{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.31334707140922546, "min": 0.30935412645339966, "max": 1.39408540725708, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9385.37109375, "min": 9245.9765625, "max": 42290.9765625, "count": 33 }, "Pyramids.Step.mean": { "value": 989998.0, "min": 29969.0, "max": 989998.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989998.0, "min": 29969.0, "max": 989998.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5813647508621216, "min": -0.12382816523313522, "max": 0.6586253643035889, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 162.2007598876953, "min": -29.47110366821289, "max": 192.318603515625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0019777491688728333, "min": -0.009812026284635067, "max": 0.6466519236564636, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.5517920255661011, "min": -2.6590590476989746, "max": 153.9031524658203, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06847971635338015, "min": 0.06537009039350412, "max": 0.07386962259331205, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0271957453007023, "min": 0.5909569807464964, "max": 1.092487700687557, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014425657873115732, "min": 0.00026462271859441374, "max": 0.018428373553130463, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.216384868096736, "min": 0.0029108499045385513, "max": 0.2579972297438265, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.504977498373329e-06, "min": 7.504977498373329e-06, "max": 0.00029501025166325, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011257466247559994, "min": 0.00011257466247559994, "max": 0.0035071697309435, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250162666666666, "min": 0.10250162666666666, "max": 0.19833675, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5375244, "min": 1.4779451, "max": 2.5727063999999995, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025991250399999994, "min": 0.00025991250399999994, "max": 0.009833841325, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003898687559999999, "min": 0.003898687559999999, "max": 0.11692874434999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.015914293006062508, "min": 0.015914293006062508, "max": 0.4476422071456909, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.23871439695358276, "min": 0.2271513044834137, "max": 3.5811376571655273, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 306.2083333333333, "min": 282.0740740740741, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29396.0, "min": 16128.0, "max": 32802.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.652108315533648, "min": -0.9999625524505973, "max": 1.6993999867527574, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 158.6023982912302, "min": -31.998801678419113, "max": 183.5351985692978, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.652108315533648, "min": -0.9999625524505973, "max": 1.6993999867527574, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 158.6023982912302, "min": -31.998801678419113, "max": 183.5351985692978, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.051195131506877566, "min": 0.04807348390830965, "max": 8.44656971447608, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.914732624660246, "min": 4.721565438841935, "max": 143.59168514609337, "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": "1685092403", "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": "1685094654" }, "total": 2250.111906167999, "count": 1, "self": 0.4742552079987945, "children": { "run_training.setup": { "total": 0.0368981880001229, "count": 1, "self": 0.0368981880001229 }, "TrainerController.start_learning": { "total": 2249.6007527720003, "count": 1, "self": 1.4274300211282025, "children": { "TrainerController._reset_env": { "total": 4.282503080999959, "count": 1, "self": 4.282503080999959 }, "TrainerController.advance": { "total": 2243.7998358968716, "count": 64046, "self": 1.4643321889489016, "children": { "env_step": { "total": 1587.2225887509248, "count": 64046, "self": 1471.5691050439818, "children": { "SubprocessEnvManager._take_step": { "total": 114.78610137293526, "count": 64046, "self": 5.183988015075556, "children": { "TorchPolicy.evaluate": { "total": 109.60211335785971, "count": 62571, "self": 109.60211335785971 } } }, "workers": { "total": 0.8673823340077433, "count": 64046, "self": 0.0, "children": { "worker_root": { "total": 2243.9662676449434, "count": 64046, "is_parallel": true, "self": 894.6123245579674, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019796659998974064, "count": 1, "is_parallel": true, "self": 0.000650848999612208, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013288170002851984, "count": 8, "is_parallel": true, "self": 0.0013288170002851984 } } }, "UnityEnvironment.step": { "total": 0.09669417300028726, "count": 1, "is_parallel": true, "self": 0.000580125999476877, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005716140003642067, "count": 1, "is_parallel": true, "self": 0.0005716140003642067 }, "communicator.exchange": { "total": 0.09357961499972589, "count": 1, "is_parallel": true, "self": 0.09357961499972589 }, "steps_from_proto": { "total": 0.00196281800072029, "count": 1, "is_parallel": true, "self": 0.00040389799869444687, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015589200020258431, "count": 8, "is_parallel": true, "self": 0.0015589200020258431 } } } } } } }, "UnityEnvironment.step": { "total": 1349.353943086976, "count": 64045, "is_parallel": true, "self": 32.37307871989924, "children": { "UnityEnvironment._generate_step_input": { "total": 25.458546876033324, "count": 64045, "is_parallel": true, "self": 25.458546876033324 }, "communicator.exchange": { "total": 1186.4374435568798, "count": 64045, "is_parallel": true, "self": 1186.4374435568798 }, "steps_from_proto": { "total": 105.08487393416362, "count": 64045, "is_parallel": true, "self": 21.895063486982508, "children": { "_process_rank_one_or_two_observation": { "total": 83.18981044718112, "count": 512360, "is_parallel": true, "self": 83.18981044718112 } } } } } } } } } } }, "trainer_advance": { "total": 655.1129149569979, "count": 64046, "self": 2.784611811081959, "children": { "process_trajectory": { "total": 115.83891026491801, "count": 64046, "self": 115.62544336891824, "children": { "RLTrainer._checkpoint": { "total": 0.21346689599977253, "count": 2, "self": 0.21346689599977253 } } }, "_update_policy": { "total": 536.4893928809979, "count": 453, "self": 350.5962974689983, "children": { "TorchPPOOptimizer.update": { "total": 185.89309541199964, "count": 22785, "self": 185.89309541199964 } } } } } } }, "trainer_threads": { "total": 9.479999789618887e-07, "count": 1, "self": 9.479999789618887e-07 }, "TrainerController._save_models": { "total": 0.09098282500053756, "count": 1, "self": 0.0012675340003625024, "children": { "RLTrainer._checkpoint": { "total": 0.08971529100017506, "count": 1, "self": 0.08971529100017506 } } } } } } }