{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4560242295265198, "min": 0.428190678358078, "max": 1.506645917892456, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13782.8759765625, "min": 12647.0400390625, "max": 45705.609375, "count": 33 }, "Pyramids.Step.mean": { "value": 989882.0, "min": 29952.0, "max": 989882.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989882.0, "min": 29952.0, "max": 989882.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.06469903141260147, "min": -0.11465805768966675, "max": 0.09703339636325836, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 16.11005973815918, "min": -27.632591247558594, "max": 24.064281463623047, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.009364745579659939, "min": 0.0039476146921515465, "max": 0.09955163300037384, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.3318216800689697, "min": 0.9592703580856323, "max": 23.892391204833984, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06846382050398028, "min": 0.06525789853455287, "max": 0.07563013646861022, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9584934870557239, "min": 0.4899245364361994, "max": 1.046818327301926, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.00719148833975071, "min": 4.861112191611242e-05, "max": 0.008414805138145262, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.10068083675650995, "min": 0.0006319445849094614, "max": 0.11780727193403366, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.607926035485714e-06, "min": 7.607926035485714e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001065109644968, "min": 0.0001065109644968, "max": 0.0032258860247046995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253594285714286, "min": 0.10253594285714286, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4355032, "min": 1.3886848, "max": 2.3467824, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002633406914285715, "min": 0.0002633406914285715, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003686769680000001, "min": 0.003686769680000001, "max": 0.10754200047000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011606285348534584, "min": 0.011606285348534584, "max": 0.25451597571372986, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16248799860477448, "min": 0.16248799860477448, "max": 1.7816119194030762, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 832.4358974358975, "min": 708.95, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32465.0, "min": 15984.0, "max": 32465.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.1416820106215966, "min": -1.0000000521540642, "max": 0.39079496581107376, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 5.525598414242268, "min": -30.998201623558998, "max": 15.631798632442951, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.1416820106215966, "min": -1.0000000521540642, "max": 0.39079496581107376, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 5.525598414242268, "min": -30.998201623558998, "max": 15.631798632442951, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.10104023319600412, "min": 0.09197263081587152, "max": 4.949434297159314, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.940569094644161, "min": 3.6150847100652754, "max": 79.19094875454903, "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": "1676123783", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1676125917" }, "total": 2134.5542478700004, "count": 1, "self": 0.4748590039998817, "children": { "run_training.setup": { "total": 0.12283512400017571, "count": 1, "self": 0.12283512400017571 }, "TrainerController.start_learning": { "total": 2133.9565537420003, "count": 1, "self": 1.2193468790214865, "children": { "TrainerController._reset_env": { "total": 6.190092013999674, "count": 1, "self": 6.190092013999674 }, "TrainerController.advance": { "total": 2126.45938309598, "count": 63093, "self": 1.3071009229843185, "children": { "env_step": { "total": 1406.5567779079456, "count": 63093, "self": 1299.393295936864, "children": { "SubprocessEnvManager._take_step": { "total": 106.42281186701302, "count": 63093, "self": 4.400783107010284, "children": { "TorchPolicy.evaluate": { "total": 102.02202876000274, "count": 62573, "self": 35.028317536955, "children": { "TorchPolicy.sample_actions": { "total": 66.99371122304774, "count": 62573, "self": 66.99371122304774 } } } } }, "workers": { "total": 0.740670104068613, "count": 63093, "self": 0.0, "children": { "worker_root": { "total": 2129.3964883450444, "count": 63093, "is_parallel": true, "self": 936.8135326430443, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018469239998921694, "count": 1, "is_parallel": true, "self": 0.000733351000235416, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011135729996567534, "count": 8, "is_parallel": true, "self": 0.0011135729996567534 } } }, "UnityEnvironment.step": { "total": 0.048866593999719043, "count": 1, "is_parallel": true, "self": 0.0005057670000496728, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045822999982192414, "count": 1, "is_parallel": true, "self": 0.00045822999982192414 }, "communicator.exchange": { "total": 0.04631425499974284, "count": 1, "is_parallel": true, "self": 0.04631425499974284 }, "steps_from_proto": { "total": 0.0015883420001046034, "count": 1, "is_parallel": true, "self": 0.0004039530003865366, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011843889997180668, "count": 8, "is_parallel": true, "self": 0.0011843889997180668 } } } } } } }, "UnityEnvironment.step": { "total": 1192.5829557020002, "count": 63092, "is_parallel": true, "self": 30.818812181998965, "children": { "UnityEnvironment._generate_step_input": { "total": 22.479508520041236, "count": 63092, "is_parallel": true, "self": 22.479508520041236 }, "communicator.exchange": { "total": 1038.942287997074, "count": 63092, "is_parallel": true, "self": 1038.942287997074 }, "steps_from_proto": { "total": 100.34234700288607, "count": 63092, "is_parallel": true, "self": 21.711927341807495, "children": { "_process_rank_one_or_two_observation": { "total": 78.63041966107858, "count": 504736, "is_parallel": true, "self": 78.63041966107858 } } } } } } } } } } }, "trainer_advance": { "total": 718.5955042650498, "count": 63093, "self": 2.198287098133278, "children": { "process_trajectory": { "total": 155.85582828990937, "count": 63093, "self": 155.6649238869095, "children": { "RLTrainer._checkpoint": { "total": 0.19090440299987677, "count": 2, "self": 0.19090440299987677 } } }, "_update_policy": { "total": 560.5413888770072, "count": 434, "self": 216.26933375304588, "children": { "TorchPPOOptimizer.update": { "total": 344.2720551239613, "count": 22818, "self": 344.2720551239613 } } } } } } }, "trainer_threads": { "total": 9.069999578059651e-07, "count": 1, "self": 9.069999578059651e-07 }, "TrainerController._save_models": { "total": 0.08773084599943104, "count": 1, "self": 0.001455425000131072, "children": { "RLTrainer._checkpoint": { "total": 0.08627542099929997, "count": 1, "self": 0.08627542099929997 } } } } } } }