{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.44261491298675537, "min": 0.43837615847587585, "max": 1.4721075296401978, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13186.3837890625, "min": 13165.3125, "max": 44657.85546875, "count": 33 }, "Pyramids.Step.mean": { "value": 989996.0, "min": 29952.0, "max": 989996.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989996.0, "min": 29952.0, "max": 989996.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4553162455558777, "min": -0.10827046632766724, "max": 0.49324721097946167, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 123.39070129394531, "min": -26.093181610107422, "max": 136.13623046875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.019929546862840652, "min": -0.026455460116267204, "max": 0.3020526170730591, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.400907039642334, "min": -6.931330680847168, "max": 73.39878845214844, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06697644606936679, "min": 0.06488949397458615, "max": 0.07345427501769293, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.937670244971135, "min": 0.49803190267793357, "max": 1.0475913411646616, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014229264436358966, "min": 0.00012469800126951137, "max": 0.01666781245654729, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19920970210902553, "min": 0.001745772017773159, "max": 0.25001718684820934, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.346690408278572e-06, "min": 7.346690408278572e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010285366571590001, "min": 0.00010285366571590001, "max": 0.0033750472749843, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10244886428571429, "min": 0.10244886428571429, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4342841, "min": 1.3886848, "max": 2.4250157, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025464154214285725, "min": 0.00025464154214285725, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003564981590000001, "min": 0.003564981590000001, "max": 0.11251906843000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01316326018422842, "min": 0.013081311248242855, "max": 0.46718230843544006, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18428564071655273, "min": 0.18313835561275482, "max": 3.2702760696411133, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 415.83561643835617, "min": 337.5280898876405, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30356.0, "min": 15984.0, "max": 33712.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5080860865612824, "min": -1.0000000521540642, "max": 1.5500921193468438, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 108.58219823241234, "min": -30.99120157957077, "max": 137.9581986218691, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5080860865612824, "min": -1.0000000521540642, "max": 1.5500921193468438, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 108.58219823241234, "min": -30.99120157957077, "max": 137.9581986218691, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.055239182177804956, "min": 0.04682008351207177, "max": 9.901827353984118, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.9772211168019567, "min": 3.9772211168019567, "max": 158.42923766374588, "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": "1679835915", "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": "1679838018" }, "total": 2102.1448134580005, "count": 1, "self": 0.433767343000909, "children": { "run_training.setup": { "total": 0.16052870699991217, "count": 1, "self": 0.16052870699991217 }, "TrainerController.start_learning": { "total": 2101.550517408, "count": 1, "self": 1.3736757070209933, "children": { "TrainerController._reset_env": { "total": 6.738379752000128, "count": 1, "self": 6.738379752000128 }, "TrainerController.advance": { "total": 2093.349650326979, "count": 63567, "self": 1.5180942139518265, "children": { "env_step": { "total": 1462.0492787379997, "count": 63567, "self": 1348.8039512560051, "children": { "SubprocessEnvManager._take_step": { "total": 112.39121099396402, "count": 63567, "self": 4.840767829892911, "children": { "TorchPolicy.evaluate": { "total": 107.55044316407111, "count": 62562, "self": 107.55044316407111 } } }, "workers": { "total": 0.8541164880305132, "count": 63567, "self": 0.0, "children": { "worker_root": { "total": 2096.65889044896, "count": 63567, "is_parallel": true, "self": 866.3655377809985, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0029389710000486957, "count": 1, "is_parallel": true, "self": 0.0008095169998796337, "children": { "_process_rank_one_or_two_observation": { "total": 0.002129454000169062, "count": 8, "is_parallel": true, "self": 0.002129454000169062 } } }, "UnityEnvironment.step": { "total": 0.047230818999878466, "count": 1, "is_parallel": true, "self": 0.0005161599997336452, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005564030000186904, "count": 1, "is_parallel": true, "self": 0.0005564030000186904 }, "communicator.exchange": { "total": 0.044633949999933975, "count": 1, "is_parallel": true, "self": 0.044633949999933975 }, "steps_from_proto": { "total": 0.001524306000192155, "count": 1, "is_parallel": true, "self": 0.0003344819999711035, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011898240002210514, "count": 8, "is_parallel": true, "self": 0.0011898240002210514 } } } } } } }, "UnityEnvironment.step": { "total": 1230.2933526679615, "count": 63566, "is_parallel": true, "self": 31.15777126498324, "children": { "UnityEnvironment._generate_step_input": { "total": 24.01261584399299, "count": 63566, "is_parallel": true, "self": 24.01261584399299 }, "communicator.exchange": { "total": 1079.6284451600022, "count": 63566, "is_parallel": true, "self": 1079.6284451600022 }, "steps_from_proto": { "total": 95.49452039898301, "count": 63566, "is_parallel": true, "self": 20.685869895909264, "children": { "_process_rank_one_or_two_observation": { "total": 74.80865050307375, "count": 508528, "is_parallel": true, "self": 74.80865050307375 } } } } } } } } } } }, "trainer_advance": { "total": 629.7822773750274, "count": 63567, "self": 2.4899708950349577, "children": { "process_trajectory": { "total": 119.09582949199194, "count": 63567, "self": 118.89810001099204, "children": { "RLTrainer._checkpoint": { "total": 0.19772948099989662, "count": 2, "self": 0.19772948099989662 } } }, "_update_policy": { "total": 508.19647698800054, "count": 446, "self": 323.0999389910278, "children": { "TorchPPOOptimizer.update": { "total": 185.09653799697276, "count": 22800, "self": 185.09653799697276 } } } } } } }, "trainer_threads": { "total": 9.509999472356867e-07, "count": 1, "self": 9.509999472356867e-07 }, "TrainerController._save_models": { "total": 0.08881067099991924, "count": 1, "self": 0.0013322249997145263, "children": { "RLTrainer._checkpoint": { "total": 0.08747844600020471, "count": 1, "self": 0.08747844600020471 } } } } } } }