{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5280116200447083, "min": 0.5280116200447083, "max": 1.3660978078842163, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15907.93359375, "min": 15907.93359375, "max": 41441.94140625, "count": 33 }, "Pyramids.Step.mean": { "value": 989970.0, "min": 29952.0, "max": 989970.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989970.0, "min": 29952.0, "max": 989970.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.053314488381147385, "min": -0.11195410788059235, "max": 0.18728280067443848, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 13.115364074707031, "min": -27.092893600463867, "max": 44.386024475097656, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.013439892791211605, "min": 0.011330770328640938, "max": 0.49259132146835327, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.306213617324829, "min": 2.810030937194824, "max": 116.744140625, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06902576163933162, "min": 0.06497942256949045, "max": 0.07245671332323288, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9663606629506426, "min": 0.5071969932626301, "max": 1.035204475665666, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.008374417846084123, "min": 8.181983830072212e-05, "max": 0.012613309092369586, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.11724184984517773, "min": 0.0011454777362101096, "max": 0.14626419761075607, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.361240403428575e-06, "min": 7.361240403428575e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010305736564800005, "min": 0.00010305736564800005, "max": 0.0033817808727397993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10245371428571429, "min": 0.10245371428571429, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.434352, "min": 1.3886848, "max": 2.5272602000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025512605714285734, "min": 0.00025512605714285734, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035717648000000027, "min": 0.0035717648000000027, "max": 0.11275329398, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01734367571771145, "min": 0.017181305214762688, "max": 0.7163676619529724, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.24281147122383118, "min": 0.24053826928138733, "max": 5.014573574066162, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 811.7222222222222, "min": 728.6666666666666, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29222.0, "min": 15984.0, "max": 32626.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.29912773540450466, "min": -1.0000000521540642, "max": 0.4276139114138692, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 10.768598474562168, "min": -31.99920167028904, "max": 18.387398190796375, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.29912773540450466, "min": -1.0000000521540642, "max": 0.4276139114138692, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 10.768598474562168, "min": -31.99920167028904, "max": 18.387398190796375, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.14433983834492714, "min": 0.1334694708388862, "max": 14.515450745821, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.1962341804173775, "min": 4.871754383377265, "max": 232.247211933136, "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": "1691031744", "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": "1691034019" }, "total": 2275.55502193, "count": 1, "self": 0.4915565409996816, "children": { "run_training.setup": { "total": 0.06689123799998242, "count": 1, "self": 0.06689123799998242 }, "TrainerController.start_learning": { "total": 2274.996574151, "count": 1, "self": 1.6048196840069977, "children": { "TrainerController._reset_env": { "total": 5.762007885000003, "count": 1, "self": 5.762007885000003 }, "TrainerController.advance": { "total": 2267.533115889993, "count": 63214, "self": 1.676050937002401, "children": { "env_step": { "total": 1568.596108532004, "count": 63214, "self": 1443.6516747410005, "children": { "SubprocessEnvManager._take_step": { "total": 123.96927312102986, "count": 63214, "self": 5.2763418730484375, "children": { "TorchPolicy.evaluate": { "total": 118.69293124798142, "count": 62563, "self": 118.69293124798142 } } }, "workers": { "total": 0.9751606699738318, "count": 63214, "self": 0.0, "children": { "worker_root": { "total": 2269.3755010989835, "count": 63214, "is_parallel": true, "self": 954.8299821089788, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007158458000020573, "count": 1, "is_parallel": true, "self": 0.005704014000116331, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014544439999042424, "count": 8, "is_parallel": true, "self": 0.0014544439999042424 } } }, "UnityEnvironment.step": { "total": 0.05180290399999876, "count": 1, "is_parallel": true, "self": 0.0005849090000253909, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005819109999833927, "count": 1, "is_parallel": true, "self": 0.0005819109999833927 }, "communicator.exchange": { "total": 0.04866447000000562, "count": 1, "is_parallel": true, "self": 0.04866447000000562 }, "steps_from_proto": { "total": 0.0019716139999843563, "count": 1, "is_parallel": true, "self": 0.0003828699999814944, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015887440000028619, "count": 8, "is_parallel": true, "self": 0.0015887440000028619 } } } } } } }, "UnityEnvironment.step": { "total": 1314.5455189900047, "count": 63213, "is_parallel": true, "self": 36.25944546500364, "children": { "UnityEnvironment._generate_step_input": { "total": 25.742639747044052, "count": 63213, "is_parallel": true, "self": 25.742639747044052 }, "communicator.exchange": { "total": 1135.5403156469388, "count": 63213, "is_parallel": true, "self": 1135.5403156469388 }, "steps_from_proto": { "total": 117.00311813101817, "count": 63213, "is_parallel": true, "self": 23.14488491912067, "children": { "_process_rank_one_or_two_observation": { "total": 93.8582332118975, "count": 505704, "is_parallel": true, "self": 93.8582332118975 } } } } } } } } } } }, "trainer_advance": { "total": 697.2609564209864, "count": 63214, "self": 2.866747943014957, "children": { "process_trajectory": { "total": 120.90293706697315, "count": 63214, "self": 120.68252031297305, "children": { "RLTrainer._checkpoint": { "total": 0.22041675400009808, "count": 2, "self": 0.22041675400009808 } } }, "_update_policy": { "total": 573.4912714109983, "count": 439, "self": 376.47104737696566, "children": { "TorchPPOOptimizer.update": { "total": 197.02022403403257, "count": 22875, "self": 197.02022403403257 } } } } } } }, "trainer_threads": { "total": 9.99999883788405e-07, "count": 1, "self": 9.99999883788405e-07 }, "TrainerController._save_models": { "total": 0.09662969200007865, "count": 1, "self": 0.001425008000296657, "children": { "RLTrainer._checkpoint": { "total": 0.09520468399978199, "count": 1, "self": 0.09520468399978199 } } } } } } }