{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 1.0083420276641846, "min": 1.0083420276641846, "max": 1.4302774667739868, "count": 3 }, "Pyramids.Policy.Entropy.sum": { "value": 30201.859375, "min": 30201.859375, "max": 43388.8984375, "count": 3 }, "Pyramids.Step.mean": { "value": 89973.0, "min": 29952.0, "max": 89973.0, "count": 3 }, "Pyramids.Step.sum": { "value": 89973.0, "min": 29952.0, "max": 89973.0, "count": 3 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.07018574327230453, "min": -0.12179777771234512, "max": -0.07018574327230453, "count": 3 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -16.984949111938477, "min": -29.35326385498047, "max": -16.984949111938477, "count": 3 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.18007464706897736, "min": 0.18007464706897736, "max": 0.33111318945884705, "count": 3 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 43.57806396484375, "min": 43.57806396484375, "max": 79.79827880859375, "count": 3 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06840852902052968, "min": 0.06840852902052968, "max": 0.07262600321856832, "count": 3 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.8893108772668858, "min": 0.48539814353591343, "max": 0.8893108772668858, "count": 3 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0019146189621139795, "min": 0.0019146189621139795, "max": 0.007645753753913804, "count": 3 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.024890046507481733, "min": 0.021900026301918066, "max": 0.053520276277396625, "count": 3 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.585484394584615e-05, "min": 7.585484394584615e-05, "max": 0.0002515063018788571, "count": 3 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.000986112971296, "min": 0.000986112971296, "max": 0.0017605441131519997, "count": 3 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1252849230769231, "min": 0.1252849230769231, "max": 0.1838354285714286, "count": 3 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.6287040000000002, "min": 1.2868480000000002, "max": 1.6287040000000002, "count": 3 }, "Pyramids.Policy.Beta.mean": { "value": 0.0025359638153846157, "min": 0.0025359638153846157, "max": 0.008385159314285713, "count": 3 }, "Pyramids.Policy.Beta.sum": { "value": 0.0329675296, "min": 0.0329675296, "max": 0.058696115199999996, "count": 3 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.12500633299350739, "min": 0.12500633299350739, "max": 0.5237194895744324, "count": 3 }, "Pyramids.Losses.RNDLoss.sum": { "value": 1.62508225440979, "min": 1.62508225440979, "max": 3.666036605834961, "count": 3 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 952.2058823529412, "min": 952.2058823529412, "max": 999.0, "count": 3 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32375.0, "min": 15984.0, "max": 32954.0, "count": 3 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.7766000507947277, "min": -1.0000000521540642, "max": -0.7766000507947277, "count": 3 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -26.40440172702074, "min": -28.98540175706148, "max": -16.000000834465027, "count": 3 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.7766000507947277, "min": -1.0000000521540642, "max": -0.7766000507947277, "count": 3 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -26.40440172702074, "min": -28.98540175706148, "max": -16.000000834465027, "count": 3 }, "Pyramids.Policy.RndReward.mean": { "value": 1.3942591010538095, "min": 1.3942591010538095, "max": 10.68658627383411, "count": 3 }, "Pyramids.Policy.RndReward.sum": { "value": 47.40480943582952, "min": 47.40480943582952, "max": 170.98538038134575, "count": 3 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1677608623", "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": "1.22.4", "end_time_seconds": "1677608825" }, "total": 202.91046453199988, "count": 1, "self": 0.4258551559996704, "children": { "run_training.setup": { "total": 0.11483413800010567, "count": 1, "self": 0.11483413800010567 }, "TrainerController.start_learning": { "total": 202.3697752380001, "count": 1, "self": 0.1167557390060665, "children": { "TrainerController._reset_env": { "total": 6.500280959999827, "count": 1, "self": 6.500280959999827 }, "TrainerController.advance": { "total": 195.65607449099411, "count": 6289, "self": 0.13216598499798238, "children": { "env_step": { "total": 125.48025085999984, "count": 6289, "self": 114.40631751500655, "children": { "SubprocessEnvManager._take_step": { "total": 10.998993092988712, "count": 6289, "self": 0.44313804499188336, "children": { "TorchPolicy.evaluate": { "total": 10.555855047996829, "count": 6278, "self": 3.5656529579969174, "children": { "TorchPolicy.sample_actions": { "total": 6.9902020899999115, "count": 6278, "self": 6.9902020899999115 } } } } }, "workers": { "total": 0.07494025200458054, "count": 6289, "self": 0.0, "children": { "worker_root": { "total": 201.8265244829911, "count": 6289, "is_parallel": true, "self": 98.24119292599244, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018671289999474538, "count": 1, "is_parallel": true, "self": 0.0006774579999273556, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011896710000200983, "count": 8, "is_parallel": true, "self": 0.0011896710000200983 } } }, "UnityEnvironment.step": { "total": 0.10972523999998884, "count": 1, "is_parallel": true, "self": 0.000557325000045239, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004595159998643794, "count": 1, "is_parallel": true, "self": 0.0004595159998643794 }, "communicator.exchange": { "total": 0.10702670299997408, "count": 1, "is_parallel": true, "self": 0.10702670299997408 }, "steps_from_proto": { "total": 0.0016816960001051484, "count": 1, "is_parallel": true, "self": 0.0004144690003613505, "children": { "_process_rank_one_or_two_observation": { "total": 0.001267226999743798, "count": 8, "is_parallel": true, "self": 0.001267226999743798 } } } } } } }, "UnityEnvironment.step": { "total": 103.58533155699865, "count": 6288, "is_parallel": true, "self": 3.0723196159704003, "children": { "UnityEnvironment._generate_step_input": { "total": 2.235619281002073, "count": 6288, "is_parallel": true, "self": 2.235619281002073 }, "communicator.exchange": { "total": 89.35091977301954, "count": 6288, "is_parallel": true, "self": 89.35091977301954 }, "steps_from_proto": { "total": 8.92647288700664, "count": 6288, "is_parallel": true, "self": 2.0610056149921547, "children": { "_process_rank_one_or_two_observation": { "total": 6.8654672720144845, "count": 50304, "is_parallel": true, "self": 6.8654672720144845 } } } } } } } } } } }, "trainer_advance": { "total": 70.04365764599629, "count": 6289, "self": 0.16077571099390298, "children": { "process_trajectory": { "total": 15.77709871800198, "count": 6289, "self": 15.77709871800198 }, "_update_policy": { "total": 54.10578321700041, "count": 33, "self": 20.686629184001276, "children": { "TorchPPOOptimizer.update": { "total": 33.41915403299913, "count": 2262, "self": 33.41915403299913 } } } } } } }, "trainer_threads": { "total": 8.460001481580548e-07, "count": 1, "self": 8.460001481580548e-07 }, "TrainerController._save_models": { "total": 0.09666320199994516, "count": 1, "self": 0.0013415470000381902, "children": { "RLTrainer._checkpoint": { "total": 0.09532165499990697, "count": 1, "self": 0.09532165499990697 } } } } } } }