{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.23797956109046936, "min": 0.23797956109046936, "max": 1.3762589693069458, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 7120.3486328125, "min": 7120.3486328125, "max": 41750.19140625, "count": 33 }, "Pyramids.Step.mean": { "value": 989884.0, "min": 29952.0, "max": 989884.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989884.0, "min": 29952.0, "max": 989884.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7378281354904175, "min": -0.0958128571510315, "max": 0.7378281354904175, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 216.92147827148438, "min": -22.899272918701172, "max": 216.92147827148438, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.015895385295152664, "min": -0.013426374644041061, "max": 0.3426330089569092, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.673243045806885, "min": -3.638547420501709, "max": 82.57455444335938, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06940749172090796, "min": 0.06501277138001979, "max": 0.07472376028348182, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9717048840927115, "min": 0.5030254713348622, "max": 1.0754707626160689, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014973445392873453, "min": 9.112080120959689e-05, "max": 0.016006233586397554, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20962823550022833, "min": 0.0011845704157247595, "max": 0.23748045564085865, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.533118917564294e-06, "min": 7.533118917564294e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010546366484590011, "min": 0.00010546366484590011, "max": 0.0036330460889846994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251100714285717, "min": 0.10251100714285717, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4351541000000003, "min": 1.3886848, "max": 2.6110153000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026084961357142886, "min": 0.00026084961357142886, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036518945900000043, "min": 0.0036518945900000043, "max": 0.12112042847000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012284232303500175, "min": 0.012209154665470123, "max": 0.4757020175457001, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17197924852371216, "min": 0.17092816531658173, "max": 3.329914093017578, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 254.1764705882353, "min": 254.1764705882353, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30247.0, "min": 15984.0, "max": 33412.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7290117544035952, "min": -1.0000000521540642, "max": 1.7290117544035952, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 205.75239877402782, "min": -30.576001703739166, "max": 205.75239877402782, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7290117544035952, "min": -1.0000000521540642, "max": 1.7290117544035952, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 205.75239877402782, "min": -30.576001703739166, "max": 205.75239877402782, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03253405797992297, "min": 0.03253405797992297, "max": 9.337946828454733, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.8715528996108333, "min": 3.6960685305966763, "max": 149.40714925527573, "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": "1747927135", "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": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1747930312" }, "total": 3176.691407279, "count": 1, "self": 0.5875935489998483, "children": { "run_training.setup": { "total": 0.03733900700012782, "count": 1, "self": 0.03733900700012782 }, "TrainerController.start_learning": { "total": 3176.066474723, "count": 1, "self": 2.3928807590568795, "children": { "TrainerController._reset_env": { "total": 3.9162066349999805, "count": 1, "self": 3.9162066349999805 }, "TrainerController.advance": { "total": 3169.6721310889425, "count": 64202, "self": 2.563738766865754, "children": { "env_step": { "total": 2132.544880050033, "count": 64202, "self": 1973.5777629570339, "children": { "SubprocessEnvManager._take_step": { "total": 157.62763653499815, "count": 64202, "self": 6.962649240043902, "children": { "TorchPolicy.evaluate": { "total": 150.66498729495424, "count": 62557, "self": 150.66498729495424 } } }, "workers": { "total": 1.3394805580010143, "count": 64202, "self": 0.0, "children": { "worker_root": { "total": 3168.8218247099835, "count": 64202, "is_parallel": true, "self": 1365.5821874760165, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003908693000084895, "count": 1, "is_parallel": true, "self": 0.001402389000304538, "children": { "_process_rank_one_or_two_observation": { "total": 0.002506303999780357, "count": 8, "is_parallel": true, "self": 0.002506303999780357 } } }, "UnityEnvironment.step": { "total": 0.1635672100001102, "count": 1, "is_parallel": true, "self": 0.0006251830000110203, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005295720000049187, "count": 1, "is_parallel": true, "self": 0.0005295720000049187 }, "communicator.exchange": { "total": 0.16065895200017621, "count": 1, "is_parallel": true, "self": 0.16065895200017621 }, "steps_from_proto": { "total": 0.0017535029999180551, "count": 1, "is_parallel": true, "self": 0.00035826799944516097, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013952350004728942, "count": 8, "is_parallel": true, "self": 0.0013952350004728942 } } } } } } }, "UnityEnvironment.step": { "total": 1803.239637233967, "count": 64201, "is_parallel": true, "self": 44.713814938863834, "children": { "UnityEnvironment._generate_step_input": { "total": 31.007144592068016, "count": 64201, "is_parallel": true, "self": 31.007144592068016 }, "communicator.exchange": { "total": 1600.1586063111117, "count": 64201, "is_parallel": true, "self": 1600.1586063111117 }, "steps_from_proto": { "total": 127.36007139192338, "count": 64201, "is_parallel": true, "self": 27.975875163406272, "children": { "_process_rank_one_or_two_observation": { "total": 99.38419622851711, "count": 513608, "is_parallel": true, "self": 99.38419622851711 } } } } } } } } } } }, "trainer_advance": { "total": 1034.5635122720437, "count": 64202, "self": 4.5667505860353685, "children": { "process_trajectory": { "total": 162.054659459003, "count": 64202, "self": 161.7196996410023, "children": { "RLTrainer._checkpoint": { "total": 0.33495981800069785, "count": 2, "self": 0.33495981800069785 } } }, "_update_policy": { "total": 867.9421022270053, "count": 455, "self": 352.2108937890373, "children": { "TorchPPOOptimizer.update": { "total": 515.731208437968, "count": 22800, "self": 515.731208437968 } } } } } } }, "trainer_threads": { "total": 1.1100000847363845e-06, "count": 1, "self": 1.1100000847363845e-06 }, "TrainerController._save_models": { "total": 0.08525513000040519, "count": 1, "self": 0.0017056670003512409, "children": { "RLTrainer._checkpoint": { "total": 0.08354946300005395, "count": 1, "self": 0.08354946300005395 } } } } } } }