{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.1605914682149887, "min": 0.15174803137779236, "max": 1.3826720714569092, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4810.03564453125, "min": 4520.87744140625, "max": 41944.73828125, "count": 100 }, "Pyramids.Step.mean": { "value": 2999935.0, "min": 29984.0, "max": 2999935.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999935.0, "min": 29984.0, "max": 2999935.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7312646508216858, "min": -0.08786865323781967, "max": 0.864769458770752, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 212.06674194335938, "min": -21.088476181030273, "max": 264.61944580078125, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.031307727098464966, "min": -0.023307139053940773, "max": 0.28635692596435547, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 9.079240798950195, "min": -6.316234588623047, "max": 68.15294647216797, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.069431693604981, "min": 0.06259889548310472, "max": 0.07356465743699421, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9720437104697339, "min": 0.5769289815857017, "max": 1.1034698615549132, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014536273691365275, "min": 0.0007999930532062535, "max": 0.015559507014115109, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20350783167911385, "min": 0.010399909691681294, "max": 0.2178330981976115, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4781780787357106e-06, "min": 1.4781780787357106e-06, "max": 0.00029828360057213336, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.0694493102299947e-05, "min": 2.0694493102299947e-05, "max": 0.004072884842371767, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10049269285714287, "min": 0.10049269285714287, "max": 0.19942786666666668, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4068977, "min": 1.4068977, "max": 2.8576282333333336, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.922001642857131e-05, "min": 5.922001642857131e-05, "max": 0.00994284388, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008290802299999984, "min": 0.0008290802299999984, "max": 0.13577706051, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.004602502100169659, "min": 0.004342348780483007, "max": 0.40666961669921875, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.06443502753973007, "min": 0.06079288199543953, "max": 3.25335693359375, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 261.6694915254237, "min": 212.27007299270073, "max": 995.2258064516129, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30877.0, "min": 16399.0, "max": 33010.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.738213657696023, "min": -0.9315290823578835, "max": 1.7781703653158965, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 203.37099795043468, "min": -28.877401553094387, "max": 241.09919920563698, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.738213657696023, "min": -0.9315290823578835, "max": 1.7781703653158965, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 203.37099795043468, "min": -28.877401553094387, "max": 241.09919920563698, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.01263972351655392, "min": 0.009993327900862341, "max": 8.080028551466325, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.4788476514368085, "min": 1.3467253648414044, "max": 137.36048537492752, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1686415716", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1686423339" }, "total": 7622.912448516, "count": 1, "self": 0.5384192190012982, "children": { "run_training.setup": { "total": 0.03806848399926821, "count": 1, "self": 0.03806848399926821 }, "TrainerController.start_learning": { "total": 7622.3359608129995, "count": 1, "self": 5.0599678118469456, "children": { "TrainerController._reset_env": { "total": 4.000870640999892, "count": 1, "self": 4.000870640999892 }, "TrainerController.advance": { "total": 7613.119245360153, "count": 194176, "self": 5.130799042612125, "children": { "env_step": { "total": 5552.522010477777, "count": 194176, "self": 5160.800616726953, "children": { "SubprocessEnvManager._take_step": { "total": 388.7483901792739, "count": 194176, "self": 16.048350887313973, "children": { "TorchPolicy.evaluate": { "total": 372.7000392919599, "count": 187549, "self": 372.7000392919599 } } }, "workers": { "total": 2.97300357155018, "count": 194176, "self": 0.0, "children": { "worker_root": { "total": 7603.66474228549, "count": 194176, "is_parallel": true, "self": 2835.15157436121, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019769840000662953, "count": 1, "is_parallel": true, "self": 0.0006528850017275545, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013240989983387408, "count": 8, "is_parallel": true, "self": 0.0013240989983387408 } } }, "UnityEnvironment.step": { "total": 0.05422819199975493, "count": 1, "is_parallel": true, "self": 0.0005977529999654507, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006190009999045287, "count": 1, "is_parallel": true, "self": 0.0006190009999045287 }, "communicator.exchange": { "total": 0.05116591499972856, "count": 1, "is_parallel": true, "self": 0.05116591499972856 }, "steps_from_proto": { "total": 0.0018455230001563905, "count": 1, "is_parallel": true, "self": 0.00037350999900809256, "children": { "_process_rank_one_or_two_observation": { "total": 0.001472013001148298, "count": 8, "is_parallel": true, "self": 0.001472013001148298 } } } } } } }, "UnityEnvironment.step": { "total": 4768.51316792428, "count": 194175, "is_parallel": true, "self": 100.4952850657155, "children": { "UnityEnvironment._generate_step_input": { "total": 74.97257792979872, "count": 194175, "is_parallel": true, "self": 74.97257792979872 }, "communicator.exchange": { "total": 4266.509113628733, "count": 194175, "is_parallel": true, "self": 4266.509113628733 }, "steps_from_proto": { "total": 326.53619130003335, "count": 194175, "is_parallel": true, "self": 68.81499423792684, "children": { "_process_rank_one_or_two_observation": { "total": 257.7211970621065, "count": 1553400, "is_parallel": true, "self": 257.7211970621065 } } } } } } } } } } }, "trainer_advance": { "total": 2055.466435839764, "count": 194176, "self": 9.878107901705334, "children": { "process_trajectory": { "total": 373.4966683280627, "count": 194176, "self": 372.5729026220615, "children": { "RLTrainer._checkpoint": { "total": 0.923765706001177, "count": 6, "self": 0.923765706001177 } } }, "_update_policy": { "total": 1672.091659609996, "count": 1405, "self": 1045.91738557982, "children": { "TorchPPOOptimizer.update": { "total": 626.1742740301761, "count": 68322, "self": 626.1742740301761 } } } } } } }, "trainer_threads": { "total": 1.0879994079004973e-06, "count": 1, "self": 1.0879994079004973e-06 }, "TrainerController._save_models": { "total": 0.15587591199982853, "count": 1, "self": 0.002404238999588415, "children": { "RLTrainer._checkpoint": { "total": 0.15347167300024012, "count": 1, "self": 0.15347167300024012 } } } } } } }