{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6845305562019348, "min": 0.5935690999031067, "max": 1.5117309093475342, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 20481.154296875, "min": 17778.58203125, "max": 45859.8671875, "count": 33 }, "Pyramids.Step.mean": { "value": 989997.0, "min": 29952.0, "max": 989997.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989997.0, "min": 29952.0, "max": 989997.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.22064973413944244, "min": -0.14155177772045135, "max": 0.22528311610221863, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 56.92763137817383, "min": -33.54777145385742, "max": 58.123043060302734, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.05479690805077553, "min": -0.00531613826751709, "max": 0.4511835277080536, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 14.137601852416992, "min": -1.3715636730194092, "max": 106.93049621582031, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07051529492517668, "min": 0.06562953495796094, "max": 0.07455276319791895, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9872141289524734, "min": 0.5028409036709365, "max": 1.0551122031967823, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.011475989040279097, "min": 0.00011528205691489219, "max": 0.02016021357838787, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.16066384656390736, "min": 0.0014986667398935985, "max": 0.16066384656390736, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.463797512100003e-06, "min": 7.463797512100003e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010449316516940004, "min": 0.00010449316516940004, "max": 0.0035068901310367, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248789999999999, "min": 0.10248789999999999, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4348306, "min": 1.3691136000000002, "max": 2.5689633, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002585412100000001, "min": 0.0002585412100000001, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003619576940000002, "min": 0.003619576940000002, "max": 0.11691943366999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013971245847642422, "min": 0.013971245847642422, "max": 0.6823915839195251, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.19559744000434875, "min": 0.19559744000434875, "max": 4.776741027832031, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 610.530612244898, "min": 583.2857142857143, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29916.0, "min": 15984.0, "max": 32348.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.6953509862021524, "min": -1.0000000521540642, "max": 1.0492530294827052, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 34.07219832390547, "min": -32.000001668930054, "max": 51.41339844465256, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.6953509862021524, "min": -1.0000000521540642, "max": 1.0492530294827052, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 34.07219832390547, "min": -32.000001668930054, "max": 51.41339844465256, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.08773033027786628, "min": 0.08760321725870254, "max": 14.721475295722485, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.298786183615448, "min": 4.292557645676425, "max": 235.54360473155975, "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": "1695247994", "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": "1695250132" }, "total": 2137.635178377, "count": 1, "self": 0.4808578080001098, "children": { "run_training.setup": { "total": 0.043554510999911145, "count": 1, "self": 0.043554510999911145 }, "TrainerController.start_learning": { "total": 2137.110766058, "count": 1, "self": 1.328336516942727, "children": { "TrainerController._reset_env": { "total": 4.187597221000033, "count": 1, "self": 4.187597221000033 }, "TrainerController.advance": { "total": 2131.4898552360573, "count": 63278, "self": 1.3883296090357362, "children": { "env_step": { "total": 1446.9183741360043, "count": 63278, "self": 1336.904682815093, "children": { "SubprocessEnvManager._take_step": { "total": 109.21892322698204, "count": 63278, "self": 4.716893894013992, "children": { "TorchPolicy.evaluate": { "total": 104.50202933296805, "count": 62561, "self": 104.50202933296805 } } }, "workers": { "total": 0.7947680939291786, "count": 63278, "self": 0.0, "children": { "worker_root": { "total": 2132.373026723988, "count": 63278, "is_parallel": true, "self": 906.6558495139591, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00174528200000168, "count": 1, "is_parallel": true, "self": 0.0005447769999591401, "children": { "_process_rank_one_or_two_observation": { "total": 0.00120050500004254, "count": 8, "is_parallel": true, "self": 0.00120050500004254 } } }, "UnityEnvironment.step": { "total": 0.0699050079999779, "count": 1, "is_parallel": true, "self": 0.0020669460000135587, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004893289999472472, "count": 1, "is_parallel": true, "self": 0.0004893289999472472 }, "communicator.exchange": { "total": 0.0646532319999551, "count": 1, "is_parallel": true, "self": 0.0646532319999551 }, "steps_from_proto": { "total": 0.002695501000061995, "count": 1, "is_parallel": true, "self": 0.0003571390002434782, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023383619998185168, "count": 8, "is_parallel": true, "self": 0.0023383619998185168 } } } } } } }, "UnityEnvironment.step": { "total": 1225.717177210029, "count": 63277, "is_parallel": true, "self": 34.375183154117394, "children": { "UnityEnvironment._generate_step_input": { "total": 23.509338538982774, "count": 63277, "is_parallel": true, "self": 23.509338538982774 }, "communicator.exchange": { "total": 1062.0632047359907, "count": 63277, "is_parallel": true, "self": 1062.0632047359907 }, "steps_from_proto": { "total": 105.76945078093809, "count": 63277, "is_parallel": true, "self": 20.634843610950384, "children": { "_process_rank_one_or_two_observation": { "total": 85.1346071699877, "count": 506216, "is_parallel": true, "self": 85.1346071699877 } } } } } } } } } } }, "trainer_advance": { "total": 683.1831514910173, "count": 63278, "self": 2.4365908959969147, "children": { "process_trajectory": { "total": 111.95430795501534, "count": 63278, "self": 111.73846351401517, "children": { "RLTrainer._checkpoint": { "total": 0.21584444100017208, "count": 2, "self": 0.21584444100017208 } } }, "_update_policy": { "total": 568.792252640005, "count": 440, "self": 370.5581742050224, "children": { "TorchPPOOptimizer.update": { "total": 198.23407843498262, "count": 22875, "self": 198.23407843498262 } } } } } } }, "trainer_threads": { "total": 8.930001058615744e-07, "count": 1, "self": 8.930001058615744e-07 }, "TrainerController._save_models": { "total": 0.10497619099987787, "count": 1, "self": 0.0013904809998166456, "children": { "RLTrainer._checkpoint": { "total": 0.10358571000006123, "count": 1, "self": 0.10358571000006123 } } } } } } }