{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.32636523246765137, "min": 0.320800244808197, "max": 1.4261311292648315, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9978.943359375, "min": 9552.1484375, "max": 43263.11328125, "count": 33 }, "Pyramids.Step.mean": { "value": 989957.0, "min": 29952.0, "max": 989957.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989957.0, "min": 29952.0, "max": 989957.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.42601123452186584, "min": -0.0996180847287178, "max": 0.46801090240478516, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 112.89297485351562, "min": -23.908340454101562, "max": 125.42692565917969, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0059366426430642605, "min": -0.016640448942780495, "max": 0.30130675435066223, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.5732102394104004, "min": -4.293235778808594, "max": 71.40969848632812, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06646674602050842, "min": 0.06513619378318743, "max": 0.07389064782727486, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.930534444287118, "min": 0.5032624694908133, "max": 1.0521650593522387, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012760811504090308, "min": 0.00016942016953765986, "max": 0.015030185567628085, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1786513610572643, "min": 0.0018636218649142585, "max": 0.2104225979467932, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.75057598793572e-06, "min": 7.75057598793572e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010850806383110006, "min": 0.00010850806383110006, "max": 0.0033817796727402, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10258349285714286, "min": 0.10258349285714286, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4361689, "min": 1.3691136000000002, "max": 2.572355, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026809093642857153, "min": 0.00026809093642857153, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037532731100000014, "min": 0.0037532731100000014, "max": 0.11275325402, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0075355591252446175, "min": 0.0075355591252446175, "max": 0.37900280952453613, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1054978296160698, "min": 0.1054978296160698, "max": 2.653019666671753, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 452.24285714285713, "min": 419.04411764705884, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31657.0, "min": 15984.0, "max": 34453.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.404834261749472, "min": -1.0000000521540642, "max": 1.4102984804715684, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 98.33839832246304, "min": -32.000001668930054, "max": 102.24599802494049, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.404834261749472, "min": -1.0000000521540642, "max": 1.4102984804715684, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 98.33839832246304, "min": -32.000001668930054, "max": 102.24599802494049, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.035276156631048904, "min": 0.03432238066991832, "max": 7.9697156911715865, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.469330964173423, "min": 2.333921885554446, "max": 127.51545105874538, "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": "1697207532", "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": "1697209574" }, "total": 2041.760609589, "count": 1, "self": 0.844667255999866, "children": { "run_training.setup": { "total": 0.041773945000159074, "count": 1, "self": 0.041773945000159074 }, "TrainerController.start_learning": { "total": 2040.874168388, "count": 1, "self": 1.207521308976311, "children": { "TrainerController._reset_env": { "total": 3.08570596200002, "count": 1, "self": 3.08570596200002 }, "TrainerController.advance": { "total": 2036.4665753630236, "count": 63608, "self": 1.245808247876539, "children": { "env_step": { "total": 1434.1491764900616, "count": 63608, "self": 1318.8108023050947, "children": { "SubprocessEnvManager._take_step": { "total": 114.61790802101768, "count": 63608, "self": 4.426886588027855, "children": { "TorchPolicy.evaluate": { "total": 110.19102143298983, "count": 62558, "self": 110.19102143298983 } } }, "workers": { "total": 0.7204661639491405, "count": 63608, "self": 0.0, "children": { "worker_root": { "total": 2036.5362739630314, "count": 63608, "is_parallel": true, "self": 825.8716285800479, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017937290001555084, "count": 1, "is_parallel": true, "self": 0.0005517970005257666, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012419319996297418, "count": 8, "is_parallel": true, "self": 0.0012419319996297418 } } }, "UnityEnvironment.step": { "total": 0.04581223499985754, "count": 1, "is_parallel": true, "self": 0.0006128249997345847, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005053800000496267, "count": 1, "is_parallel": true, "self": 0.0005053800000496267 }, "communicator.exchange": { "total": 0.04305242899999939, "count": 1, "is_parallel": true, "self": 0.04305242899999939 }, "steps_from_proto": { "total": 0.0016416010000739334, "count": 1, "is_parallel": true, "self": 0.00033779199975469965, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013038090003192337, "count": 8, "is_parallel": true, "self": 0.0013038090003192337 } } } } } } }, "UnityEnvironment.step": { "total": 1210.6646453829835, "count": 63607, "is_parallel": true, "self": 33.01905779097319, "children": { "UnityEnvironment._generate_step_input": { "total": 22.466816858991933, "count": 63607, "is_parallel": true, "self": 22.466816858991933 }, "communicator.exchange": { "total": 1062.6178455870133, "count": 63607, "is_parallel": true, "self": 1062.6178455870133 }, "steps_from_proto": { "total": 92.56092514600505, "count": 63607, "is_parallel": true, "self": 17.86866790096883, "children": { "_process_rank_one_or_two_observation": { "total": 74.69225724503622, "count": 508856, "is_parallel": true, "self": 74.69225724503622 } } } } } } } } } } }, "trainer_advance": { "total": 601.0715906250855, "count": 63608, "self": 2.226060882075444, "children": { "process_trajectory": { "total": 113.41035507300921, "count": 63608, "self": 113.15426694900952, "children": { "RLTrainer._checkpoint": { "total": 0.25608812399968883, "count": 2, "self": 0.25608812399968883 } } }, "_update_policy": { "total": 485.43517467000083, "count": 445, "self": 292.3422913239983, "children": { "TorchPPOOptimizer.update": { "total": 193.0928833460025, "count": 22809, "self": 193.0928833460025 } } } } } } }, "trainer_threads": { "total": 1.258999873243738e-06, "count": 1, "self": 1.258999873243738e-06 }, "TrainerController._save_models": { "total": 0.11436449500024537, "count": 1, "self": 0.0017873730002975208, "children": { "RLTrainer._checkpoint": { "total": 0.11257712199994785, "count": 1, "self": 0.11257712199994785 } } } } } } }