{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.73075932264328, "min": 0.6708958148956299, "max": 1.4215344190597534, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 21887.703125, "min": 20073.203125, "max": 43123.66796875, "count": 33 }, "Pyramids.Step.mean": { "value": 989988.0, "min": 29952.0, "max": 989988.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989988.0, "min": 29952.0, "max": 989988.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.09480485320091248, "min": -0.10160810500383377, "max": 0.09480485320091248, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 23.701213836669922, "min": -24.385944366455078, "max": 23.701213836669922, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.049889273941516876, "min": 0.013466407544910908, "max": 0.4943709969520569, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 12.472318649291992, "min": 3.3127362728118896, "max": 117.16592407226562, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07157881780066029, "min": 0.0639325553748972, "max": 0.07277367609381515, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.002103449209244, "min": 0.4974685737832407, "max": 1.0624960574090903, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.009709257556697654, "min": 0.00011170198267120196, "max": 0.015417325796398833, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.13592960579376714, "min": 0.0015638277573968274, "max": 0.13592960579376714, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.280154716171427e-06, "min": 7.280154716171427e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010192216602639998, "min": 0.00010192216602639998, "max": 0.0035075879308041, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10242668571428569, "min": 0.10242668571428569, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4339735999999996, "min": 1.3886848, "max": 2.5691959000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002524259028571428, "min": 0.0002524259028571428, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035339626399999995, "min": 0.0035339626399999995, "max": 0.11694267040999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013450860045850277, "min": 0.013450860045850277, "max": 0.598111629486084, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18831203877925873, "min": 0.18831203877925873, "max": 4.186781406402588, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 713.8, "min": 713.8, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28552.0, "min": 15984.0, "max": 32607.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.4859849657863379, "min": -1.0000000521540642, "max": 0.4859849657863379, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 19.439398631453514, "min": -30.99680159986019, "max": 19.439398631453514, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.4859849657863379, "min": -1.0000000521540642, "max": 0.4859849657863379, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 19.439398631453514, "min": -30.99680159986019, "max": 19.439398631453514, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0995938936874154, "min": 0.0995938936874154, "max": 12.716632867231965, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.983755747496616, "min": 3.983755747496616, "max": 203.46612587571144, "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": "1697458797", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1697460816" }, "total": 2019.0856081000002, "count": 1, "self": 0.6330330089999734, "children": { "run_training.setup": { "total": 0.04492526500001759, "count": 1, "self": 0.04492526500001759 }, "TrainerController.start_learning": { "total": 2018.4076498260001, "count": 1, "self": 1.290525824985707, "children": { "TrainerController._reset_env": { "total": 3.7188611079999987, "count": 1, "self": 3.7188611079999987 }, "TrainerController.advance": { "total": 2013.316640359014, "count": 63171, "self": 1.39551492294936, "children": { "env_step": { "total": 1398.5654953990208, "count": 63171, "self": 1275.9197896580058, "children": { "SubprocessEnvManager._take_step": { "total": 121.87336608902484, "count": 63171, "self": 4.61206085202781, "children": { "TorchPolicy.evaluate": { "total": 117.26130523699703, "count": 62561, "self": 117.26130523699703 } } }, "workers": { "total": 0.7723396519902508, "count": 63171, "self": 0.0, "children": { "worker_root": { "total": 2014.0000522339642, "count": 63171, "is_parallel": true, "self": 852.3451737910036, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019994669999618964, "count": 1, "is_parallel": true, "self": 0.0006438130000105957, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013556539999513006, "count": 8, "is_parallel": true, "self": 0.0013556539999513006 } } }, "UnityEnvironment.step": { "total": 0.09706946599999355, "count": 1, "is_parallel": true, "self": 0.0006635429999732878, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046991900001103204, "count": 1, "is_parallel": true, "self": 0.00046991900001103204 }, "communicator.exchange": { "total": 0.09417395400004125, "count": 1, "is_parallel": true, "self": 0.09417395400004125 }, "steps_from_proto": { "total": 0.001762049999967985, "count": 1, "is_parallel": true, "self": 0.000384370000006129, "children": { "_process_rank_one_or_two_observation": { "total": 0.001377679999961856, "count": 8, "is_parallel": true, "self": 0.001377679999961856 } } } } } } }, "UnityEnvironment.step": { "total": 1161.6548784429606, "count": 63170, "is_parallel": true, "self": 34.377744162953604, "children": { "UnityEnvironment._generate_step_input": { "total": 24.206498968996016, "count": 63170, "is_parallel": true, "self": 24.206498968996016 }, "communicator.exchange": { "total": 1006.5051460910136, "count": 63170, "is_parallel": true, "self": 1006.5051460910136 }, "steps_from_proto": { "total": 96.5654892199974, "count": 63170, "is_parallel": true, "self": 18.957319100169116, "children": { "_process_rank_one_or_two_observation": { "total": 77.60817011982829, "count": 505360, "is_parallel": true, "self": 77.60817011982829 } } } } } } } } } } }, "trainer_advance": { "total": 613.3556300370437, "count": 63171, "self": 2.3698330500724296, "children": { "process_trajectory": { "total": 115.98816142897124, "count": 63171, "self": 115.8128837979715, "children": { "RLTrainer._checkpoint": { "total": 0.17527763099974436, "count": 2, "self": 0.17527763099974436 } } }, "_update_policy": { "total": 494.99763555800007, "count": 443, "self": 297.79790413098203, "children": { "TorchPPOOptimizer.update": { "total": 197.19973142701804, "count": 22740, "self": 197.19973142701804 } } } } } } }, "trainer_threads": { "total": 1.4480001482297666e-06, "count": 1, "self": 1.4480001482297666e-06 }, "TrainerController._save_models": { "total": 0.0816210860002684, "count": 1, "self": 0.0013908589999118703, "children": { "RLTrainer._checkpoint": { "total": 0.08023022700035654, "count": 1, "self": 0.08023022700035654 } } } } } } }