{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.41402897238731384, "min": 0.38275349140167236, "max": 1.5000090599060059, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12546.734375, "min": 11427.48828125, "max": 45504.2734375, "count": 33 }, "Pyramids.Step.mean": { "value": 989972.0, "min": 29952.0, "max": 989972.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989972.0, "min": 29952.0, "max": 989972.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.43022415041923523, "min": -0.096071258187294, "max": 0.5210638642311096, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 117.4511947631836, "min": -23.249244689941406, "max": 144.33468627929688, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.03661458194255829, "min": -0.032980453222990036, "max": 0.22700749337673187, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 9.995780944824219, "min": -8.77280044555664, "max": 53.800777435302734, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06967339946866212, "min": 0.0647315547025615, "max": 0.07592414100701259, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9754275925612697, "min": 0.5314689870490881, "max": 1.086894438669939, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015497342088825205, "min": 0.0010223211651975354, "max": 0.015497342088825205, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21696278924355286, "min": 0.01329017514756796, "max": 0.21696278924355286, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.353933263007146e-06, "min": 7.353933263007146e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010295506568210004, "min": 0.00010295506568210004, "max": 0.003507294230902, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10245127857142859, "min": 0.10245127857142859, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4343179000000004, "min": 1.3886848, "max": 2.5690980000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002548827292857144, "min": 0.0002548827292857144, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035683582100000015, "min": 0.0035683582100000015, "max": 0.11693289020000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008288775570690632, "min": 0.008288775570690632, "max": 0.33939069509506226, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.116042859852314, "min": 0.116042859852314, "max": 2.375734806060791, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 424.73333333333335, "min": 394.49295774647885, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31855.0, "min": 15984.0, "max": 33228.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.409768401498073, "min": -1.0000000521540642, "max": 1.5653447126479525, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 107.14239851385355, "min": -29.26000164449215, "max": 118.96619816124439, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.409768401498073, "min": -1.0000000521540642, "max": 1.5653447126479525, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 107.14239851385355, "min": -29.26000164449215, "max": 118.96619816124439, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03783793606338517, "min": 0.034975540379946324, "max": 6.215885441750288, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.875683140817273, "min": 2.2384345843165647, "max": 99.45416706800461, "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": "1679707385", "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": "1679709573" }, "total": 2187.9114083490003, "count": 1, "self": 0.4787300430002688, "children": { "run_training.setup": { "total": 0.11111950199983767, "count": 1, "self": 0.11111950199983767 }, "TrainerController.start_learning": { "total": 2187.3215588040002, "count": 1, "self": 1.368744864887958, "children": { "TrainerController._reset_env": { "total": 6.905462395000086, "count": 1, "self": 6.905462395000086 }, "TrainerController.advance": { "total": 2178.9553671201124, "count": 63661, "self": 1.4793326010822057, "children": { "env_step": { "total": 1535.6891169800228, "count": 63661, "self": 1424.275889506002, "children": { "SubprocessEnvManager._take_step": { "total": 110.58915559304614, "count": 63661, "self": 4.69272035419408, "children": { "TorchPolicy.evaluate": { "total": 105.89643523885206, "count": 62569, "self": 105.89643523885206 } } }, "workers": { "total": 0.8240718809747705, "count": 63661, "self": 0.0, "children": { "worker_root": { "total": 2182.532268457067, "count": 63661, "is_parallel": true, "self": 876.7531658811254, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001923557999816694, "count": 1, "is_parallel": true, "self": 0.0005758979996244307, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013476600001922634, "count": 8, "is_parallel": true, "self": 0.0013476600001922634 } } }, "UnityEnvironment.step": { "total": 0.07956802099988636, "count": 1, "is_parallel": true, "self": 0.0005413099988800241, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004942620003021148, "count": 1, "is_parallel": true, "self": 0.0004942620003021148 }, "communicator.exchange": { "total": 0.07695487900036824, "count": 1, "is_parallel": true, "self": 0.07695487900036824 }, "steps_from_proto": { "total": 0.0015775700003359816, "count": 1, "is_parallel": true, "self": 0.000354403000073944, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012231670002620376, "count": 8, "is_parallel": true, "self": 0.0012231670002620376 } } } } } } }, "UnityEnvironment.step": { "total": 1305.7791025759416, "count": 63660, "is_parallel": true, "self": 31.402091823877527, "children": { "UnityEnvironment._generate_step_input": { "total": 22.74132980003742, "count": 63660, "is_parallel": true, "self": 22.74132980003742 }, "communicator.exchange": { "total": 1159.367154359053, "count": 63660, "is_parallel": true, "self": 1159.367154359053 }, "steps_from_proto": { "total": 92.26852659297356, "count": 63660, "is_parallel": true, "self": 19.639640735085777, "children": { "_process_rank_one_or_two_observation": { "total": 72.62888585788778, "count": 509280, "is_parallel": true, "self": 72.62888585788778 } } } } } } } } } } }, "trainer_advance": { "total": 641.7869175390074, "count": 63661, "self": 2.561114365906633, "children": { "process_trajectory": { "total": 119.55675760810027, "count": 63661, "self": 119.35736458209976, "children": { "RLTrainer._checkpoint": { "total": 0.19939302600050723, "count": 2, "self": 0.19939302600050723 } } }, "_update_policy": { "total": 519.6690455650005, "count": 452, "self": 331.61634734498693, "children": { "TorchPPOOptimizer.update": { "total": 188.05269822001355, "count": 22821, "self": 188.05269822001355 } } } } } } }, "trainer_threads": { "total": 9.679997674538754e-07, "count": 1, "self": 9.679997674538754e-07 }, "TrainerController._save_models": { "total": 0.09198345599997992, "count": 1, "self": 0.0014408150000235764, "children": { "RLTrainer._checkpoint": { "total": 0.09054264099995635, "count": 1, "self": 0.09054264099995635 } } } } } } }