30.40620169788599, "max": 162.59439872205257, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5170026530822118, "min": -1.0000000521540642, "max": 1.6762309146603358, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 113.77519898116589, "min": -30.40620169788599, "max": 162.59439872205257, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06242571748249854, "min": 0.05358445981127983, "max": 13.34334221854806, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.68192881118739, "min": 4.68192881118739, "max": 213.49347549676895, "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": "1699561951", "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": "1699564167" }, "total": 2216.238286706, "count": 1, "self": 0.47654615500005093, "children": { "run_training.setup": { "total": 0.04511496999998599, "count": 1, "self": 0.04511496999998599 }, "TrainerController.start_learning": { "total": 2215.716625581, "count": 1, "self": 1.2220533800077646, "children": { "TrainerController._reset_env": { "total": 8.93151507399989, "count": 1, "self": 8.93151507399989 }, "TrainerController.advance": { "total": 2205.486150846992, "count": 63695, "self": 1.3049954610214627, "children": { "env_step": { "total": 1580.526663182951, "count": 63695, "self": 1453.0760863549822, "children": { "SubprocessEnvManager._take_step": { "total": 126.68077171797495, "count": 63695, "self": 4.621322425028893, "children": { "TorchPolicy.evaluate": { "total": 122.05944929294606, "count": 62558, "self": 122.05944929294606 } } }, "workers": { "total": 0.7698051099939676, "count": 63695, "self": 0.0, "children": { "worker_root": { "total": 2211.231235368969, "count": 63695, "is_parallel": true, "self": 867.8587928839845, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005095142000072883, "count": 1, "is_parallel": true, "self": 0.003562445000397929, "children": { "_process_rank_one_or_two_observation": { "total": 0.001532696999674954, "count": 8, "is_parallel": true, "self": 0.001532696999674954 } } }, "UnityEnvironment.step": { "total": 0.04986780800004453, "count": 1, "is_parallel": true, "self": 0.0006248610000056942, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004741630000353325, "count": 1, "is_parallel": true, "self": 0.0004741630000353325 }, "communicator.exchange": { "total": 0.04719653400002244, "count": 1, "is_parallel": true, "self": 0.04719653400002244 }, "steps_from_proto": { "total": 0.001572249999981068, "count": 1, "is_parallel": true, "self": 0.0003394589998606534, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012327910001204145, "count": 8, "is_parallel": true, "self": 0.0012327910001204145 } } } } } } }, "UnityEnvironment.step": { "total": 1343.3724424849845, "count": 63694, "is_parallel": true, "self": 34.690201781023006, "children": { "UnityEnvironment._generate_step_input": { "total": 23.850148585025636, "count": 63694, "is_parallel": true, "self": 23.850148585025636 }, "communicator.exchange": { "total": 1187.430589418954, "count": 63694, "is_parallel": true, "self": 1187.430589418954 }, "steps_from_proto": { "total": 97.40150269998185, "count": 63694, "is_parallel": true, "self": 18.943393323022065, "children": { "_process_rank_one_or_two_observation": { "total": 78.45810937695978, "count": 509552, "is_parallel": true, "self": 78.45810937695978 } } } } } } } } } } }, "trainer_advance": { "total": 623.6544922030193, "count": 63695, "self": 2.3886360759681793, "children": { "process_trajectory": { "total": 119.7939376970412, "count": 63695, "self": 119.58311027904165, "children": { "RLTrainer._checkpoint": { "total": 0.2108274179995533, "count": 2, "self": 0.2108274179995533 } } }, "_update_policy": { "total": 501.47191843000996, "count": 453, "self": 300.3981185300297, "children": { "TorchPPOOptimizer.update": { "total": 201.07379989998026, "count": 22788, "self": 201.07379989998026 } } } } } } }, "trainer_threads": { "total": 1.0600001587590668e-06, "count": 1, "self": 1.0600001587590668e-06 }, "TrainerController._save_models": { "total": 0.07690521999984412, "count": 1, "self": 0.0013572259995271452, "children": { "RLTrainer._checkpoint": { "total": 0.07554799400031698, "count": 1, "self": 0.07554799400031698 } } } } } } }