{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.7259551286697388, "min": 0.706507682800293, "max": 1.4525808095932007, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 21813.5, "min": 21070.884765625, "max": 44065.4921875, "count": 33 }, "Pyramids.Step.mean": { "value": 989971.0, "min": 29952.0, "max": 989971.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989971.0, "min": 29952.0, "max": 989971.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.27198728919029236, "min": -0.10689862072467804, "max": 0.34591540694236755, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 69.9007339477539, "min": -25.655668258666992, "max": 89.24617767333984, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.1284852772951126, "min": 0.016058355569839478, "max": 0.6301138997077942, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 33.02071762084961, "min": 3.9021804332733154, "max": 149.3369903564453, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06735436232152059, "min": 0.0626776327117159, "max": 0.07317206777537803, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9429610725012882, "min": 0.45986074512946856, "max": 1.0898411615926307, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012549591998082808, "min": 8.734140113184621e-05, "max": 0.03127210894639013, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1756942879731593, "min": 0.001222779615845847, "max": 0.2189047626247309, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.321597559500001e-06, "min": 7.321597559500001e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.000102502365833, "min": 0.000102502365833, "max": 0.003259602213466, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10244050000000002, "min": 0.10244050000000002, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4341670000000002, "min": 1.3691136000000002, "max": 2.3865339999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025380594999999996, "min": 0.00025380594999999996, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035532832999999996, "min": 0.0035532832999999996, "max": 0.1086747466, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01599080301821232, "min": 0.01599080301821232, "max": 0.6596052050590515, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.22387123107910156, "min": 0.22387123107910156, "max": 4.617236614227295, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 639.0204081632653, "min": 497.65, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31312.0, "min": 15984.0, "max": 32163.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.7077632284894282, "min": -1.0000000521540642, "max": 1.0688866348316273, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 34.68039819598198, "min": -32.000001668930054, "max": 64.13319808989763, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.7077632284894282, "min": -1.0000000521540642, "max": 1.0688866348316273, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 34.68039819598198, "min": -32.000001668930054, "max": 64.13319808989763, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.10806346305988121, "min": 0.09658229661969624, "max": 15.742426561191678, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.295109689934179, "min": 5.295109689934179, "max": 251.87882497906685, "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": "1681763080", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "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": "1681765005" }, "total": 1925.0731090890001, "count": 1, "self": 0.4379680679999183, "children": { "run_training.setup": { "total": 0.1099432240000624, "count": 1, "self": 0.1099432240000624 }, "TrainerController.start_learning": { "total": 1924.5251977970001, "count": 1, "self": 1.2460167649760479, "children": { "TrainerController._reset_env": { "total": 3.7412921630000255, "count": 1, "self": 3.7412921630000255 }, "TrainerController.advance": { "total": 1919.4453341050241, "count": 63250, "self": 1.3029965781054216, "children": { "env_step": { "total": 1319.7388196769475, "count": 63250, "self": 1219.1260804229742, "children": { "SubprocessEnvManager._take_step": { "total": 99.85000720303037, "count": 63250, "self": 4.492595957978665, "children": { "TorchPolicy.evaluate": { "total": 95.35741124505171, "count": 62550, "self": 95.35741124505171 } } }, "workers": { "total": 0.7627320509429865, "count": 63250, "self": 0.0, "children": { "worker_root": { "total": 1920.0863427850002, "count": 63250, "is_parallel": true, "self": 803.7980730899474, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0016529360000276938, "count": 1, "is_parallel": true, "self": 0.0005146870000771742, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011382489999505196, "count": 8, "is_parallel": true, "self": 0.0011382489999505196 } } }, "UnityEnvironment.step": { "total": 0.04449640300003921, "count": 1, "is_parallel": true, "self": 0.0005173290003313014, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004624389998753031, "count": 1, "is_parallel": true, "self": 0.0004624389998753031 }, "communicator.exchange": { "total": 0.041957454999874244, "count": 1, "is_parallel": true, "self": 0.041957454999874244 }, "steps_from_proto": { "total": 0.00155917999995836, "count": 1, "is_parallel": true, "self": 0.00034795200008375105, "children": { "_process_rank_one_or_two_observation": { "total": 0.001211227999874609, "count": 8, "is_parallel": true, "self": 0.001211227999874609 } } } } } } }, "UnityEnvironment.step": { "total": 1116.2882696950528, "count": 63249, "is_parallel": true, "self": 31.201497553118543, "children": { "UnityEnvironment._generate_step_input": { "total": 21.891460788979657, "count": 63249, "is_parallel": true, "self": 21.891460788979657 }, "communicator.exchange": { "total": 973.5124761659588, "count": 63249, "is_parallel": true, "self": 973.5124761659588 }, "steps_from_proto": { "total": 89.68283518699582, "count": 63249, "is_parallel": true, "self": 18.735588352964214, "children": { "_process_rank_one_or_two_observation": { "total": 70.9472468340316, "count": 505992, "is_parallel": true, "self": 70.9472468340316 } } } } } } } } } } }, "trainer_advance": { "total": 598.4035178499712, "count": 63250, "self": 2.2627071179792893, "children": { "process_trajectory": { "total": 99.21298119299308, "count": 63250, "self": 99.01596679199315, "children": { "RLTrainer._checkpoint": { "total": 0.19701440099993306, "count": 2, "self": 0.19701440099993306 } } }, "_update_policy": { "total": 496.9278295389988, "count": 434, "self": 317.42427379801006, "children": { "TorchPPOOptimizer.update": { "total": 179.50355574098876, "count": 22881, "self": 179.50355574098876 } } } } } } }, "trainer_threads": { "total": 9.149998732027598e-07, "count": 1, "self": 9.149998732027598e-07 }, "TrainerController._save_models": { "total": 0.09255384900006902, "count": 1, "self": 0.0014217539996934647, "children": { "RLTrainer._checkpoint": { "total": 0.09113209500037556, "count": 1, "self": 0.09113209500037556 } } } } } } }