{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.33878129720687866, "min": 0.3279014527797699, "max": 1.4677177667617798, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10185.12109375, "min": 9810.8115234375, "max": 44524.6875, "count": 33 }, "Pyramids.Step.mean": { "value": 989961.0, "min": 29952.0, "max": 989961.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989961.0, "min": 29952.0, "max": 989961.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6350641250610352, "min": -0.12968619167804718, "max": 0.6350641250610352, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 177.81796264648438, "min": -30.735626220703125, "max": 179.19821166992188, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.034083496779203415, "min": -0.034083496779203415, "max": 0.4348238706588745, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -9.543378829956055, "min": -9.543378829956055, "max": 103.05326080322266, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06714561907643829, "min": 0.06469425843719129, "max": 0.07317983523033708, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9400386670701361, "min": 0.4937994109024093, "max": 1.0817727096145973, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014929211549488607, "min": 0.0018182546812835817, "max": 0.016307139471636336, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2090089616928405, "min": 0.02249961055176491, "max": 0.22829995260290872, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.550047483350001e-06, "min": 7.550047483350001e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010570066476690001, "min": 0.00010570066476690001, "max": 0.0036360538879820995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251664999999999, "min": 0.10251664999999999, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4352330999999998, "min": 1.3886848, "max": 2.6120179000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026141333500000007, "min": 0.00026141333500000007, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036597866900000007, "min": 0.0036597866900000007, "max": 0.12122058820999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014234104193747044, "min": 0.014193777926266193, "max": 0.4770968556404114, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.19927746057510376, "min": 0.19871288537979126, "max": 3.3396780490875244, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 297.6372549019608, "min": 297.18811881188117, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30359.0, "min": 15984.0, "max": 32807.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7006892972779506, "min": -1.0000000521540642, "max": 1.7028118562285264, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 175.1709976196289, "min": -28.839001685380936, "max": 175.1709976196289, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7006892972779506, "min": -1.0000000521540642, "max": 1.7028118562285264, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 175.1709976196289, "min": -28.839001685380936, "max": 175.1709976196289, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04361485140875673, "min": 0.04361485140875673, "max": 10.031430395320058, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.492329695101944, "min": 4.425779998942744, "max": 160.50288632512093, "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": "1681826776", "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", "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": "1681828967" }, "total": 2191.0454228769995, "count": 1, "self": 0.5246301589986615, "children": { "run_training.setup": { "total": 0.10622238300015852, "count": 1, "self": 0.10622238300015852 }, "TrainerController.start_learning": { "total": 2190.4145703350005, "count": 1, "self": 1.4053229989513056, "children": { "TrainerController._reset_env": { "total": 3.760328915999935, "count": 1, "self": 3.760328915999935 }, "TrainerController.advance": { "total": 2185.1525042780495, "count": 64003, "self": 1.4323783620193353, "children": { "env_step": { "total": 1585.659492278049, "count": 64003, "self": 1480.312832046113, "children": { "SubprocessEnvManager._take_step": { "total": 104.5102405679495, "count": 64003, "self": 4.700981539996064, "children": { "TorchPolicy.evaluate": { "total": 99.80925902795343, "count": 62571, "self": 99.80925902795343 } } }, "workers": { "total": 0.8364196639863621, "count": 64003, "self": 0.0, "children": { "worker_root": { "total": 2184.896259684037, "count": 64003, "is_parallel": true, "self": 815.8168399110432, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001662746000192783, "count": 1, "is_parallel": true, "self": 0.0005310679998729029, "children": { "_process_rank_one_or_two_observation": { "total": 0.00113167800031988, "count": 8, "is_parallel": true, "self": 0.00113167800031988 } } }, "UnityEnvironment.step": { "total": 0.04611302199987222, "count": 1, "is_parallel": true, "self": 0.0005337029999736842, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004620649999651505, "count": 1, "is_parallel": true, "self": 0.0004620649999651505 }, "communicator.exchange": { "total": 0.04350789699992674, "count": 1, "is_parallel": true, "self": 0.04350789699992674 }, "steps_from_proto": { "total": 0.0016093570000066393, "count": 1, "is_parallel": true, "self": 0.0003694979998272174, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012398590001794219, "count": 8, "is_parallel": true, "self": 0.0012398590001794219 } } } } } } }, "UnityEnvironment.step": { "total": 1369.0794197729938, "count": 64002, "is_parallel": true, "self": 31.88418147993002, "children": { "UnityEnvironment._generate_step_input": { "total": 22.703342509015783, "count": 64002, "is_parallel": true, "self": 22.703342509015783 }, "communicator.exchange": { "total": 1222.1778288150167, "count": 64002, "is_parallel": true, "self": 1222.1778288150167 }, "steps_from_proto": { "total": 92.31406696903127, "count": 64002, "is_parallel": true, "self": 19.64125920324409, "children": { "_process_rank_one_or_two_observation": { "total": 72.67280776578718, "count": 512016, "is_parallel": true, "self": 72.67280776578718 } } } } } } } } } } }, "trainer_advance": { "total": 598.0606336379815, "count": 64003, "self": 2.7168533919752917, "children": { "process_trajectory": { "total": 102.58799950301045, "count": 64003, "self": 102.3875072120104, "children": { "RLTrainer._checkpoint": { "total": 0.20049229100004595, "count": 2, "self": 0.20049229100004595 } } }, "_update_policy": { "total": 492.75578074299574, "count": 454, "self": 315.7059068820149, "children": { "TorchPPOOptimizer.update": { "total": 177.04987386098082, "count": 22776, "self": 177.04987386098082 } } } } } } }, "trainer_threads": { "total": 1.0849998943740502e-06, "count": 1, "self": 1.0849998943740502e-06 }, "TrainerController._save_models": { "total": 0.09641305700006342, "count": 1, "self": 0.0015480870001738367, "children": { "RLTrainer._checkpoint": { "total": 0.09486496999988958, "count": 1, "self": 0.09486496999988958 } } } } } } }