{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.31167134642601013, "min": 0.289847195148468, "max": 1.5125924348831177, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9380.060546875, "min": 8778.8916015625, "max": 45886.00390625, "count": 33 }, "Pyramids.Step.mean": { "value": 989887.0, "min": 29952.0, "max": 989887.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989887.0, "min": 29952.0, "max": 989887.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5530117154121399, "min": -0.09105511754751205, "max": 0.5530117154121399, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 152.6312255859375, "min": -21.94428253173828, "max": 152.6312255859375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.005710777826607227, "min": 0.005338628776371479, "max": 0.3996799886226654, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.5761747360229492, "min": 1.4414297342300415, "max": 94.72415924072266, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06591394608687083, "min": 0.0657598286480232, "max": 0.07247299217140404, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9227952452161916, "min": 0.4931479327045462, "max": 1.0870948825710607, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015456281445287193, "min": 0.0003208501558051864, "max": 0.015456281445287193, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2163879402340207, "min": 0.0038502018696622373, "max": 0.2163879402340207, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.483876076835711e-06, "min": 7.483876076835711e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010477426507569995, "min": 0.00010477426507569995, "max": 0.003635452988182399, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1024945928571429, "min": 0.1024945928571429, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4349243000000005, "min": 1.3886848, "max": 2.6118176, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025920982642857135, "min": 0.00025920982642857135, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036289375699999986, "min": 0.0036289375699999986, "max": 0.12120057824, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009613236412405968, "min": 0.009613236412405968, "max": 0.4146565794944763, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13458530604839325, "min": 0.13458530604839325, "max": 2.9025959968566895, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 349.5952380952381, "min": 348.55913978494624, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29366.0, "min": 15984.0, "max": 34032.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5313166503217959, "min": -1.0000000521540642, "max": 1.5313166503217959, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 128.63059862703085, "min": -30.996801614761353, "max": 141.57919885218143, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5313166503217959, "min": -1.0000000521540642, "max": 1.5313166503217959, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 128.63059862703085, "min": -30.996801614761353, "max": 141.57919885218143, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03523873055954547, "min": 0.03523873055954547, "max": 8.696537014096975, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.9600533670018194, "min": 2.9600533670018194, "max": 139.1445922255516, "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": "1711644773", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1711646999" }, "total": 2226.2868554730003, "count": 1, "self": 0.8536973960008254, "children": { "run_training.setup": { "total": 0.05275534399993376, "count": 1, "self": 0.05275534399993376 }, "TrainerController.start_learning": { "total": 2225.3804027329998, "count": 1, "self": 1.4913657840438646, "children": { "TrainerController._reset_env": { "total": 2.9712654930000326, "count": 1, "self": 2.9712654930000326 }, "TrainerController.advance": { "total": 2220.7773488649564, "count": 63762, "self": 1.5403392740017807, "children": { "env_step": { "total": 1597.5624181099283, "count": 63762, "self": 1459.9735557809402, "children": { "SubprocessEnvManager._take_step": { "total": 136.70036855100443, "count": 63762, "self": 4.878827015959132, "children": { "TorchPolicy.evaluate": { "total": 131.8215415350453, "count": 62551, "self": 131.8215415350453 } } }, "workers": { "total": 0.8884937779837401, "count": 63762, "self": 0.0, "children": { "worker_root": { "total": 2219.847435752019, "count": 63762, "is_parallel": true, "self": 886.2319080629779, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005078248000017993, "count": 1, "is_parallel": true, "self": 0.0035029829999757567, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015752650000422364, "count": 8, "is_parallel": true, "self": 0.0015752650000422364 } } }, "UnityEnvironment.step": { "total": 0.05220764600005623, "count": 1, "is_parallel": true, "self": 0.0006847550000657066, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005846540000220557, "count": 1, "is_parallel": true, "self": 0.0005846540000220557 }, "communicator.exchange": { "total": 0.04897885899993071, "count": 1, "is_parallel": true, "self": 0.04897885899993071 }, "steps_from_proto": { "total": 0.001959378000037759, "count": 1, "is_parallel": true, "self": 0.00047427900005914125, "children": { "_process_rank_one_or_two_observation": { "total": 0.001485098999978618, "count": 8, "is_parallel": true, "self": 0.001485098999978618 } } } } } } }, "UnityEnvironment.step": { "total": 1333.615527689041, "count": 63761, "is_parallel": true, "self": 35.572326158903934, "children": { "UnityEnvironment._generate_step_input": { "total": 25.59172798907889, "count": 63761, "is_parallel": true, "self": 25.59172798907889 }, "communicator.exchange": { "total": 1166.7417469450206, "count": 63761, "is_parallel": true, "self": 1166.7417469450206 }, "steps_from_proto": { "total": 105.70972659603774, "count": 63761, "is_parallel": true, "self": 21.672286620945897, "children": { "_process_rank_one_or_two_observation": { "total": 84.03743997509184, "count": 510088, "is_parallel": true, "self": 84.03743997509184 } } } } } } } } } } }, "trainer_advance": { "total": 621.6745914810263, "count": 63762, "self": 2.925004569041903, "children": { "process_trajectory": { "total": 131.15720408898244, "count": 63762, "self": 130.84482015698234, "children": { "RLTrainer._checkpoint": { "total": 0.3123839320001025, "count": 2, "self": 0.3123839320001025 } } }, "_update_policy": { "total": 487.5923828230019, "count": 457, "self": 284.965492988963, "children": { "TorchPPOOptimizer.update": { "total": 202.62688983403893, "count": 22785, "self": 202.62688983403893 } } } } } } }, "trainer_threads": { "total": 1.909999809868168e-06, "count": 1, "self": 1.909999809868168e-06 }, "TrainerController._save_models": { "total": 0.14042068099979588, "count": 1, "self": 0.0023180459998002334, "children": { "RLTrainer._checkpoint": { "total": 0.13810263499999564, "count": 1, "self": 0.13810263499999564 } } } } } } }