{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.41574981808662415, "min": 0.41270533204078674, "max": 1.4435620307922363, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12525.7109375, "min": 12433.986328125, "max": 43791.8984375, "count": 33 }, "Pyramids.Step.mean": { "value": 989946.0, "min": 29952.0, "max": 989946.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989946.0, "min": 29952.0, "max": 989946.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5585272908210754, "min": -0.08787776529788971, "max": 0.5596181154251099, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 156.9461669921875, "min": -21.09066390991211, "max": 157.8123016357422, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.023766616359353065, "min": -0.011373305693268776, "max": 0.4616280496120453, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.67841911315918, "min": -2.9911794662475586, "max": 109.40584564208984, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06728463603699833, "min": 0.06513332866614226, "max": 0.0725590607138032, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9419849045179766, "min": 0.4913756623402527, "max": 1.0619016631389968, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016137953829365104, "min": 0.001391728315921715, "max": 0.016137953829365104, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22593135361111147, "min": 0.015309011475138867, "max": 0.2410771035404953, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.332890412878571e-06, "min": 7.332890412878571e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010266046578029999, "min": 0.00010266046578029999, "max": 0.0035076686307772, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10244426428571429, "min": 0.10244426428571429, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4342197, "min": 1.3886848, "max": 2.5692228000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002541820021428571, "min": 0.0002541820021428571, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00355854803, "min": 0.00355854803, "max": 0.11694535772, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010792193002998829, "min": 0.010792193002998829, "max": 0.4404819905757904, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15109069645404816, "min": 0.15109069645404816, "max": 3.0833740234375, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 330.19101123595505, "min": 330.19101123595505, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29387.0, "min": 15984.0, "max": 33005.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5798988617705496, "min": -1.0000000521540642, "max": 1.612279046760049, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 140.6109986975789, "min": -30.569001734256744, "max": 140.6109986975789, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5798988617705496, "min": -1.0000000521540642, "max": 1.612279046760049, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 140.6109986975789, "min": -30.569001734256744, "max": 140.6109986975789, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03750491829711965, "min": 0.03750491829711965, "max": 9.385949248448014, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.3379377284436487, "min": 3.302489072062599, "max": 150.17518797516823, "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": "1684197522", "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": "1684199619" }, "total": 2097.470821871, "count": 1, "self": 0.4815336909996404, "children": { "run_training.setup": { "total": 0.05863233600007334, "count": 1, "self": 0.05863233600007334 }, "TrainerController.start_learning": { "total": 2096.9306558440003, "count": 1, "self": 1.4177478410520052, "children": { "TrainerController._reset_env": { "total": 4.851348729000165, "count": 1, "self": 4.851348729000165 }, "TrainerController.advance": { "total": 2090.565889932948, "count": 63745, "self": 1.4317470949158633, "children": { "env_step": { "total": 1462.4287661810179, "count": 63745, "self": 1352.0446519870693, "children": { "SubprocessEnvManager._take_step": { "total": 109.55713331101629, "count": 63745, "self": 4.74511208913259, "children": { "TorchPolicy.evaluate": { "total": 104.8120212218837, "count": 62572, "self": 104.8120212218837 } } }, "workers": { "total": 0.8269808829322756, "count": 63745, "self": 0.0, "children": { "worker_root": { "total": 2092.108701539946, "count": 63745, "is_parallel": true, "self": 851.7665327339284, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002359723999916241, "count": 1, "is_parallel": true, "self": 0.0006536309999773948, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017060929999388463, "count": 8, "is_parallel": true, "self": 0.0017060929999388463 } } }, "UnityEnvironment.step": { "total": 0.04687190200002078, "count": 1, "is_parallel": true, "self": 0.0005282229999465926, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004895570000371663, "count": 1, "is_parallel": true, "self": 0.0004895570000371663 }, "communicator.exchange": { "total": 0.04411564699989867, "count": 1, "is_parallel": true, "self": 0.04411564699989867 }, "steps_from_proto": { "total": 0.0017384750001383509, "count": 1, "is_parallel": true, "self": 0.0003643250004188303, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013741499997195206, "count": 8, "is_parallel": true, "self": 0.0013741499997195206 } } } } } } }, "UnityEnvironment.step": { "total": 1240.3421688060178, "count": 63744, "is_parallel": true, "self": 31.571458374990243, "children": { "UnityEnvironment._generate_step_input": { "total": 22.504583360067727, "count": 63744, "is_parallel": true, "self": 22.504583360067727 }, "communicator.exchange": { "total": 1089.6709811079672, "count": 63744, "is_parallel": true, "self": 1089.6709811079672 }, "steps_from_proto": { "total": 96.59514596299255, "count": 63744, "is_parallel": true, "self": 19.59986346919345, "children": { "_process_rank_one_or_two_observation": { "total": 76.9952824937991, "count": 509952, "is_parallel": true, "self": 76.9952824937991 } } } } } } } } } } }, "trainer_advance": { "total": 626.7053766570143, "count": 63745, "self": 2.6664691879909697, "children": { "process_trajectory": { "total": 105.13788481702022, "count": 63745, "self": 104.9256982750203, "children": { "RLTrainer._checkpoint": { "total": 0.2121865419999267, "count": 2, "self": 0.2121865419999267 } } }, "_update_policy": { "total": 518.9010226520031, "count": 448, "self": 332.70575356905147, "children": { "TorchPPOOptimizer.update": { "total": 186.19526908295165, "count": 22818, "self": 186.19526908295165 } } } } } } }, "trainer_threads": { "total": 1.0070002645079512e-06, "count": 1, "self": 1.0070002645079512e-06 }, "TrainerController._save_models": { "total": 0.09566833400003816, "count": 1, "self": 0.0014591429999200045, "children": { "RLTrainer._checkpoint": { "total": 0.09420919100011815, "count": 1, "self": 0.09420919100011815 } } } } } } }