{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.42359355092048645, "min": 0.40888747572898865, "max": 1.4004228115081787, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12728.138671875, "min": 12266.6240234375, "max": 42483.2265625, "count": 33 }, "Pyramids.Step.mean": { "value": 989990.0, "min": 29946.0, "max": 989990.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989990.0, "min": 29946.0, "max": 989990.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6292451620101929, "min": -0.10390913486480713, "max": 0.6292451620101929, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 177.4471435546875, "min": -25.146011352539062, "max": 177.4471435546875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.031041685491800308, "min": -0.037443701177835464, "max": 0.6632154583930969, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -8.753755569458008, "min": -10.40934944152832, "max": 159.83493041992188, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.047578030461186756, "min": 0.04317630058538535, "max": 0.050813903056439895, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.7136704569178013, "min": 0.41889273742941896, "max": 0.735434598599871, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015975262350144074, "min": 0.001656410757659233, "max": 0.01725054602277288, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2396289352521611, "min": 0.021018970428043793, "max": 0.2415076443188203, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.2490064168673327e-05, "min": 1.2490064168673327e-05, "max": 0.000491457890597311, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00018735096253009992, "min": 0.00018735096253009992, "max": 0.0058482997303401, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249799333333336, "min": 0.10249799333333336, "max": 0.19829157777777778, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5374699000000003, "min": 1.4781425000000001, "max": 2.5696599, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002595495339999999, "min": 0.0002595495339999999, "max": 0.009829328620000001, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003893243009999999, "min": 0.003893243009999999, "max": 0.11698902401, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.018557267263531685, "min": 0.018557267263531685, "max": 0.9921481609344482, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.27835899591445923, "min": 0.2696244716644287, "max": 8.929333686828613, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 299.3020833333333, "min": 299.3020833333333, "max": 992.8333333333334, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28733.0, "min": 16617.0, "max": 32712.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7006979038317998, "min": -0.9269867179294428, "max": 1.7006979038317998, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 163.26699876785278, "min": -30.35360173881054, "max": 163.26699876785278, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7006979038317998, "min": -0.9269867179294428, "max": 1.7006979038317998, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 163.26699876785278, "min": -30.35360173881054, "max": 163.26699876785278, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05697577516305804, "min": 0.05697577516305804, "max": 15.03711075291914, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.4696744156535715, "min": 5.4696744156535715, "max": 255.6308827996254, "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": "1689615837", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1689618318" }, "total": 2481.1984182369997, "count": 1, "self": 0.635651422000592, "children": { "run_training.setup": { "total": 0.04030262800006312, "count": 1, "self": 0.04030262800006312 }, "TrainerController.start_learning": { "total": 2480.522464186999, "count": 1, "self": 2.068419042390815, "children": { "TrainerController._reset_env": { "total": 5.8857769679998455, "count": 1, "self": 5.8857769679998455 }, "TrainerController.advance": { "total": 2472.4606981316083, "count": 63931, "self": 2.0060280439138296, "children": { "env_step": { "total": 1870.6341038389291, "count": 63931, "self": 1717.7245051247246, "children": { "SubprocessEnvManager._take_step": { "total": 151.64333255104248, "count": 63931, "self": 6.222321481040126, "children": { "TorchPolicy.evaluate": { "total": 145.42101107000235, "count": 62555, "self": 145.42101107000235 } } }, "workers": { "total": 1.2662661631620722, "count": 63931, "self": 0.0, "children": { "worker_root": { "total": 2473.5997564987556, "count": 63931, "is_parallel": true, "self": 908.4169780398461, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002722096000070451, "count": 1, "is_parallel": true, "self": 0.0007711350026511354, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019509609974193154, "count": 8, "is_parallel": true, "self": 0.0019509609974193154 } } }, "UnityEnvironment.step": { "total": 0.09119553199889197, "count": 1, "is_parallel": true, "self": 0.0006356610010698205, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000577361999603454, "count": 1, "is_parallel": true, "self": 0.000577361999603454 }, "communicator.exchange": { "total": 0.08747604999916803, "count": 1, "is_parallel": true, "self": 0.08747604999916803 }, "steps_from_proto": { "total": 0.0025064589990506647, "count": 1, "is_parallel": true, "self": 0.0004435260016180109, "children": { "_process_rank_one_or_two_observation": { "total": 0.002062932997432654, "count": 8, "is_parallel": true, "self": 0.002062932997432654 } } } } } } }, "UnityEnvironment.step": { "total": 1565.1827784589095, "count": 63930, "is_parallel": true, "self": 41.0472034522918, "children": { "UnityEnvironment._generate_step_input": { "total": 28.149523154739654, "count": 63930, "is_parallel": true, "self": 28.149523154739654 }, "communicator.exchange": { "total": 1364.7793758531952, "count": 63930, "is_parallel": true, "self": 1364.7793758531952 }, "steps_from_proto": { "total": 131.20667599868284, "count": 63930, "is_parallel": true, "self": 26.67348606786436, "children": { "_process_rank_one_or_two_observation": { "total": 104.53318993081848, "count": 511440, "is_parallel": true, "self": 104.53318993081848 } } } } } } } } } } }, "trainer_advance": { "total": 599.8205662487653, "count": 63931, "self": 3.736428418011201, "children": { "process_trajectory": { "total": 132.43415591975463, "count": 63931, "self": 132.19711207575529, "children": { "RLTrainer._checkpoint": { "total": 0.23704384399934497, "count": 2, "self": 0.23704384399934497 } } }, "_update_policy": { "total": 463.6499819109995, "count": 455, "self": 345.5020858910575, "children": { "TorchPPOOptimizer.update": { "total": 118.14789601994198, "count": 11286, "self": 118.14789601994198 } } } } } } }, "trainer_threads": { "total": 1.2870004866272211e-06, "count": 1, "self": 1.2870004866272211e-06 }, "TrainerController._save_models": { "total": 0.10756875799961563, "count": 1, "self": 0.0015640019992133602, "children": { "RLTrainer._checkpoint": { "total": 0.10600475600040227, "count": 1, "self": 0.10600475600040227 } } } } } } }