{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.40391188859939575, "min": 0.37802359461784363, "max": 1.4555761814117432, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12052.73046875, "min": 11223.728515625, "max": 44156.359375, "count": 33 }, "Pyramids.Step.mean": { "value": 989943.0, "min": 29952.0, "max": 989943.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989943.0, "min": 29952.0, "max": 989943.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.42684200406074524, "min": -0.11419922858476639, "max": 0.51920086145401, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 115.67418670654297, "min": -27.522014617919922, "max": 140.18423461914062, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.03045622631907463, "min": -0.0071845874190330505, "max": 0.2545965909957886, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 8.253637313842773, "min": -1.9470231533050537, "max": 61.3577766418457, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06958047147953253, "min": 0.06431832809660895, "max": 0.07191744222919541, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9741266007134555, "min": 0.49487013869581686, "max": 1.0479775922077335, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017853617543951057, "min": 0.0007625030939983567, "max": 0.017853617543951057, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2499506456153148, "min": 0.00915003712798028, "max": 0.2499506456153148, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.2880832849571435e-06, "min": 7.2880832849571435e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001020331659894, "min": 0.0001020331659894, "max": 0.0035071730309423994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10242932857142859, "min": 0.10242932857142859, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4340106000000001, "min": 1.3886848, "max": 2.5690576000000007, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002526899242857142, "min": 0.0002526899242857142, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035376589399999992, "min": 0.0035376589399999992, "max": 0.11692885423999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01333265844732523, "min": 0.01312931627035141, "max": 0.40482741594314575, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18665722012519836, "min": 0.18381042778491974, "max": 2.833791971206665, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 400.6578947368421, "min": 365.8641975308642, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30450.0, "min": 15984.0, "max": 35635.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4414131411988484, "min": -1.0000000521540642, "max": 1.5055078705282587, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 109.54739873111248, "min": -30.67400173842907, "max": 127.01079887151718, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4414131411988484, "min": -1.0000000521540642, "max": 1.5055078705282587, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 109.54739873111248, "min": -30.67400173842907, "max": 127.01079887151718, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05590870281479223, "min": 0.050498242676329075, "max": 7.938176089897752, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.24906141392421, "min": 3.9960728346486576, "max": 127.01081743836403, "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": "1678709652", "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": "1678712002" }, "total": 2350.324033859, "count": 1, "self": 0.48330757400026414, "children": { "run_training.setup": { "total": 0.09904302999984793, "count": 1, "self": 0.09904302999984793 }, "TrainerController.start_learning": { "total": 2349.7416832549998, "count": 1, "self": 1.7566871040435217, "children": { "TrainerController._reset_env": { "total": 5.891009650000115, "count": 1, "self": 5.891009650000115 }, "TrainerController.advance": { "total": 2341.993735896956, "count": 63767, "self": 1.7793547610608584, "children": { "env_step": { "total": 1695.0659784539546, "count": 63767, "self": 1566.594709085922, "children": { "SubprocessEnvManager._take_step": { "total": 127.41352077101988, "count": 63767, "self": 5.421622580980511, "children": { "TorchPolicy.evaluate": { "total": 121.99189819003936, "count": 62565, "self": 121.99189819003936 } } }, "workers": { "total": 1.0577485970127327, "count": 63767, "self": 0.0, "children": { "worker_root": { "total": 2343.9248496069617, "count": 63767, "is_parallel": true, "self": 913.3869382579587, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017990580001878698, "count": 1, "is_parallel": true, "self": 0.0006049479998182505, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011941100003696192, "count": 8, "is_parallel": true, "self": 0.0011941100003696192 } } }, "UnityEnvironment.step": { "total": 0.054069197999979224, "count": 1, "is_parallel": true, "self": 0.000672210999937306, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005332060000000638, "count": 1, "is_parallel": true, "self": 0.0005332060000000638 }, "communicator.exchange": { "total": 0.05071977600005084, "count": 1, "is_parallel": true, "self": 0.05071977600005084 }, "steps_from_proto": { "total": 0.0021440049999910116, "count": 1, "is_parallel": true, "self": 0.0004854559999785124, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016585490000124992, "count": 8, "is_parallel": true, "self": 0.0016585490000124992 } } } } } } }, "UnityEnvironment.step": { "total": 1430.537911349003, "count": 63766, "is_parallel": true, "self": 33.30274710401068, "children": { "UnityEnvironment._generate_step_input": { "total": 25.32507420596403, "count": 63766, "is_parallel": true, "self": 25.32507420596403 }, "communicator.exchange": { "total": 1269.2596071870357, "count": 63766, "is_parallel": true, "self": 1269.2596071870357 }, "steps_from_proto": { "total": 102.65048285199259, "count": 63766, "is_parallel": true, "self": 22.892166537978028, "children": { "_process_rank_one_or_two_observation": { "total": 79.75831631401456, "count": 510128, "is_parallel": true, "self": 79.75831631401456 } } } } } } } } } } }, "trainer_advance": { "total": 645.1484026819405, "count": 63767, "self": 3.1950089709696385, "children": { "process_trajectory": { "total": 127.56914203496626, "count": 63767, "self": 127.36160276196642, "children": { "RLTrainer._checkpoint": { "total": 0.20753927299983843, "count": 2, "self": 0.20753927299983843 } } }, "_update_policy": { "total": 514.3842516760046, "count": 447, "self": 326.9634286579701, "children": { "TorchPPOOptimizer.update": { "total": 187.42082301803453, "count": 22794, "self": 187.42082301803453 } } } } } } }, "trainer_threads": { "total": 1.0400003702670801e-06, "count": 1, "self": 1.0400003702670801e-06 }, "TrainerController._save_models": { "total": 0.10024956400002338, "count": 1, "self": 0.0015402180001728993, "children": { "RLTrainer._checkpoint": { "total": 0.09870934599985048, "count": 1, "self": 0.09870934599985048 } } } } } } }