{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.43718820810317993, "min": 0.4214741885662079, "max": 1.36246919631958, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13087.666015625, "min": 12671.2001953125, "max": 41331.8671875, "count": 33 }, "Pyramids.Step.mean": { "value": 989944.0, "min": 29952.0, "max": 989944.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989944.0, "min": 29952.0, "max": 989944.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.36034029722213745, "min": -0.0969676524400711, "max": 0.3714187741279602, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 94.76950073242188, "min": -23.563138961791992, "max": 97.68313598632812, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.10909298807382584, "min": -0.026576140895485878, "max": 0.29709962010383606, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 28.691455841064453, "min": -6.962948799133301, "max": 72.19520568847656, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06422974380815508, "min": 0.06422974380815508, "max": 0.0748397302297223, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.8992164133141711, "min": 0.5238781116080561, "max": 1.0498653510197378, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014749017517106526, "min": 0.0003799078849292282, "max": 0.017032219871347253, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20648624523949136, "min": 0.004938802504079967, "max": 0.23845107819886155, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.710204572821428e-06, "min": 7.710204572821428e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010794286401950001, "min": 0.00010794286401950001, "max": 0.0036347146884285, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10257003571428572, "min": 0.10257003571428572, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4359805, "min": 1.3886848, "max": 2.6115714999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000266746567857143, "min": 0.000266746567857143, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037344519500000016, "min": 0.0037344519500000016, "max": 0.12117599285, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00806504487991333, "min": 0.0077030169777572155, "max": 0.36458176374435425, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11291062831878662, "min": 0.10784223675727844, "max": 2.552072286605835, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 507.6666666666667, "min": 418.64179104477614, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28937.0, "min": 15984.0, "max": 34549.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.1734379073926087, "min": -1.0000000521540642, "max": 1.4022029614937839, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 68.0593986287713, "min": -31.99320164322853, "max": 93.94759842008352, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.1734379073926087, "min": -1.0000000521540642, "max": 1.4022029614937839, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 68.0593986287713, "min": -31.99320164322853, "max": 93.94759842008352, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04362147075071648, "min": 0.03715203479279388, "max": 7.315720745362341, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.5300453035415558, "min": 2.414882261531602, "max": 117.05153192579746, "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": "1690714009", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "command_line_arguments": "/home/darth/MLAI-projects/unity_ML_env_rl/envunity/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training 1 --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": "1690715364" }, "total": 1355.2869846730027, "count": 1, "self": 0.32776218600338325, "children": { "run_training.setup": { "total": 0.01180758599366527, "count": 1, "self": 0.01180758599366527 }, "TrainerController.start_learning": { "total": 1354.9474149010057, "count": 1, "self": 1.262483415324823, "children": { "TrainerController._reset_env": { "total": 4.15478988099494, "count": 1, "self": 4.15478988099494 }, "TrainerController.advance": { "total": 1349.339796562679, "count": 63455, "self": 1.1920719061308773, "children": { "env_step": { "total": 814.3728989905067, "count": 63455, "self": 709.2076148435008, "children": { "SubprocessEnvManager._take_step": { "total": 104.34805970343587, "count": 63455, "self": 3.7180437336937757, "children": { "TorchPolicy.evaluate": { "total": 100.63001596974209, "count": 62559, "self": 100.63001596974209 } } }, "workers": { "total": 0.8172244435700122, "count": 63455, "self": 0.0, "children": { "worker_root": { "total": 1352.562000917751, "count": 63455, "is_parallel": true, "self": 727.7343813870393, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0015142119955271482, "count": 1, "is_parallel": true, "self": 0.00042518599366303533, "children": { "_process_rank_one_or_two_observation": { "total": 0.001089026001864113, "count": 8, "is_parallel": true, "self": 0.001089026001864113 } } }, "UnityEnvironment.step": { "total": 0.030337206000695005, "count": 1, "is_parallel": true, "self": 0.0002902650012401864, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00026979199901688844, "count": 1, "is_parallel": true, "self": 0.00026979199901688844 }, "communicator.exchange": { "total": 0.02759240999876056, "count": 1, "is_parallel": true, "self": 0.02759240999876056 }, "steps_from_proto": { "total": 0.0021847390016773716, "count": 1, "is_parallel": true, "self": 0.00022255700605455786, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019621819956228137, "count": 8, "is_parallel": true, "self": 0.0019621819956228137 } } } } } } }, "UnityEnvironment.step": { "total": 624.8276195307117, "count": 63454, "is_parallel": true, "self": 18.086606050259434, "children": { "UnityEnvironment._generate_step_input": { "total": 13.577428215998225, "count": 63454, "is_parallel": true, "self": 13.577428215998225 }, "communicator.exchange": { "total": 538.0262261589087, "count": 63454, "is_parallel": true, "self": 538.0262261589087 }, "steps_from_proto": { "total": 55.13735910554533, "count": 63454, "is_parallel": true, "self": 13.193120055278996, "children": { "_process_rank_one_or_two_observation": { "total": 41.94423905026633, "count": 507632, "is_parallel": true, "self": 41.94423905026633 } } } } } } } } } } }, "trainer_advance": { "total": 533.7748256660416, "count": 63455, "self": 2.2904333026817767, "children": { "process_trajectory": { "total": 86.06598896317882, "count": 63455, "self": 85.88292472717876, "children": { "RLTrainer._checkpoint": { "total": 0.18306423600006383, "count": 2, "self": 0.18306423600006383 } } }, "_update_policy": { "total": 445.418403400181, "count": 454, "self": 273.9075825845357, "children": { "TorchPPOOptimizer.update": { "total": 171.51082081564527, "count": 22812, "self": 171.51082081564527 } } } } } } }, "trainer_threads": { "total": 9.369978215545416e-07, "count": 1, "self": 9.369978215545416e-07 }, "TrainerController._save_models": { "total": 0.19034410500898957, "count": 1, "self": 0.0014047120203031227, "children": { "RLTrainer._checkpoint": { "total": 0.18893939298868645, "count": 1, "self": 0.18893939298868645 } } } } } } }