{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.566974937915802, "min": 0.566974937915802, "max": 1.4878919124603271, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 17063.677734375, "min": 17063.677734375, "max": 45136.6875, "count": 33 }, "Pyramids.Step.mean": { "value": 989912.0, "min": 29952.0, "max": 989912.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989912.0, "min": 29952.0, "max": 989912.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4658448398113251, "min": -0.10962673276662827, "max": 0.4658448398113251, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 124.84642028808594, "min": -26.420042037963867, "max": 124.84642028808594, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 8.818729838822037e-05, "min": -0.012685851193964481, "max": 0.29153934121131897, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.02363419532775879, "min": -3.2222061157226562, "max": 69.0948257446289, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06546331636907, "min": 0.06490303629316999, "max": 0.07337082125249143, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.91648642916698, "min": 0.4884220254851703, "max": 1.0399216895360344, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015518705902477016, "min": 0.0004439950287837023, "max": 0.015518705902477016, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21726188263467822, "min": 0.00577193537418813, "max": 0.22561648765501255, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.280733287407141e-06, "min": 7.280733287407141e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010193026602369998, "min": 0.00010193026602369998, "max": 0.0032580623139792995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10242687857142856, "min": 0.10242687857142856, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4339762999999999, "min": 1.3886848, "max": 2.4421624, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025244516928571426, "min": 0.00025244516928571426, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035342323699999994, "min": 0.0035342323699999994, "max": 0.10862346793000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009604522958397865, "min": 0.009604522958397865, "max": 0.3958647847175598, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1344633251428604, "min": 0.1344633251428604, "max": 2.7710535526275635, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 433.3, "min": 417.65277777777777, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30331.0, "min": 15984.0, "max": 32573.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4530647642595667, "min": -1.0000000521540642, "max": 1.4530647642595667, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 103.16759826242924, "min": -30.99840161204338, "max": 103.16759826242924, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4530647642595667, "min": -1.0000000521540642, "max": 1.4530647642595667, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 103.16759826242924, "min": -30.99840161204338, "max": 103.16759826242924, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04285186388969264, "min": 0.04263482952669171, "max": 8.186559871770442, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.0424823361681774, "min": 3.0270728963951115, "max": 130.98495794832706, "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": "1680777219", "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": "1680779297" }, "total": 2078.667990549, "count": 1, "self": 0.44317462100025296, "children": { "run_training.setup": { "total": 0.1050111099998503, "count": 1, "self": 0.1050111099998503 }, "TrainerController.start_learning": { "total": 2078.119804818, "count": 1, "self": 1.428423256037604, "children": { "TrainerController._reset_env": { "total": 3.6331771420000223, "count": 1, "self": 3.6331771420000223 }, "TrainerController.advance": { "total": 2072.958720927963, "count": 63548, "self": 1.5146966499969494, "children": { "env_step": { "total": 1458.7550160150995, "count": 63548, "self": 1348.771459305151, "children": { "SubprocessEnvManager._take_step": { "total": 109.10004711194233, "count": 63548, "self": 4.911477132907294, "children": { "TorchPolicy.evaluate": { "total": 104.18856997903504, "count": 62562, "self": 104.18856997903504 } } }, "workers": { "total": 0.8835095980061851, "count": 63548, "self": 0.0, "children": { "worker_root": { "total": 2073.127712743932, "count": 63548, "is_parallel": true, "self": 839.8836317158075, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017176950000248326, "count": 1, "is_parallel": true, "self": 0.0005520130002878432, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011656819997369894, "count": 8, "is_parallel": true, "self": 0.0011656819997369894 } } }, "UnityEnvironment.step": { "total": 0.04648295100014366, "count": 1, "is_parallel": true, "self": 0.0007246309996844502, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005319270003383281, "count": 1, "is_parallel": true, "self": 0.0005319270003383281 }, "communicator.exchange": { "total": 0.04354032300034305, "count": 1, "is_parallel": true, "self": 0.04354032300034305 }, "steps_from_proto": { "total": 0.0016860699997778283, "count": 1, "is_parallel": true, "self": 0.0003676539995467465, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013184160002310819, "count": 8, "is_parallel": true, "self": 0.0013184160002310819 } } } } } } }, "UnityEnvironment.step": { "total": 1233.2440810281246, "count": 63547, "is_parallel": true, "self": 32.21417822609874, "children": { "UnityEnvironment._generate_step_input": { "total": 24.046735874936985, "count": 63547, "is_parallel": true, "self": 24.046735874936985 }, "communicator.exchange": { "total": 1079.654197613063, "count": 63547, "is_parallel": true, "self": 1079.654197613063 }, "steps_from_proto": { "total": 97.32896931402593, "count": 63547, "is_parallel": true, "self": 20.877511394960948, "children": { "_process_rank_one_or_two_observation": { "total": 76.45145791906498, "count": 508376, "is_parallel": true, "self": 76.45145791906498 } } } } } } } } } } }, "trainer_advance": { "total": 612.6890082628665, "count": 63548, "self": 2.5862980749921007, "children": { "process_trajectory": { "total": 109.2912073168859, "count": 63548, "self": 109.08597677288662, "children": { "RLTrainer._checkpoint": { "total": 0.20523054399927787, "count": 2, "self": 0.20523054399927787 } } }, "_update_policy": { "total": 500.81150287098853, "count": 449, "self": 321.87357364390846, "children": { "TorchPPOOptimizer.update": { "total": 178.93792922708008, "count": 22851, "self": 178.93792922708008 } } } } } } }, "trainer_threads": { "total": 9.609993867343292e-07, "count": 1, "self": 9.609993867343292e-07 }, "TrainerController._save_models": { "total": 0.09948253099992144, "count": 1, "self": 0.001422585999534931, "children": { "RLTrainer._checkpoint": { "total": 0.0980599450003865, "count": 1, "self": 0.0980599450003865 } } } } } } }