{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.7206080555915833, "min": 0.7206080555915833, "max": 1.463507056236267, "count": 16 }, "Pyramids.Policy.Entropy.sum": { "value": 21549.0625, "min": 21549.0625, "max": 44396.94921875, "count": 16 }, "Pyramids.Step.mean": { "value": 479997.0, "min": 29952.0, "max": 479997.0, "count": 16 }, "Pyramids.Step.sum": { "value": 479997.0, "min": 29952.0, "max": 479997.0, "count": 16 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.1874702423810959, "min": -0.08975708484649658, "max": 0.21668332815170288, "count": 16 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 46.86756134033203, "min": -21.631458282470703, "max": 55.037567138671875, "count": 16 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.020687760785222054, "min": 0.011550032533705235, "max": 0.3298008143901825, "count": 16 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.171940326690674, "min": 2.9337081909179688, "max": 78.16279602050781, "count": 16 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06982567651945372, "min": 0.06627717401944498, "max": 0.07250926116765993, "count": 16 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9775594712723521, "min": 0.5003745376400719, "max": 1.087638917514899, "count": 16 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.011309595999003195, "min": 0.00059722600205701, "max": 0.011309595999003195, "count": 16 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.15833434398604473, "min": 0.004239162832879953, "max": 0.1591349841777022, "count": 16 }, "Pyramids.Policy.LearningRate.mean": { "value": 2.0463264607514286e-05, "min": 2.0463264607514286e-05, "max": 0.00029030126037577137, "count": 16 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0002864857045052, "min": 0.0002864857045052, "max": 0.002607855430715, "count": 16 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10682105714285713, "min": 0.10682105714285713, "max": 0.19676708571428575, "count": 16 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4954947999999997, "min": 1.3382272, "max": 2.1692849999999995, "count": 16 }, "Pyramids.Policy.Beta.mean": { "value": 0.0006914236085714285, "min": 0.0006914236085714285, "max": 0.00967703186285714, "count": 16 }, "Pyramids.Policy.Beta.sum": { "value": 0.00967993052, "min": 0.00967993052, "max": 0.0869715715, "count": 16 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.02160811610519886, "min": 0.021184373646974564, "max": 0.41403502225875854, "count": 16 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.30251362919807434, "min": 0.30251362919807434, "max": 2.898245096206665, "count": 16 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 607.734693877551, "min": 607.734693877551, "max": 999.0, "count": 16 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29779.0, "min": 15984.0, "max": 32077.0, "count": 16 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.7957039652764797, "min": -1.0000000521540642, "max": 0.8623135967010801, "count": 16 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 39.785198263823986, "min": -32.000001668930054, "max": 39.785198263823986, "count": 16 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.7957039652764797, "min": -1.0000000521540642, "max": 0.8623135967010801, "count": 16 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 39.785198263823986, "min": -32.000001668930054, "max": 39.785198263823986, "count": 16 }, "Pyramids.Policy.RndReward.mean": { "value": 0.13523935666307807, "min": 0.13523935666307807, "max": 8.042321138083935, "count": 16 }, "Pyramids.Policy.RndReward.sum": { "value": 6.7619678331539035, "min": 6.144896588288248, "max": 128.67713820934296, "count": 16 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 16 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 16 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1671883066", "python_version": "3.10.1 (v3.10.1:2cd268a3a9, Dec 6 2021, 14:28:59) [Clang 13.0.0 (clang-1300.0.29.3)]", "command_line_arguments": "/Library/Frameworks/Python.framework/Versions/3.10/bin/mlagents-learn config/ppo/PyramidsRND.yaml --env=Project/RL_pyramids --run-id=Run1 --no-graphics --force", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0", "numpy_version": "1.23.4", "end_time_seconds": "1671883938" }, "total": 872.4381035419938, "count": 1, "self": 0.27622999998857267, "children": { "run_training.setup": { "total": 0.015691249995143153, "count": 1, "self": 0.015691249995143153 }, "TrainerController.start_learning": { "total": 872.14618229201, "count": 1, "self": 0.27930660110723693, "children": { "TrainerController._reset_env": { "total": 1.0129065410001203, "count": 1, "self": 1.0129065410001203 }, "TrainerController.advance": { "total": 870.7933363169141, "count": 31650, "self": 0.2454130093101412, "children": { "env_step": { "total": 708.8848299748206, "count": 31650, "self": 691.3094396025699, "children": { "SubprocessEnvManager._take_step": { "total": 17.35078969274764, "count": 31650, "self": 0.8142677712166915, "children": { "TorchPolicy.evaluate": { "total": 16.536521921530948, "count": 31315, "self": 3.034965333165019, "children": { "TorchPolicy.sample_actions": { "total": 13.50155658836593, "count": 31315, "self": 13.50155658836593 } } } } }, "workers": { "total": 0.2246006795030553, "count": 31650, "self": 0.0, "children": { "worker_root": { "total": 870.6194659991743, "count": 31650, "is_parallel": true, "self": 198.97912739841559, "children": { "steps_from_proto": { "total": 0.00075270798697602, "count": 1, "is_parallel": true, "self": 0.00016141899686772376, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005912889901082963, "count": 8, "is_parallel": true, "self": 0.0005912889901082963 } } }, "UnityEnvironment.step": { "total": 671.6395858927717, "count": 31650, "is_parallel": true, "self": 2.0083917222364107, "children": { "UnityEnvironment._generate_step_input": { "total": 10.448567773491959, "count": 31650, "is_parallel": true, "self": 10.448567773491959 }, "communicator.exchange": { "total": 639.7029029303667, "count": 31650, "is_parallel": true, "self": 639.7029029303667 }, "steps_from_proto": { "total": 19.47972346667666, "count": 31650, "is_parallel": true, "self": 3.430760283721611, "children": { "_process_rank_one_or_two_observation": { "total": 16.04896318295505, "count": 253200, "is_parallel": true, "self": 16.04896318295505 } } } } } } } } } } }, "trainer_advance": { "total": 161.66309333278332, "count": 31650, "self": 0.44237450808577705, "children": { "process_trajectory": { "total": 31.569715538658784, "count": 31650, "self": 31.5208572466654, "children": { "RLTrainer._checkpoint": { "total": 0.04885829199338332, "count": 1, "self": 0.04885829199338332 } } }, "_update_policy": { "total": 129.65100328603876, "count": 205, "self": 38.5087801283662, "children": { "TorchPPOOptimizer.update": { "total": 91.14222315767256, "count": 11442, "self": 91.14222315767256 } } } } } } }, "trainer_threads": { "total": 3.749883035197854e-07, "count": 1, "self": 3.749883035197854e-07 }, "TrainerController._save_models": { "total": 0.06063245800032746, "count": 1, "self": 0.000818957996671088, "children": { "RLTrainer._checkpoint": { "total": 0.05981350000365637, "count": 1, "self": 0.05981350000365637 } } } } } } }