{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.13755440711975098, "min": 0.11292234063148499, "max": 1.461676001548767, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4137.63671875, "min": 3371.409423828125, "max": 44341.40234375, "count": 100 }, "Pyramids.Step.mean": { "value": 2999973.0, "min": 29952.0, "max": 2999973.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999973.0, "min": 29952.0, "max": 2999973.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6989985108375549, "min": -0.07424189150333405, "max": 0.8806230425834656, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 205.50555419921875, "min": -17.966537475585938, "max": 275.635009765625, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02050773799419403, "min": -0.028567658737301826, "max": 0.4134120047092438, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.029274940490723, "min": -8.313188552856445, "max": 97.97864532470703, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06939235450339593, "min": 0.06265041423729668, "max": 0.07432071263321442, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.971492963047543, "min": 0.4869951103638654, "max": 1.0702533304517834, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013207408518480535, "min": 0.0014658968526502533, "max": 0.01862175935160803, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18490371925872748, "min": 0.010261277968551773, "max": 0.2674620140072269, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5254852058238048e-06, "min": 1.5254852058238048e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.1356792881533267e-05, "min": 2.1356792881533267e-05, "max": 0.004027689657436833, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1005084619047619, "min": 0.1005084619047619, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4071184666666665, "min": 1.3897045333333333, "max": 2.842563166666667, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.079534428571414e-05, "min": 6.079534428571414e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008511348199999979, "min": 0.0008511348199999979, "max": 0.13427206035, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008000039495527744, "min": 0.007364943623542786, "max": 0.497846394777298, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11200055480003357, "min": 0.103109210729599, "max": 3.484924793243408, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 265.45762711864404, "min": 203.51333333333332, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31324.0, "min": 15984.0, "max": 33126.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6667288020253181, "min": -1.0000000521540642, "max": 1.7958858949226022, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 196.67399863898754, "min": -32.000001668930054, "max": 267.5869983434677, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6667288020253181, "min": -1.0000000521540642, "max": 1.7958858949226022, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 196.67399863898754, "min": -32.000001668930054, "max": 267.5869983434677, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.021846185818411235, "min": 0.017574053610734223, "max": 11.250928545370698, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.577849926572526, "min": 2.28366629613447, "max": 180.01485672593117, "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": "1679571458", "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 --force", "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": "1679579167" }, "total": 7709.640150595, "count": 1, "self": 0.47543022699846915, "children": { "run_training.setup": { "total": 0.11731187100031093, "count": 1, "self": 0.11731187100031093 }, "TrainerController.start_learning": { "total": 7709.047408497001, "count": 1, "self": 4.920498894221964, "children": { "TrainerController._reset_env": { "total": 5.95611521400042, "count": 1, "self": 5.95611521400042 }, "TrainerController.advance": { "total": 7698.059133287778, "count": 195403, "self": 5.061908261356621, "children": { "env_step": { "total": 5717.309200730153, "count": 195403, "self": 5360.876378972827, "children": { "SubprocessEnvManager._take_step": { "total": 353.5875502981098, "count": 195403, "self": 15.58003869716049, "children": { "TorchPolicy.evaluate": { "total": 338.00751160094933, "count": 187571, "self": 338.00751160094933 } } }, "workers": { "total": 2.8452714592158372, "count": 195403, "self": 0.0, "children": { "worker_root": { "total": 7691.149895716042, "count": 195403, "is_parallel": true, "self": 2721.0529060158497, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019517509999786853, "count": 1, "is_parallel": true, "self": 0.000636156000837218, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013155949991414673, "count": 8, "is_parallel": true, "self": 0.0013155949991414673 } } }, "UnityEnvironment.step": { "total": 0.04745198000000528, "count": 1, "is_parallel": true, "self": 0.0005771790001745103, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005382250001275679, "count": 1, "is_parallel": true, "self": 0.0005382250001275679 }, "communicator.exchange": { "total": 0.04459791299996141, "count": 1, "is_parallel": true, "self": 0.04459791299996141 }, "steps_from_proto": { "total": 0.0017386629997417913, "count": 1, "is_parallel": true, "self": 0.00041127699842036236, "children": { "_process_rank_one_or_two_observation": { "total": 0.001327386001321429, "count": 8, "is_parallel": true, "self": 0.001327386001321429 } } } } } } }, "UnityEnvironment.step": { "total": 4970.096989700192, "count": 195402, "is_parallel": true, "self": 99.66318261350716, "children": { "UnityEnvironment._generate_step_input": { "total": 75.58128074609249, "count": 195402, "is_parallel": true, "self": 75.58128074609249 }, "communicator.exchange": { "total": 4483.754457321949, "count": 195402, "is_parallel": true, "self": 4483.754457321949 }, "steps_from_proto": { "total": 311.0980690186434, "count": 195402, "is_parallel": true, "self": 69.01404161383653, "children": { "_process_rank_one_or_two_observation": { "total": 242.08402740480687, "count": 1563216, "is_parallel": true, "self": 242.08402740480687 } } } } } } } } } } }, "trainer_advance": { "total": 1975.6880242962688, "count": 195403, "self": 9.250320269365147, "children": { "process_trajectory": { "total": 394.36669847191297, "count": 195403, "self": 393.7184922599108, "children": { "RLTrainer._checkpoint": { "total": 0.648206212002151, "count": 6, "self": 0.648206212002151 } } }, "_update_policy": { "total": 1572.0710055549907, "count": 1400, "self": 1004.010656932699, "children": { "TorchPPOOptimizer.update": { "total": 568.0603486222917, "count": 68373, "self": 568.0603486222917 } } } } } } }, "trainer_threads": { "total": 1.203001374960877e-06, "count": 1, "self": 1.203001374960877e-06 }, "TrainerController._save_models": { "total": 0.11165989799883391, "count": 1, "self": 0.001618020998648717, "children": { "RLTrainer._checkpoint": { "total": 0.1100418770001852, "count": 1, "self": 0.1100418770001852 } } } } } } }