{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7540989518165588, "min": 0.7509713768959045, "max": 2.8544716835021973, "count": 40 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7631.4814453125, "min": 7178.53515625, "max": 29232.64453125, "count": 40 }, "SnowballTarget.Step.mean": { "value": 399992.0, "min": 9952.0, "max": 399992.0, "count": 40 }, "SnowballTarget.Step.sum": { "value": 399992.0, "min": 9952.0, "max": 399992.0, "count": 40 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.709442138671875, "min": 0.37919145822525024, "max": 13.748085975646973, "count": 40 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2673.34130859375, "min": 73.56314086914062, "max": 2813.556640625, "count": 40 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 40 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 40 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06753559517200497, "min": 0.06183863029844931, "max": 0.0765778742175362, "count": 40 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2701423806880199, "min": 0.24752901096484956, "max": 0.36887590581717833, "count": 40 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17932815506469968, "min": 0.1226801106183534, "max": 0.26482234918603714, "count": 40 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7173126202587987, "min": 0.4907204424734136, "max": 1.3241117459301857, "count": 40 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 3.891098702999994e-06, "min": 3.891098702999994e-06, "max": 0.000295941001353, "count": 40 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.5564394811999976e-05, "min": 1.5564394811999976e-05, "max": 0.0014425800191399996, "count": 40 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.101297, "min": 0.101297, "max": 0.19864700000000002, "count": 40 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.405188, "min": 0.405188, "max": 0.98086, "count": 40 }, "SnowballTarget.Policy.Beta.mean": { "value": 7.472029999999992e-05, "min": 7.472029999999992e-05, "max": 0.004932485299999999, "count": 40 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00029888119999999966, "min": 0.00029888119999999966, "max": 0.024044914, "count": 40 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 27.068181818181817, "min": 3.272727272727273, "max": 27.068181818181817, "count": 40 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1191.0, "min": 144.0, "max": 1469.0, "count": 40 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 27.068181818181817, "min": 3.272727272727273, "max": 27.068181818181817, "count": 40 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1191.0, "min": 144.0, "max": 1469.0, "count": 40 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679250873", "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 --force ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --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": "1679251765" }, "total": 891.8117125760002, "count": 1, "self": 0.8525653340002464, "children": { "run_training.setup": { "total": 0.09895160700011729, "count": 1, "self": 0.09895160700011729 }, "TrainerController.start_learning": { "total": 890.8601956349999, "count": 1, "self": 1.0520900850065118, "children": { "TrainerController._reset_env": { "total": 5.457522214000164, "count": 1, "self": 5.457522214000164 }, "TrainerController.advance": { "total": 884.1411102139932, "count": 36410, "self": 0.48831130802022926, "children": { "env_step": { "total": 883.652798905973, "count": 36410, "self": 636.8254537769212, "children": { "SubprocessEnvManager._take_step": { "total": 246.3199526060389, "count": 36410, "self": 4.135007505025669, "children": { "TorchPolicy.evaluate": { "total": 242.18494510101323, "count": 36410, "self": 242.18494510101323 } } }, "workers": { "total": 0.507392523012868, "count": 36410, "self": 0.0, "children": { "worker_root": { "total": 888.0916931100242, "count": 36410, "is_parallel": true, "self": 421.3944678570206, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019270519999281532, "count": 1, "is_parallel": true, "self": 0.0005869359995358536, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013401160003922996, "count": 10, "is_parallel": true, "self": 0.0013401160003922996 } } }, "UnityEnvironment.step": { "total": 0.04759080799999538, "count": 1, "is_parallel": true, "self": 0.0004915520000849938, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000303345000020272, "count": 1, "is_parallel": true, "self": 0.000303345000020272 }, "communicator.exchange": { "total": 0.04522522000002027, "count": 1, "is_parallel": true, "self": 0.04522522000002027 }, "steps_from_proto": { "total": 0.0015706909998698393, "count": 1, "is_parallel": true, "self": 0.0003334949999498349, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012371959999200044, "count": 10, "is_parallel": true, "self": 0.0012371959999200044 } } } } } } }, "UnityEnvironment.step": { "total": 466.6972252530036, "count": 36409, "is_parallel": true, "self": 18.36872623301565, "children": { "UnityEnvironment._generate_step_input": { "total": 10.109062429934966, "count": 36409, "is_parallel": true, "self": 10.109062429934966 }, "communicator.exchange": { "total": 376.9459000480133, "count": 36409, "is_parallel": true, "self": 376.9459000480133 }, "steps_from_proto": { "total": 61.273536542039665, "count": 36409, "is_parallel": true, "self": 11.93635280790022, "children": { "_process_rank_one_or_two_observation": { "total": 49.337183734139444, "count": 364090, "is_parallel": true, "self": 49.337183734139444 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0002868589999707183, "count": 1, "self": 0.0002868589999707183, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 877.583537931085, "count": 773222, "is_parallel": true, "self": 20.18850114104498, "children": { "process_trajectory": { "total": 487.6788062670373, "count": 773222, "is_parallel": true, "self": 485.30850892303783, "children": { "RLTrainer._checkpoint": { "total": 2.370297343999482, "count": 8, "is_parallel": true, "self": 2.370297343999482 } } }, "_update_policy": { "total": 369.71623052300265, "count": 181, "is_parallel": true, "self": 136.69635624398938, "children": { "TorchPPOOptimizer.update": { "total": 233.01987427901327, "count": 9228, "is_parallel": true, "self": 233.01987427901327 } } } } } } } } }, "TrainerController._save_models": { "total": 0.20918626299999232, "count": 1, "self": 0.002009664000070188, "children": { "RLTrainer._checkpoint": { "total": 0.20717659899992213, "count": 1, "self": 0.20717659899992213 } } } } } } }