{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5234447121620178, "min": 0.44178539514541626, "max": 1.2805911302566528, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15611.21484375, "min": 13232.3564453125, "max": 38848.01171875, "count": 33 }, "Pyramids.Step.mean": { "value": 989933.0, "min": 29952.0, "max": 989933.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989933.0, "min": 29952.0, "max": 989933.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3698161840438843, "min": -0.10520529001951218, "max": 0.4652939736843109, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 97.26165771484375, "min": -25.459680557250977, "max": 123.30290222167969, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.6486706137657166, "min": -0.3630850613117218, "max": 0.9557820558547974, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 170.60037231445312, "min": -93.11280822753906, "max": 230.34347534179688, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.03061083713805096, "min": 0.02714713000404161, "max": 0.038319045031557274, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.4591625570707644, "min": 0.26823331522090094, "max": 0.4732016403383265, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.046957996777362294, "min": 0.001488061693914787, "max": 0.05827856288912396, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.7043699516604344, "min": 0.016368678633062655, "max": 0.8158998804477354, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.5337574887799985e-06, "min": 7.5337574887799985e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011300636233169997, "min": 0.00011300636233169997, "max": 0.0033695470768177003, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251122, "min": 0.10251122, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5376683, "min": 1.3886848, "max": 2.5724715000000002, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002608708779999999, "min": 0.0002608708779999999, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003913063169999999, "min": 0.003913063169999999, "max": 0.11233591176999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.026244288310408592, "min": 0.026244288310408592, "max": 1.487569808959961, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.39366433024406433, "min": 0.3790101408958435, "max": 10.412988662719727, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 450.4925373134328, "min": 413.0135135135135, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30183.0, "min": 15984.0, "max": 34602.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3413970381678904, "min": -1.0000000521540642, "max": 1.532586637934049, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 91.21499859541655, "min": -30.391201697289944, "max": 114.94399784505367, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3413970381678904, "min": -1.0000000521540642, "max": 1.532586637934049, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 91.21499859541655, "min": -30.391201697289944, "max": 114.94399784505367, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.11943421701546279, "min": 0.11943421701546279, "max": 16.96426861733198, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 8.12152675705147, "min": 8.12152675705147, "max": 368.24541572481394, "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": "1787233461", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1787235695" }, "total": 2234.7899577800003, "count": 1, "self": 1.05437016300084, "children": { "run_training.setup": { "total": 0.026004407000073115, "count": 1, "self": 0.026004407000073115 }, "TrainerController.start_learning": { "total": 2233.7095832099994, "count": 1, "self": 1.5331191670675253, "children": { "TrainerController._reset_env": { "total": 2.2684573880001153, "count": 1, "self": 2.2684573880001153 }, "TrainerController.advance": { "total": 2229.771881671932, "count": 63625, "self": 1.6033390369138942, "children": { "env_step": { "total": 1808.7397675810716, "count": 63625, "self": 1643.700411362166, "children": { "SubprocessEnvManager._take_step": { "total": 164.13696902794072, "count": 63625, "self": 4.896677176001049, "children": { "TorchPolicy.evaluate": { "total": 159.24029185193967, "count": 62555, "self": 159.24029185193967 } } }, "workers": { "total": 0.9023871909648733, "count": 63625, "self": 0.0, "children": { "worker_root": { "total": 2227.5037970868884, "count": 63625, "is_parallel": true, "self": 710.1784162309345, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017740060002324753, "count": 1, "is_parallel": true, "self": 0.0005748110002059548, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011991950000265206, "count": 8, "is_parallel": true, "self": 0.0011991950000265206 } } }, "UnityEnvironment.step": { "total": 0.052282478000051924, "count": 1, "is_parallel": true, "self": 0.0006208939994394314, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004855460001635947, "count": 1, "is_parallel": true, "self": 0.0004855460001635947 }, "communicator.exchange": { "total": 0.04941679700004897, "count": 1, "is_parallel": true, "self": 0.04941679700004897 }, "steps_from_proto": { "total": 0.0017592410003999248, "count": 1, "is_parallel": true, "self": 0.00035192300038033864, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014073180000195862, "count": 8, "is_parallel": true, "self": 0.0014073180000195862 } } } } } } }, "UnityEnvironment.step": { "total": 1517.3253808559539, "count": 63624, "is_parallel": true, "self": 34.995367980086485, "children": { "UnityEnvironment._generate_step_input": { "total": 24.806526795038735, "count": 63624, "is_parallel": true, "self": 24.806526795038735 }, "communicator.exchange": { "total": 1342.1133428819312, "count": 63624, "is_parallel": true, "self": 1342.1133428819312 }, "steps_from_proto": { "total": 115.41014319889746, "count": 63624, "is_parallel": true, "self": 24.195799725801407, "children": { "_process_rank_one_or_two_observation": { "total": 91.21434347309605, "count": 508992, "is_parallel": true, "self": 91.21434347309605 } } } } } } } } } } }, "trainer_advance": { "total": 419.42877505394654, "count": 63625, "self": 2.9717405319220234, "children": { "process_trajectory": { "total": 113.48650814402117, "count": 63625, "self": 113.26241048302109, "children": { "RLTrainer._checkpoint": { "total": 0.2240976610000871, "count": 2, "self": 0.2240976610000871 } } }, "_update_policy": { "total": 302.97052637800334, "count": 451, "self": 225.78707360600492, "children": { "TorchPPOOptimizer.update": { "total": 77.18345277199842, "count": 5643, "self": 77.18345277199842 } } } } } } }, "trainer_threads": { "total": 1.1049996828660369e-06, "count": 1, "self": 1.1049996828660369e-06 }, "TrainerController._save_models": { "total": 0.1361238780000349, "count": 1, "self": 0.0013260310006444342, "children": { "RLTrainer._checkpoint": { "total": 0.13479784699939046, "count": 1, "self": 0.13479784699939046 } } } } } } }