{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3227108418941498, "min": 0.3227108418941498, "max": 1.4600976705551147, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9691.65234375, "min": 9691.65234375, "max": 44293.5234375, "count": 33 }, "Pyramids.Step.mean": { "value": 989922.0, "min": 29952.0, "max": 989922.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989922.0, "min": 29952.0, "max": 989922.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6206331849098206, "min": -0.12352751195430756, "max": 0.6526339054107666, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 175.63919067382812, "min": -29.276020050048828, "max": 186.00067138671875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.022035706788301468, "min": -0.00826762244105339, "max": 0.42271462082862854, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.236104965209961, "min": -2.2818636894226074, "max": 100.18336486816406, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07107731086871763, "min": 0.06559640576943777, "max": 0.07279403375421589, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9950823521620468, "min": 0.5030248105047932, "max": 1.0629226593768644, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01794988925752839, "min": 0.0013511177532911452, "max": 0.01794988925752839, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2512984496053975, "min": 0.01621341303949374, "max": 0.2642991977028193, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.578247473949998e-06, "min": 7.578247473949998e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010609546463529997, "min": 0.00010609546463529997, "max": 0.0036334228888590995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252605000000004, "min": 0.10252605000000004, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4353647000000005, "min": 1.3886848, "max": 2.6111409, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026235239500000003, "min": 0.00026235239500000003, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036729335300000002, "min": 0.0036729335300000002, "max": 0.12113297591000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008422180078923702, "min": 0.008422180078923702, "max": 0.3937978446483612, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11791052669286728, "min": 0.11791052669286728, "max": 2.756584882736206, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 300.1734693877551, "min": 300.1734693877551, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29417.0, "min": 15984.0, "max": 33286.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.642461840332169, "min": -1.0000000521540642, "max": 1.6465958187667031, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 159.31879851222038, "min": -29.317401729524136, "max": 159.84739807248116, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.642461840332169, "min": -1.0000000521540642, "max": 1.6465958187667031, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 159.31879851222038, "min": -29.317401729524136, "max": 159.84739807248116, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.026509514374936902, "min": 0.026509514374936902, "max": 7.754152173176408, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.5714228943688795, "min": 2.5346552167029586, "max": 124.06643477082253, "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": "1732809606", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1732811927" }, "total": 2321.242042645, "count": 1, "self": 0.4763939180002126, "children": { "run_training.setup": { "total": 0.05462130199998683, "count": 1, "self": 0.05462130199998683 }, "TrainerController.start_learning": { "total": 2320.711027425, "count": 1, "self": 1.2718071839826735, "children": { "TrainerController._reset_env": { "total": 2.221696536999957, "count": 1, "self": 2.221696536999957 }, "TrainerController.advance": { "total": 2317.132234603017, "count": 64268, "self": 1.2673407859597319, "children": { "env_step": { "total": 1633.0428183770464, "count": 64268, "self": 1491.676505775094, "children": { "SubprocessEnvManager._take_step": { "total": 140.60928710798885, "count": 64268, "self": 4.399733765998235, "children": { "TorchPolicy.evaluate": { "total": 136.2095533419906, "count": 62543, "self": 136.2095533419906 } } }, "workers": { "total": 0.7570254939633969, "count": 64268, "self": 0.0, "children": { "worker_root": { "total": 2315.703033100982, "count": 64268, "is_parallel": true, "self": 936.973240951974, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002455665999946177, "count": 1, "is_parallel": true, "self": 0.0007561449998547687, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016995210000914085, "count": 8, "is_parallel": true, "self": 0.0016995210000914085 } } }, "UnityEnvironment.step": { "total": 0.04552580200004286, "count": 1, "is_parallel": true, "self": 0.0006237400000372872, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004226840000001175, "count": 1, "is_parallel": true, "self": 0.0004226840000001175 }, "communicator.exchange": { "total": 0.042846660999998676, "count": 1, "is_parallel": true, "self": 0.042846660999998676 }, "steps_from_proto": { "total": 0.001632717000006778, "count": 1, "is_parallel": true, "self": 0.0003497060000654528, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012830109999413253, "count": 8, "is_parallel": true, "self": 0.0012830109999413253 } } } } } } }, "UnityEnvironment.step": { "total": 1378.7297921490078, "count": 64267, "is_parallel": true, "self": 32.23767399090161, "children": { "UnityEnvironment._generate_step_input": { "total": 22.92927933003989, "count": 64267, "is_parallel": true, "self": 22.92927933003989 }, "communicator.exchange": { "total": 1229.1501840140054, "count": 64267, "is_parallel": true, "self": 1229.1501840140054 }, "steps_from_proto": { "total": 94.41265481406083, "count": 64267, "is_parallel": true, "self": 18.46028050207667, "children": { "_process_rank_one_or_two_observation": { "total": 75.95237431198416, "count": 514136, "is_parallel": true, "self": 75.95237431198416 } } } } } } } } } } }, "trainer_advance": { "total": 682.8220754400111, "count": 64268, "self": 2.4383202939951616, "children": { "process_trajectory": { "total": 131.41275739901323, "count": 64268, "self": 131.20886084801293, "children": { "RLTrainer._checkpoint": { "total": 0.20389655100029813, "count": 2, "self": 0.20389655100029813 } } }, "_update_policy": { "total": 548.9709977470027, "count": 454, "self": 309.0866353279722, "children": { "TorchPPOOptimizer.update": { "total": 239.88436241903048, "count": 22794, "self": 239.88436241903048 } } } } } } }, "trainer_threads": { "total": 1.0000003385357559e-06, "count": 1, "self": 1.0000003385357559e-06 }, "TrainerController._save_models": { "total": 0.08528810100006012, "count": 1, "self": 0.0014909720002833637, "children": { "RLTrainer._checkpoint": { "total": 0.08379712899977676, "count": 1, "self": 0.08379712899977676 } } } } } } }