{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.17109832167625427, "min": 0.16057273745536804, "max": 1.3771406412124634, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 5138.4248046875, "min": 4809.474609375, "max": 41776.9375, "count": 100 }, "Pyramids.Step.mean": { "value": 2999996.0, "min": 29952.0, "max": 2999996.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999996.0, "min": 29952.0, "max": 2999996.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7007200121879578, "min": -0.08919369429349899, "max": 0.7798454761505127, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 206.01168823242188, "min": -21.674068450927734, "max": 234.73348999023438, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.021695759147405624, "min": -0.0022547650150954723, "max": 0.5337816476821899, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.37855339050293, "min": -0.6290794610977173, "max": 126.5062484741211, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0674413235274104, "min": 0.06371912420534917, "max": 0.07563034672611614, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.011619852911156, "min": 0.5133406563502089, "max": 1.063783585839202, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.018225575071033638, "min": 0.0003060013534493882, "max": 0.018225575071033638, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2733836260655046, "min": 0.00336601488794327, "max": 0.2733836260655046, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4996528334822232e-06, "min": 1.4996528334822232e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.2494792502233348e-05, "min": 2.2494792502233348e-05, "max": 0.004072655942448066, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10049985111111112, "min": 0.10049985111111112, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.507497766666667, "min": 1.3962282666666668, "max": 2.857551933333334, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.993512600000004e-05, "min": 5.993512600000004e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008990268900000006, "min": 0.0008990268900000006, "max": 0.13576943814, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0056941937655210495, "min": 0.005341517738997936, "max": 0.6331058144569397, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.0854129046201706, "min": 0.07478124648332596, "max": 4.431740760803223, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 251.20491803278688, "min": 237.88188976377953, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30647.0, "min": 15984.0, "max": 32642.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7159999875260181, "min": -1.0000000521540642, "max": 1.756169477761802, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 209.3519984781742, "min": -31.9980016797781, "max": 221.7879988923669, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7159999875260181, "min": -1.0000000521540642, "max": 1.756169477761802, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 209.3519984781742, "min": -31.9980016797781, "max": 221.7879988923669, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.014948785258445136, "min": 0.01437271043083086, "max": 12.625328617170453, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.8237518015303067, "min": 1.6891360212175641, "max": 202.00525787472725, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679340584", "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": "1679347501" }, "total": 6917.467330616999, "count": 1, "self": 0.47427901300034137, "children": { "run_training.setup": { "total": 0.12704875600002197, "count": 1, "self": 0.12704875600002197 }, "TrainerController.start_learning": { "total": 6916.866002847999, "count": 1, "self": 4.305607217042052, "children": { "TrainerController._reset_env": { "total": 6.434605873999772, "count": 1, "self": 6.434605873999772 }, "TrainerController.advance": { "total": 6906.035073113959, "count": 193428, "self": 4.699485653049123, "children": { "env_step": { "total": 5023.275904295955, "count": 193428, "self": 4689.267389930873, "children": { "SubprocessEnvManager._take_step": { "total": 331.39201045309164, "count": 193428, "self": 14.468764096130599, "children": { "TorchPolicy.evaluate": { "total": 316.92324635696104, "count": 187559, "self": 316.92324635696104 } } }, "workers": { "total": 2.6165039119905487, "count": 193428, "self": 0.0, "children": { "worker_root": { "total": 6901.6316362299, "count": 193428, "is_parallel": true, "self": 2576.7029972658993, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001820765000047686, "count": 1, "is_parallel": true, "self": 0.0006175359994813334, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012032290005663526, "count": 8, "is_parallel": true, "self": 0.0012032290005663526 } } }, "UnityEnvironment.step": { "total": 0.10767863899991426, "count": 1, "is_parallel": true, "self": 0.000542128000233788, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005078899998807174, "count": 1, "is_parallel": true, "self": 0.0005078899998807174 }, "communicator.exchange": { "total": 0.10482674299964856, "count": 1, "is_parallel": true, "self": 0.10482674299964856 }, "steps_from_proto": { "total": 0.0018018780001511914, "count": 1, "is_parallel": true, "self": 0.00038458999961221707, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014172880005389743, "count": 8, "is_parallel": true, "self": 0.0014172880005389743 } } } } } } }, "UnityEnvironment.step": { "total": 4324.928638964001, "count": 193427, "is_parallel": true, "self": 94.49958033491839, "children": { "UnityEnvironment._generate_step_input": { "total": 72.46432054514298, "count": 193427, "is_parallel": true, "self": 72.46432054514298 }, "communicator.exchange": { "total": 3867.0375175310714, "count": 193427, "is_parallel": true, "self": 3867.0375175310714 }, "steps_from_proto": { "total": 290.9272205528682, "count": 193427, "is_parallel": true, "self": 63.15526180199595, "children": { "_process_rank_one_or_two_observation": { "total": 227.77195875087227, "count": 1547416, "is_parallel": true, "self": 227.77195875087227 } } } } } } } } } } }, "trainer_advance": { "total": 1878.059683164954, "count": 193428, "self": 8.276509396103393, "children": { "process_trajectory": { "total": 372.9284969058822, "count": 193428, "self": 372.32822178488004, "children": { "RLTrainer._checkpoint": { "total": 0.6002751210021415, "count": 6, "self": 0.6002751210021415 } } }, "_update_policy": { "total": 1496.8546768629685, "count": 1395, "self": 955.4853125419359, "children": { "TorchPPOOptimizer.update": { "total": 541.3693643210327, "count": 68352, "self": 541.3693643210327 } } } } } } }, "trainer_threads": { "total": 1.0179992386838421e-06, "count": 1, "self": 1.0179992386838421e-06 }, "TrainerController._save_models": { "total": 0.09071562499957508, "count": 1, "self": 0.0014053059985599248, "children": { "RLTrainer._checkpoint": { "total": 0.08931031900101516, "count": 1, "self": 0.08931031900101516 } } } } } } }