{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4361632466316223, "min": 0.4210100471973419, "max": 1.5096745491027832, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13140.7265625, "min": 12567.822265625, "max": 45797.48828125, "count": 33 }, "Pyramids.Step.mean": { "value": 989899.0, "min": 29952.0, "max": 989899.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989899.0, "min": 29952.0, "max": 989899.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5044113397598267, "min": -0.12804773449897766, "max": 0.5866509079933167, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 139.72193908691406, "min": -30.8595027923584, "max": 167.1955108642578, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01884152740240097, "min": 0.007882833480834961, "max": 0.2504799962043762, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.2191033363342285, "min": 2.1598963737487793, "max": 60.36567687988281, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07092397024906757, "min": 0.06596286348468271, "max": 0.07414632835870552, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0638595537360136, "min": 0.4963826650433141, "max": 1.0638595537360136, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014979683704182714, "min": 0.00045318320660177027, "max": 0.016786849141811087, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22469525556274073, "min": 0.005438198479221243, "max": 0.23501588798535522, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.524497491866666e-06, "min": 7.524497491866666e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.000112867462378, "min": 0.000112867462378, "max": 0.0035084846305051993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250813333333335, "min": 0.10250813333333335, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5376220000000003, "min": 1.3886848, "max": 2.5694948, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026056252, "min": 0.00026056252, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0039084378, "min": 0.0039084378, "max": 0.11697253052, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012885530479252338, "min": 0.012885530479252338, "max": 0.4076363742351532, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.19328296184539795, "min": 0.18648114800453186, "max": 2.85345458984375, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 351.5061728395062, "min": 332.80434782608694, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28472.0, "min": 15984.0, "max": 33439.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6237999771112277, "min": -1.0000000521540642, "max": 1.6237999771112277, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 131.52779814600945, "min": -31.997201651334763, "max": 145.73579777777195, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6237999771112277, "min": -1.0000000521540642, "max": 1.6237999771112277, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 131.52779814600945, "min": -31.997201651334763, "max": 145.73579777777195, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04724960826031208, "min": 0.04724960826031208, "max": 8.12600458227098, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.8272182690852787, "min": 3.8272182690852787, "max": 130.01607331633568, "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": "1690130993", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "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": "1690133276" }, "total": 2283.01820866, "count": 1, "self": 0.4758206420001443, "children": { "run_training.setup": { "total": 0.050776012999904196, "count": 1, "self": 0.050776012999904196 }, "TrainerController.start_learning": { "total": 2282.4916120049998, "count": 1, "self": 1.465627282049354, "children": { "TrainerController._reset_env": { "total": 4.034046866999688, "count": 1, "self": 4.034046866999688 }, "TrainerController.advance": { "total": 2276.9000254109496, "count": 63853, "self": 1.5227728699478575, "children": { "env_step": { "total": 1618.1715882489934, "count": 63853, "self": 1503.4735411699894, "children": { "SubprocessEnvManager._take_step": { "total": 113.82047784100587, "count": 63853, "self": 5.040478084876668, "children": { "TorchPolicy.evaluate": { "total": 108.7799997561292, "count": 62558, "self": 108.7799997561292 } } }, "workers": { "total": 0.8775692379981592, "count": 63853, "self": 0.0, "children": { "worker_root": { "total": 2276.811012251027, "count": 63853, "is_parallel": true, "self": 895.6435692760488, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001980746999834082, "count": 1, "is_parallel": true, "self": 0.0006990389993006829, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012817080005333992, "count": 8, "is_parallel": true, "self": 0.0012817080005333992 } } }, "UnityEnvironment.step": { "total": 0.06226184899969667, "count": 1, "is_parallel": true, "self": 0.0005547809992094699, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005661370000780153, "count": 1, "is_parallel": true, "self": 0.0005661370000780153 }, "communicator.exchange": { "total": 0.0591188210000837, "count": 1, "is_parallel": true, "self": 0.0591188210000837 }, "steps_from_proto": { "total": 0.0020221100003254833, "count": 1, "is_parallel": true, "self": 0.00037822200147275, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016438879988527333, "count": 8, "is_parallel": true, "self": 0.0016438879988527333 } } } } } } }, "UnityEnvironment.step": { "total": 1381.1674429749783, "count": 63852, "is_parallel": true, "self": 34.455697988959855, "children": { "UnityEnvironment._generate_step_input": { "total": 23.826032549042793, "count": 63852, "is_parallel": true, "self": 23.826032549042793 }, "communicator.exchange": { "total": 1216.0484591260706, "count": 63852, "is_parallel": true, "self": 1216.0484591260706 }, "steps_from_proto": { "total": 106.837253310905, "count": 63852, "is_parallel": true, "self": 22.394140374917697, "children": { "_process_rank_one_or_two_observation": { "total": 84.4431129359873, "count": 510816, "is_parallel": true, "self": 84.4431129359873 } } } } } } } } } } }, "trainer_advance": { "total": 657.2056642920084, "count": 63853, "self": 2.6737428150577216, "children": { "process_trajectory": { "total": 115.84862112695237, "count": 63853, "self": 115.62991032395257, "children": { "RLTrainer._checkpoint": { "total": 0.2187108029997944, "count": 2, "self": 0.2187108029997944 } } }, "_update_policy": { "total": 538.6833003499983, "count": 451, "self": 352.2253423089528, "children": { "TorchPPOOptimizer.update": { "total": 186.45795804104546, "count": 22815, "self": 186.45795804104546 } } } } } } }, "trainer_threads": { "total": 1.109000550059136e-06, "count": 1, "self": 1.109000550059136e-06 }, "TrainerController._save_models": { "total": 0.09191133600052126, "count": 1, "self": 0.0014216880008461885, "children": { "RLTrainer._checkpoint": { "total": 0.09048964799967507, "count": 1, "self": 0.09048964799967507 } } } } } } }