{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5478100776672363, "min": 0.5478100776672363, "max": 1.482829213142395, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16583.306640625, "min": 16583.306640625, "max": 44983.10546875, "count": 33 }, "Pyramids.Step.mean": { "value": 989894.0, "min": 29952.0, "max": 989894.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989894.0, "min": 29952.0, "max": 989894.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.09733311086893082, "min": -0.024922801181674004, "max": 0.10092341899871826, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 25.403942108154297, "min": -5.906703948974609, "max": 26.240089416503906, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.004445817321538925, "min": 0.0038571178447455168, "max": 0.19789820909500122, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.1603583097457886, "min": 0.9719936847686768, "max": 46.90187454223633, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.04793918480364872, "min": 0.04505280806500066, "max": 0.05555411185835537, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.33557429362554103, "min": 0.22221644743342148, "max": 0.41074146510800347, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.00807030579289858, "min": 0.0006559917398882524, "max": 0.00807030579289858, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.05649214055029006, "min": 0.004591942179217767, "max": 0.05723020702998838, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.396940391528577e-06, "min": 7.396940391528577e-06, "max": 0.00029544960151679995, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 5.177858274070004e-05, "min": 5.177858274070004e-05, "max": 0.0019440030519989999, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10246561428571428, "min": 0.10246561428571428, "max": 0.1984832, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.7172592999999999, "min": 0.7172592999999999, "max": 1.4443046000000002, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002563148671428573, "min": 0.0002563148671428573, "max": 0.00984847168, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0017942040700000012, "min": 0.0017942040700000012, "max": 0.0648052999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.022244691848754883, "min": 0.021590787917375565, "max": 0.7208585739135742, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15571284294128418, "min": 0.15300633013248444, "max": 2.883434295654297, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 481.55737704918033, "min": 481.55737704918033, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29375.0, "min": 15984.0, "max": 32897.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.2232557127221686, "min": -1.0000000521540642, "max": 1.3359626830886986, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 74.61859847605228, "min": -26.40100172907114, "max": 78.82179830223322, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.2232557127221686, "min": -1.0000000521540642, "max": 1.3359626830886986, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 74.61859847605228, "min": -26.40100172907114, "max": 78.82179830223322, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.11178126698169003, "min": 0.11178126698169003, "max": 15.677298514172435, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 6.818657285883091, "min": 6.4843866564915515, "max": 250.83677622675896, "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": "1694196798", "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": "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": "1694198998" }, "total": 2199.606937942, "count": 1, "self": 0.49237487199980023, "children": { "run_training.setup": { "total": 0.04467192799984332, "count": 1, "self": 0.04467192799984332 }, "TrainerController.start_learning": { "total": 2199.0698911420004, "count": 1, "self": 1.3869056659673333, "children": { "TrainerController._reset_env": { "total": 5.937399001999893, "count": 1, "self": 5.937399001999893 }, "TrainerController.advance": { "total": 2191.654674545034, "count": 63649, "self": 1.3692285960737536, "children": { "env_step": { "total": 1494.056498098872, "count": 63649, "self": 1382.775481912698, "children": { "SubprocessEnvManager._take_step": { "total": 110.4170719220383, "count": 63649, "self": 4.736353934110866, "children": { "TorchPolicy.evaluate": { "total": 105.68071798792744, "count": 62577, "self": 105.68071798792744 } } }, "workers": { "total": 0.8639442641356254, "count": 63649, "self": 0.0, "children": { "worker_root": { "total": 2194.6059844349197, "count": 63649, "is_parallel": true, "self": 923.434709709969, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0026307349999115104, "count": 1, "is_parallel": true, "self": 0.0006780280000384664, "children": { "_process_rank_one_or_two_observation": { "total": 0.001952706999873044, "count": 8, "is_parallel": true, "self": 0.001952706999873044 } } }, "UnityEnvironment.step": { "total": 0.054389394000281754, "count": 1, "is_parallel": true, "self": 0.0006154450002213707, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005376100002649764, "count": 1, "is_parallel": true, "self": 0.0005376100002649764 }, "communicator.exchange": { "total": 0.05119169999989026, "count": 1, "is_parallel": true, "self": 0.05119169999989026 }, "steps_from_proto": { "total": 0.002044638999905146, "count": 1, "is_parallel": true, "self": 0.00037213599898677785, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016725030009183683, "count": 8, "is_parallel": true, "self": 0.0016725030009183683 } } } } } } }, "UnityEnvironment.step": { "total": 1271.1712747249508, "count": 63648, "is_parallel": true, "self": 33.60163621597849, "children": { "UnityEnvironment._generate_step_input": { "total": 22.27848315797337, "count": 63648, "is_parallel": true, "self": 22.27848315797337 }, "communicator.exchange": { "total": 1111.8676038439094, "count": 63648, "is_parallel": true, "self": 1111.8676038439094 }, "steps_from_proto": { "total": 103.42355150708954, "count": 63648, "is_parallel": true, "self": 20.14628031750044, "children": { "_process_rank_one_or_two_observation": { "total": 83.2772711895891, "count": 509184, "is_parallel": true, "self": 83.2772711895891 } } } } } } } } } } }, "trainer_advance": { "total": 696.2289478500884, "count": 63649, "self": 2.7012917411316266, "children": { "process_trajectory": { "total": 113.47056337195909, "count": 63649, "self": 113.27730265995888, "children": { "RLTrainer._checkpoint": { "total": 0.19326071200021033, "count": 2, "self": 0.19326071200021033 } } }, "_update_policy": { "total": 580.0570927369977, "count": 235, "self": 430.2800087409969, "children": { "TorchPPOOptimizer.update": { "total": 149.77708399600078, "count": 15312, "self": 149.77708399600078 } } } } } } }, "trainer_threads": { "total": 1.089999386749696e-06, "count": 1, "self": 1.089999386749696e-06 }, "TrainerController._save_models": { "total": 0.09091083899966179, "count": 1, "self": 0.0009247199996025302, "children": { "RLTrainer._checkpoint": { "total": 0.08998611900005926, "count": 1, "self": 0.08998611900005926 } } } } } } }