{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2931484580039978, "min": 0.2665848433971405, "max": 1.4609137773513794, "count": 56 }, "Pyramids.Policy.Entropy.sum": { "value": 8860.119140625, "min": 7989.0146484375, "max": 44318.28125, "count": 56 }, "Pyramids.Step.mean": { "value": 1679911.0, "min": 29952.0, "max": 1679911.0, "count": 56 }, "Pyramids.Step.sum": { "value": 1679911.0, "min": 29952.0, "max": 1679911.0, "count": 56 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7794104814529419, "min": -0.11826352030038834, "max": 0.7794104814529419, "count": 56 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 233.82315063476562, "min": -28.38324546813965, "max": 233.82315063476562, "count": 56 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.004252551589161158, "min": -0.011837872676551342, "max": 0.2804987132549286, "count": 56 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.2757654190063477, "min": -3.5040102005004883, "max": 67.60018920898438, "count": 56 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07077525041296169, "min": 0.0639679330717107, "max": 0.07478135623305537, "count": 56 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9908535057814636, "min": 0.5014895615668034, "max": 1.0870989519510958, "count": 56 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015636562794541186, "min": 0.00033381134784784546, "max": 0.017174676580387835, "count": 56 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2189118791235766, "min": 0.004005736174174146, "max": 0.2404454721254297, "count": 56 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00013353511263117145, "min": 0.00013353511263117145, "max": 0.00029838354339596195, "count": 56 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0018694915768364003, "min": 0.0018694915768364003, "max": 0.003927338390887233, "count": 56 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.14451168571428571, "min": 0.14451168571428571, "max": 0.19946118095238097, "count": 56 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.0231636, "min": 1.3962282666666668, "max": 2.752448666666667, "count": 56 }, "Pyramids.Policy.Beta.mean": { "value": 0.004456717402857143, "min": 0.004456717402857143, "max": 0.009946171977142856, "count": 56 }, "Pyramids.Policy.Beta.sum": { "value": 0.06239404364000001, "min": 0.06239404364000001, "max": 0.13092036539000002, "count": 56 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007925021462142467, "min": 0.007855609059333801, "max": 0.4275193214416504, "count": 56 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11095030605792999, "min": 0.10997852683067322, "max": 2.9926352500915527, "count": 56 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 238.23846153846154, "min": 238.23846153846154, "max": 999.0, "count": 56 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30971.0, "min": 15984.0, "max": 33164.0, "count": 56 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7309876807607136, "min": -1.0000000521540642, "max": 1.756549989680449, "count": 56 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 225.02839849889278, "min": -30.998601615428925, "max": 225.02839849889278, "count": 56 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7309876807607136, "min": -1.0000000521540642, "max": 1.756549989680449, "count": 56 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 225.02839849889278, "min": -30.998601615428925, "max": 225.02839849889278, "count": 56 }, "Pyramids.Policy.RndReward.mean": { "value": 0.019866735798104156, "min": 0.01971790480887042, "max": 8.419557301327586, "count": 56 }, "Pyramids.Policy.RndReward.sum": { "value": 2.5826756537535402, "min": 2.3661485770644504, "max": 134.71291682124138, "count": 56 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 56 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 56 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1744650376", "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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1744656863" }, "total": 6487.150673892, "count": 1, "self": 0.8525136649996057, "children": { "run_training.setup": { "total": 0.037207108999837146, "count": 1, "self": 0.037207108999837146 }, "TrainerController.start_learning": { "total": 6486.2609531180005, "count": 1, "self": 4.41639423505876, "children": { "TrainerController._reset_env": { "total": 2.798245260000158, "count": 1, "self": 2.798245260000158 }, "TrainerController.advance": { "total": 6479.045734166942, "count": 109155, "self": 4.449014292867105, "children": { "env_step": { "total": 4443.289429718136, "count": 109155, "self": 4137.828989645221, "children": { "SubprocessEnvManager._take_step": { "total": 302.95726527005127, "count": 109155, "self": 14.238312247149452, "children": { "TorchPolicy.evaluate": { "total": 288.7189530229018, "count": 105750, "self": 288.7189530229018 } } }, "workers": { "total": 2.5031748028632137, "count": 109155, "self": 0.0, "children": { "worker_root": { "total": 6470.257814337056, "count": 109155, "is_parallel": true, "self": 2656.194395836025, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0031115780000163795, "count": 1, "is_parallel": true, "self": 0.0010544669994487776, "children": { "_process_rank_one_or_two_observation": { "total": 0.002057111000567602, "count": 8, "is_parallel": true, "self": 0.002057111000567602 } } }, "UnityEnvironment.step": { "total": 0.0706088549998185, "count": 1, "is_parallel": true, "self": 0.0006806690000757953, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005332639998414379, "count": 1, "is_parallel": true, "self": 0.0005332639998414379 }, "communicator.exchange": { "total": 0.06743210499985253, "count": 1, "is_parallel": true, "self": 0.06743210499985253 }, "steps_from_proto": { "total": 0.0019628170000487444, "count": 1, "is_parallel": true, "self": 0.0004130190002342715, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015497979998144729, "count": 8, "is_parallel": true, "self": 0.0015497979998144729 } } } } } } }, "UnityEnvironment.step": { "total": 3814.063418501031, "count": 109154, "is_parallel": true, "self": 81.4590992737476, "children": { "UnityEnvironment._generate_step_input": { "total": 54.88486883310475, "count": 109154, "is_parallel": true, "self": 54.88486883310475 }, "communicator.exchange": { "total": 3448.7404790420355, "count": 109154, "is_parallel": true, "self": 3448.7404790420355 }, "steps_from_proto": { "total": 228.9789713521427, "count": 109154, "is_parallel": true, "self": 49.94616121683816, "children": { "_process_rank_one_or_two_observation": { "total": 179.03281013530454, "count": 873232, "is_parallel": true, "self": 179.03281013530454 } } } } } } } } } } }, "trainer_advance": { "total": 2031.3072901559385, "count": 109155, "self": 8.581635675024245, "children": { "process_trajectory": { "total": 306.9528613519294, "count": 109155, "self": 306.50651188792904, "children": { "RLTrainer._checkpoint": { "total": 0.44634946400037734, "count": 3, "self": 0.44634946400037734 } } }, "_update_policy": { "total": 1715.7727931289849, "count": 774, "self": 660.4967012699508, "children": { "TorchPPOOptimizer.update": { "total": 1055.276091859034, "count": 38572, "self": 1055.276091859034 } } } } } } }, "trainer_threads": { "total": 2.3299999156733975e-06, "count": 1, "self": 2.3299999156733975e-06 }, "TrainerController._save_models": { "total": 0.0005771260002802592, "count": 1, "self": 4.054999953950755e-05, "children": { "RLTrainer._checkpoint": { "total": 0.0005365760007407516, "count": 1, "self": 0.0005365760007407516 } } } } } } }