{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.17355196177959442, "min": 0.16420860588550568, "max": 0.2072158306837082, "count": 26 }, "Pyramids.Policy.Entropy.sum": { "value": 5195.45166015625, "min": 739.3460693359375, "max": 6200.927734375, "count": 26 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 203.34640522875816, "min": 137.1818181818182, "max": 266.0869565217391, "count": 26 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31112.0, "min": 1509.0, "max": 31112.0, "count": 26 }, "Pyramids.Step.mean": { "value": 2999965.0, "min": 2249901.0, "max": 2999965.0, "count": 26 }, "Pyramids.Step.sum": { "value": 2999965.0, "min": 2249901.0, "max": 2999965.0, "count": 26 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8030513525009155, "min": 0.6866229176521301, "max": 0.8825000524520874, "count": 26 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 250.55201721191406, "min": 17.96554946899414, "max": 274.45751953125, "count": 26 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01156849879771471, "min": -0.007139449007809162, "max": 0.01156849879771471, "count": 26 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.6093716621398926, "min": -2.1703925132751465, "max": 3.6093716621398926, "count": 26 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7966535824771022, "min": 1.6988483163838586, "max": 1.8628181611949748, "count": 26 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 274.8879981189966, "min": 20.490999773144722, "max": 274.8879981189966, "count": 26 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7966535824771022, "min": 1.6988483163838586, "max": 1.8628181611949748, "count": 26 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 274.8879981189966, "min": 20.490999773144722, "max": 274.8879981189966, "count": 26 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0161147126172794, "min": 0.012873910875482992, "max": 0.022824993208885883, "count": 26 }, "Pyramids.Policy.RndReward.sum": { "value": 2.4655510304437485, "min": 0.14161301963031292, "max": 2.6762451415124815, "count": 26 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06950231084746995, "min": 0.0616434053129827, "max": 0.07306709795562859, "count": 26 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9730323518645794, "min": 0.0616434053129827, "max": 1.0867448678656255, "count": 26 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01704566014675601, "min": 0.01213806154600479, "max": 0.01704566014675601, "count": 26 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23863924205458414, "min": 0.012157515874908617, "max": 0.24767852623308834, "count": 26 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5459280561523882e-06, "min": 1.5459280561523882e-06, "max": 7.504397498536666e-05, "count": 26 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.1642992786133434e-05, "min": 2.1642992786133434e-05, "max": 0.0010285187571607666, "count": 26 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10051527619047619, "min": 0.10051527619047619, "max": 0.12501463333333332, "count": 26 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4072138666666667, "min": 0.12501463333333332, "max": 1.8224306000000001, "count": 26 }, "Pyramids.Policy.Beta.mean": { "value": 6.147609142857168e-05, "min": 6.147609142857168e-05, "max": 0.00250896187, "count": 26 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008606652800000036, "min": 0.0008606652800000036, "max": 0.034389639410000006, "count": 26 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007651600055396557, "min": 0.007641063537448645, "max": 0.00874959584325552, "count": 26 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10712239891290665, "min": 0.00874959584325552, "max": 0.12965339422225952, "count": 26 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 26 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 26 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1735006912", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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 --resume", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1735009761" }, "total": 2849.092937874, "count": 1, "self": 0.5527164740005901, "children": { "run_training.setup": { "total": 0.11786107599982643, "count": 1, "self": 0.11786107599982643 }, "TrainerController.start_learning": { "total": 2848.422360324, "count": 1, "self": 1.9139394270969206, "children": { "TrainerController._reset_env": { "total": 3.4482140979998803, "count": 1, "self": 3.4482140979998803 }, "TrainerController.advance": { "total": 2842.964544472902, "count": 49718, "self": 2.1399073789661998, "children": { "env_step": { "total": 2004.155540452828, "count": 49718, "self": 1878.0823433381347, "children": { "SubprocessEnvManager._take_step": { "total": 124.96388724586632, "count": 49718, "self": 5.3285741006684475, "children": { "TorchPolicy.evaluate": { "total": 119.63531314519787, "count": 47093, "self": 119.63531314519787 } } }, "workers": { "total": 1.1093098688270402, "count": 49718, "self": 0.0, "children": { "worker_root": { "total": 2842.76201507908, "count": 49718, "is_parallel": true, "self": 1102.1298034450574, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0033426230002078228, "count": 1, "is_parallel": true, "self": 0.0011192299998583621, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022233930003494606, "count": 8, "is_parallel": true, "self": 0.0022233930003494606 } } }, "UnityEnvironment.step": { "total": 0.059097385999848484, "count": 1, "is_parallel": true, "self": 0.0007673770014662296, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005476899996210705, "count": 1, "is_parallel": true, "self": 0.0005476899996210705 }, "communicator.exchange": { "total": 0.05564322299960622, "count": 1, "is_parallel": true, "self": 0.05564322299960622 }, "steps_from_proto": { "total": 0.0021390959991549607, "count": 1, "is_parallel": true, "self": 0.0004222169982313062, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017168790009236545, "count": 8, "is_parallel": true, "self": 0.0017168790009236545 } } } } } } }, "UnityEnvironment.step": { "total": 1740.6322116340225, "count": 49717, "is_parallel": true, "self": 37.806009343980804, "children": { "UnityEnvironment._generate_step_input": { "total": 22.703305782042662, "count": 49717, "is_parallel": true, "self": 22.703305782042662 }, "communicator.exchange": { "total": 1580.99651460513, "count": 49717, "is_parallel": true, "self": 1580.99651460513 }, "steps_from_proto": { "total": 99.12638190286907, "count": 49717, "is_parallel": true, "self": 21.274063288505204, "children": { "_process_rank_one_or_two_observation": { "total": 77.85231861436387, "count": 397736, "is_parallel": true, "self": 77.85231861436387 } } } } } } } } } } }, "trainer_advance": { "total": 836.6690966411079, "count": 49718, "self": 3.5754450272861504, "children": { "process_trajectory": { "total": 132.90481768981135, "count": 49718, "self": 132.64810448481057, "children": { "RLTrainer._checkpoint": { "total": 0.25671320500077854, "count": 2, "self": 0.25671320500077854 } } }, "_update_policy": { "total": 700.1888339240104, "count": 356, "self": 276.9183073091617, "children": { "TorchPPOOptimizer.update": { "total": 423.2705266148487, "count": 17124, "self": 423.2705266148487 } } } } } } }, "trainer_threads": { "total": 1.196000084746629e-06, "count": 1, "self": 1.196000084746629e-06 }, "TrainerController._save_models": { "total": 0.09566113000073528, "count": 1, "self": 0.0027113550022477284, "children": { "RLTrainer._checkpoint": { "total": 0.09294977499848756, "count": 1, "self": 0.09294977499848756 } } } } } } }