{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4551127254962921, "min": 0.42451587319374084, "max": 1.4681589603424072, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13704.3544921875, "min": 12674.345703125, "max": 44538.0703125, "count": 33 }, "Pyramids.Step.mean": { "value": 989997.0, "min": 29985.0, "max": 989997.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989997.0, "min": 29985.0, "max": 989997.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3583263158798218, "min": -0.12268036603927612, "max": 0.3583263158798218, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 94.23982238769531, "min": -29.565967559814453, "max": 94.23982238769531, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.1676287055015564, "min": -0.002137561794370413, "max": 0.39246413111686707, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 44.08634948730469, "min": -0.5386655926704407, "max": 93.40646362304688, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06978873842745088, "min": 0.06415673648128502, "max": 0.07353385191934812, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0468310764117632, "min": 0.5692309833047722, "max": 1.0561341104319084, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015858215509150696, "min": 0.00012148027873194602, "max": 0.015858215509150696, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23787323263726043, "min": 0.0014577633447833522, "max": 0.23787323263726043, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.631801604024654e-06, "min": 7.631801604024654e-06, "max": 0.0002948532625851449, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011447702406036982, "min": 0.00011447702406036982, "max": 0.0033320345720804596, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10254390138264204, "min": 0.10254390138264204, "max": 0.19828442028985507, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5381585207396304, "min": 1.4785644177911046, "max": 2.317018990504748, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002641357481259371, "min": 0.0002641357481259371, "max": 0.009828613586956522, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003962036221889056, "min": 0.003962036221889056, "max": 0.11107674827586207, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009732798673212528, "min": 0.009732798673212528, "max": 0.2895022928714752, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1459919810295105, "min": 0.1374702751636505, "max": 2.3160183429718018, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 447.44262295081967, "min": 447.44262295081967, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27294.0, "min": 16400.0, "max": 32506.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3557803010354277, "min": -0.9999000514547031, "max": 1.3557803010354277, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 82.70259836316109, "min": -31.99600164592266, "max": 82.70259836316109, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3557803010354277, "min": -0.9999000514547031, "max": 1.3557803010354277, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 82.70259836316109, "min": -31.99600164592266, "max": 82.70259836316109, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04500335845027546, "min": 0.04500335845027546, "max": 6.013633237165563, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.7452048654668033, "min": 2.7452048654668033, "max": 102.23176503181458, "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": "1679256223", "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": "1679258261" }, "total": 2037.39379102, "count": 1, "self": 1.0532449780000661, "children": { "run_training.setup": { "total": 0.10305628800006161, "count": 1, "self": 0.10305628800006161 }, "TrainerController.start_learning": { "total": 2036.2374897539999, "count": 1, "self": 1.344994569973096, "children": { "TrainerController._reset_env": { "total": 7.089526703000047, "count": 1, "self": 7.089526703000047 }, "TrainerController.advance": { "total": 2027.6834260040268, "count": 63367, "self": 1.5168456190688175, "children": { "env_step": { "total": 1405.5409332989761, "count": 63367, "self": 1294.0317847089339, "children": { "SubprocessEnvManager._take_step": { "total": 110.67039413304451, "count": 63367, "self": 4.935321253107759, "children": { "TorchPolicy.evaluate": { "total": 105.73507287993675, "count": 62590, "self": 105.73507287993675 } } }, "workers": { "total": 0.8387544569977763, "count": 63367, "self": 0.0, "children": { "worker_root": { "total": 2031.5918928349324, "count": 63367, "is_parallel": true, "self": 857.9520871939576, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002019345999997313, "count": 1, "is_parallel": true, "self": 0.0006430669998280791, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013762790001692338, "count": 8, "is_parallel": true, "self": 0.0013762790001692338 } } }, "UnityEnvironment.step": { "total": 0.046445686999959435, "count": 1, "is_parallel": true, "self": 0.0005046019998644624, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045528000009653624, "count": 1, "is_parallel": true, "self": 0.00045528000009653624 }, "communicator.exchange": { "total": 0.04385661500009519, "count": 1, "is_parallel": true, "self": 0.04385661500009519 }, "steps_from_proto": { "total": 0.0016291899999032466, "count": 1, "is_parallel": true, "self": 0.0003568079996512097, "children": { "_process_rank_one_or_two_observation": { "total": 0.001272382000252037, "count": 8, "is_parallel": true, "self": 0.001272382000252037 } } } } } } }, "UnityEnvironment.step": { "total": 1173.6398056409748, "count": 63366, "is_parallel": true, "self": 31.26444371182606, "children": { "UnityEnvironment._generate_step_input": { "total": 24.075154972045766, "count": 63366, "is_parallel": true, "self": 24.075154972045766 }, "communicator.exchange": { "total": 1022.0349384380486, "count": 63366, "is_parallel": true, "self": 1022.0349384380486 }, "steps_from_proto": { "total": 96.26526851905442, "count": 63366, "is_parallel": true, "self": 20.737528234216597, "children": { "_process_rank_one_or_two_observation": { "total": 75.52774028483782, "count": 506928, "is_parallel": true, "self": 75.52774028483782 } } } } } } } } } } }, "trainer_advance": { "total": 620.6256470859819, "count": 63367, "self": 2.4029402969615603, "children": { "process_trajectory": { "total": 118.09035308102307, "count": 63367, "self": 117.80228540202302, "children": { "RLTrainer._checkpoint": { "total": 0.2880676790000507, "count": 2, "self": 0.2880676790000507 } } }, "_update_policy": { "total": 500.13235370799725, "count": 436, "self": 318.04088598905605, "children": { "TorchPPOOptimizer.update": { "total": 182.0914677189412, "count": 22851, "self": 182.0914677189412 } } } } } } }, "trainer_threads": { "total": 5.514999884326244e-06, "count": 1, "self": 5.514999884326244e-06 }, "TrainerController._save_models": { "total": 0.11953696199998376, "count": 1, "self": 0.002596451000044908, "children": { "RLTrainer._checkpoint": { "total": 0.11694051099993885, "count": 1, "self": 0.11694051099993885 } } } } } } }