{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2902367115020752, "min": 0.2902367115020752, "max": 1.4471205472946167, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 8739.607421875, "min": 8739.607421875, "max": 43899.84765625, "count": 33 }, "Pyramids.Step.mean": { "value": 989931.0, "min": 29952.0, "max": 989931.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989931.0, "min": 29952.0, "max": 989931.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7491468191146851, "min": -0.08783175051212311, "max": 0.7491468191146851, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 221.74746704101562, "min": -21.079620361328125, "max": 221.74746704101562, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.022463684901595116, "min": 0.001055103144608438, "max": 0.5796311497688293, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.649250507354736, "min": 0.2859329581260681, "max": 137.37258911132812, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06569638026190834, "min": 0.06569638026190834, "max": 0.07456615001728878, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9197493236667167, "min": 0.48482350153706694, "max": 1.0896176799855597, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016082921049452296, "min": 0.0013029887808222607, "max": 0.016705714106224366, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22516089469233216, "min": 0.014332876589044868, "max": 0.2424649964685908, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.721625997585716e-06, "min": 7.721625997585716e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010810276396620002, "min": 0.00010810276396620002, "max": 0.0035089313303562995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10257384285714287, "min": 0.10257384285714287, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4360338000000001, "min": 1.3886848, "max": 2.5725594000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002671269014285715, "min": 0.0002671269014285715, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037397766200000008, "min": 0.0037397766200000008, "max": 0.11698740562999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013974836096167564, "min": 0.013663789257407188, "max": 0.6173111796379089, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1956477016210556, "min": 0.19129304587841034, "max": 4.321178436279297, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 253.41322314049586, "min": 249.6949152542373, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30663.0, "min": 15984.0, "max": 33473.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.73069834623669, "min": -1.0000000521540642, "max": 1.7327059619447105, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 211.1451982408762, "min": -30.99940161406994, "max": 211.1451982408762, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.73069834623669, "min": -1.0000000521540642, "max": 1.7327059619447105, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 211.1451982408762, "min": -30.99940161406994, "max": 211.1451982408762, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03643655400691252, "min": 0.03514016188186609, "max": 13.027768436819315, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.445259588843328, "min": 4.111398940178333, "max": 208.44429498910904, "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": "1684202149", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1684204601" }, "total": 2452.6500570870003, "count": 1, "self": 0.499612210000123, "children": { "run_training.setup": { "total": 0.04138785000009193, "count": 1, "self": 0.04138785000009193 }, "TrainerController.start_learning": { "total": 2452.109057027, "count": 1, "self": 1.4456424399818388, "children": { "TrainerController._reset_env": { "total": 3.892750583000179, "count": 1, "self": 3.892750583000179 }, "TrainerController.advance": { "total": 2446.669218941018, "count": 64358, "self": 1.4191847740448793, "children": { "env_step": { "total": 1790.128826315996, "count": 64358, "self": 1673.9071472999915, "children": { "SubprocessEnvManager._take_step": { "total": 115.40191625202237, "count": 64358, "self": 5.004032854044226, "children": { "TorchPolicy.evaluate": { "total": 110.39788339797815, "count": 62568, "self": 110.39788339797815 } } }, "workers": { "total": 0.8197627639822258, "count": 64358, "self": 0.0, "children": { "worker_root": { "total": 2446.47734888903, "count": 64358, "is_parallel": true, "self": 892.9067821479832, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002185217000032935, "count": 1, "is_parallel": true, "self": 0.0006347870000809053, "children": { "_process_rank_one_or_two_observation": { "total": 0.00155042999995203, "count": 8, "is_parallel": true, "self": 0.00155042999995203 } } }, "UnityEnvironment.step": { "total": 0.05385033600009592, "count": 1, "is_parallel": true, "self": 0.0005366340001273784, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004639830001451628, "count": 1, "is_parallel": true, "self": 0.0004639830001451628 }, "communicator.exchange": { "total": 0.05076844799987157, "count": 1, "is_parallel": true, "self": 0.05076844799987157 }, "steps_from_proto": { "total": 0.002081270999951812, "count": 1, "is_parallel": true, "self": 0.00041940399955819885, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016618670003936131, "count": 8, "is_parallel": true, "self": 0.0016618670003936131 } } } } } } }, "UnityEnvironment.step": { "total": 1553.5705667410468, "count": 64357, "is_parallel": true, "self": 33.59625722203509, "children": { "UnityEnvironment._generate_step_input": { "total": 25.477793304929037, "count": 64357, "is_parallel": true, "self": 25.477793304929037 }, "communicator.exchange": { "total": 1386.1793140780173, "count": 64357, "is_parallel": true, "self": 1386.1793140780173 }, "steps_from_proto": { "total": 108.31720213606536, "count": 64357, "is_parallel": true, "self": 22.654074116122047, "children": { "_process_rank_one_or_two_observation": { "total": 85.66312801994331, "count": 514856, "is_parallel": true, "self": 85.66312801994331 } } } } } } } } } } }, "trainer_advance": { "total": 655.121207850977, "count": 64358, "self": 2.7269371719899027, "children": { "process_trajectory": { "total": 117.80928907399107, "count": 64358, "self": 117.52016508099109, "children": { "RLTrainer._checkpoint": { "total": 0.2891239929999756, "count": 2, "self": 0.2891239929999756 } } }, "_update_policy": { "total": 534.5849816049961, "count": 454, "self": 342.2467206790177, "children": { "TorchPPOOptimizer.update": { "total": 192.33826092597837, "count": 22794, "self": 192.33826092597837 } } } } } } }, "trainer_threads": { "total": 1.02400008472614e-06, "count": 1, "self": 1.02400008472614e-06 }, "TrainerController._save_models": { "total": 0.10144403899994359, "count": 1, "self": 0.0013755109998783155, "children": { "RLTrainer._checkpoint": { "total": 0.10006852800006527, "count": 1, "self": 0.10006852800006527 } } } } } } }