{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.35866230726242065, "min": 0.35866230726242065, "max": 1.3993011713027954, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10880.3798828125, "min": 10880.3798828125, "max": 42449.19921875, "count": 33 }, "Pyramids.Step.mean": { "value": 989873.0, "min": 29952.0, "max": 989873.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989873.0, "min": 29952.0, "max": 989873.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5610277652740479, "min": -0.07672976702451706, "max": 0.5867434144020081, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 158.77085876464844, "min": -18.49187469482422, "max": 166.6351318359375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.019127245992422104, "min": 0.010812677443027496, "max": 0.6053438186645508, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.413010597229004, "min": 2.9842989444732666, "max": 143.46649169921875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06887442944432787, "min": 0.06548510361157935, "max": 0.0732635804577977, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9642420122205901, "min": 0.5059841690382962, "max": 1.0908435207578198, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015459876919131992, "min": 0.0008229976322410607, "max": 0.018043673940659, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2164382768678479, "min": 0.01152196685137485, "max": 0.24905205308944764, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.30036185229286e-06, "min": 7.30036185229286e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010220506593210003, "min": 0.00010220506593210003, "max": 0.0036365125878291995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10243342142857144, "min": 0.10243342142857144, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4340679, "min": 1.3886848, "max": 2.6121708, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025309880071428583, "min": 0.00025309880071428583, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035433832100000015, "min": 0.0035433832100000015, "max": 0.12123586292, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014259764924645424, "min": 0.014259764924645424, "max": 0.6292320489883423, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.19963671267032623, "min": 0.19963671267032623, "max": 4.4046244621276855, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 332.8901098901099, "min": 329.0888888888889, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30293.0, "min": 15984.0, "max": 32885.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6011516279899156, "min": -1.0000000521540642, "max": 1.6475590704516931, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 145.70479814708233, "min": -30.565001666545868, "max": 152.737198241055, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6011516279899156, "min": -1.0000000521540642, "max": 1.6475590704516931, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 145.70479814708233, "min": -30.565001666545868, "max": 152.737198241055, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04855204433660729, "min": 0.04855204433660729, "max": 13.744093339890242, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.4182360346312635, "min": 4.3243188370834105, "max": 219.90549343824387, "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": "1684167734", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1684169907" }, "total": 2173.1350519029993, "count": 1, "self": 0.47498634599924117, "children": { "run_training.setup": { "total": 0.06023302500011596, "count": 1, "self": 0.06023302500011596 }, "TrainerController.start_learning": { "total": 2172.5998325319997, "count": 1, "self": 1.2422317269874839, "children": { "TrainerController._reset_env": { "total": 4.168205598999975, "count": 1, "self": 4.168205598999975 }, "TrainerController.advance": { "total": 2167.100573657012, "count": 63973, "self": 1.2753728590264473, "children": { "env_step": { "total": 1543.7632127849558, "count": 63973, "self": 1441.298102238006, "children": { "SubprocessEnvManager._take_step": { "total": 101.73182336900572, "count": 63973, "self": 4.568509338993181, "children": { "TorchPolicy.evaluate": { "total": 97.16331403001254, "count": 62547, "self": 97.16331403001254 } } }, "workers": { "total": 0.7332871779440211, "count": 63973, "self": 0.0, "children": { "worker_root": { "total": 2168.03935150507, "count": 63973, "is_parallel": true, "self": 833.7086661030905, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0026858389999233623, "count": 1, "is_parallel": true, "self": 0.0007584410000163189, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019273979999070434, "count": 8, "is_parallel": true, "self": 0.0019273979999070434 } } }, "UnityEnvironment.step": { "total": 0.04482039200001964, "count": 1, "is_parallel": true, "self": 0.0005461279997689417, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004585670001233666, "count": 1, "is_parallel": true, "self": 0.0004585670001233666 }, "communicator.exchange": { "total": 0.042049202000043806, "count": 1, "is_parallel": true, "self": 0.042049202000043806 }, "steps_from_proto": { "total": 0.0017664950000835233, "count": 1, "is_parallel": true, "self": 0.0003616439998950227, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014048510001885006, "count": 8, "is_parallel": true, "self": 0.0014048510001885006 } } } } } } }, "UnityEnvironment.step": { "total": 1334.3306854019795, "count": 63972, "is_parallel": true, "self": 32.41259530891966, "children": { "UnityEnvironment._generate_step_input": { "total": 21.78714580705605, "count": 63972, "is_parallel": true, "self": 21.78714580705605 }, "communicator.exchange": { "total": 1182.5304673619278, "count": 63972, "is_parallel": true, "self": 1182.5304673619278 }, "steps_from_proto": { "total": 97.60047692407602, "count": 63972, "is_parallel": true, "self": 18.868905130248777, "children": { "_process_rank_one_or_two_observation": { "total": 78.73157179382724, "count": 511776, "is_parallel": true, "self": 78.73157179382724 } } } } } } } } } } }, "trainer_advance": { "total": 622.0619880130293, "count": 63973, "self": 2.502087075107511, "children": { "process_trajectory": { "total": 105.33646378591925, "count": 63973, "self": 105.02895251691939, "children": { "RLTrainer._checkpoint": { "total": 0.3075112689998605, "count": 2, "self": 0.3075112689998605 } } }, "_update_policy": { "total": 514.2234371520026, "count": 456, "self": 332.8317823289924, "children": { "TorchPPOOptimizer.update": { "total": 181.39165482301019, "count": 22803, "self": 181.39165482301019 } } } } } } }, "trainer_threads": { "total": 9.4600000011269e-07, "count": 1, "self": 9.4600000011269e-07 }, "TrainerController._save_models": { "total": 0.08882060300038574, "count": 1, "self": 0.001353573999949731, "children": { "RLTrainer._checkpoint": { "total": 0.08746702900043601, "count": 1, "self": 0.08746702900043601 } } } } } } }