{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.4052774906158447, "min": 1.2892510890960693, "max": 3.0776782035827637, "count": 1776 }, "SoccerTwos.Policy.Entropy.sum": { "value": 26711.513671875, "min": 22800.2578125, "max": 99646.8203125, "count": 1776 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 58.55952380952381, "min": 41.3109243697479, "max": 418.0, "count": 1776 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19676.0, "min": 16212.0, "max": 23060.0, "count": 1776 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1667.5504021710647, "min": 1219.4617375560056, "max": 1685.517318454644, "count": 1776 }, "SoccerTwos.Self-play.ELO.sum": { "value": 280148.4675647389, "min": 19628.174642454993, "max": 383278.0922806496, "count": 1776 }, "SoccerTwos.Step.mean": { "value": 19009998.0, "min": 1259086.0, "max": 19009998.0, "count": 1776 }, "SoccerTwos.Step.sum": { "value": 19009998.0, "min": 1259086.0, "max": 19009998.0, "count": 1776 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.04422707483172417, "min": -0.13672944903373718, "max": 0.1572747826576233, "count": 1776 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 7.4743757247924805, "min": -21.007102966308594, "max": 24.849414825439453, "count": 1776 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.04937828332185745, "min": -0.137770876288414, "max": 0.15660060942173004, "count": 1776 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 8.344929695129395, "min": -20.55115509033203, "max": 24.742897033691406, "count": 1776 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1776 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1776 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.09089940997975818, "min": -0.41454722152815926, "max": 0.38462451657941266, "count": 1776 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -15.362000286579132, "min": -59.69479990005493, "max": 59.61680006980896, "count": 1776 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.09089940997975818, "min": -0.41454722152815926, "max": 0.38462451657941266, "count": 1776 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -15.362000286579132, "min": -59.69479990005493, "max": 59.61680006980896, "count": 1776 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1776 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1776 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.014517392086812226, "min": 0.010807773818184312, "max": 0.025038353477915127, "count": 861 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.014517392086812226, "min": 0.010807773818184312, "max": 0.025038353477915127, "count": 861 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09137426341573397, "min": 0.015598694514483213, "max": 0.12954994613925616, "count": 861 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09137426341573397, "min": 0.015598694514483213, "max": 0.12954994613925616, "count": 861 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09285440072417259, "min": 0.015897353428105512, "max": 0.13209352617462475, "count": 861 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09285440072417259, "min": 0.015897353428105512, "max": 0.13209352617462475, "count": 861 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 861 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 861 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 861 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 861 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 861 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 861 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1684260937", "python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]", "command_line_arguments": "/home/isaac/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume", "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": "1684281566" }, "total": 20628.963836344, "count": 1, "self": 0.11666468600014923, "children": { "run_training.setup": { "total": 0.0072291229998882045, "count": 1, "self": 0.0072291229998882045 }, "TrainerController.start_learning": { "total": 20628.839942535, "count": 1, "self": 16.770210161750583, "children": { "TrainerController._reset_env": { "total": 3.5585314190111603, "count": 90, "self": 3.5585314190111603 }, "TrainerController.advance": { "total": 20608.31019457424, "count": 1227163, "self": 15.195070378093078, "children": { "env_step": { "total": 15046.286969933906, "count": 1227163, "self": 11616.913635806131, "children": { "SubprocessEnvManager._take_step": { "total": 3418.9883410701077, "count": 1227163, "self": 92.81003765157129, "children": { "TorchPolicy.evaluate": { "total": 3326.1783034185364, "count": 2229236, "self": 3326.1783034185364 } } }, "workers": { "total": 10.384993057667089, "count": 1227163, "self": 0.0, "children": { "worker_root": { "total": 20605.684158293247, "count": 1227163, "is_parallel": true, "self": 10857.862104096264, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002020928000092681, "count": 2, "is_parallel": true, "self": 0.0003930299999410636, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016278980001516175, "count": 8, "is_parallel": true, "self": 0.0016278980001516175 } } }, "UnityEnvironment.step": { "total": 0.018647951999810175, "count": 1, "is_parallel": true, "self": 0.0006229349992281641, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040039000032265903, "count": 1, "is_parallel": true, "self": 0.00040039000032265903 }, "communicator.exchange": { "total": 0.015967940000336966, "count": 1, "is_parallel": true, "self": 0.015967940000336966 }, "steps_from_proto": { "total": 0.0016566869999223854, "count": 2, "is_parallel": true, "self": 0.0002602020003905636, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013964849995318218, "count": 8, "is_parallel": true, "self": 0.0013964849995318218 } } } } } } }, "steps_from_proto": { "total": 0.1427363029870321, "count": 178, "is_parallel": true, "self": 0.021300865972989413, "children": { "_process_rank_one_or_two_observation": { "total": 0.12143543701404269, "count": 712, "is_parallel": true, "self": 0.12143543701404269 } } }, "UnityEnvironment.step": { "total": 9747.679317893995, "count": 1227162, "is_parallel": true, "self": 650.8921135476521, "children": { "UnityEnvironment._generate_step_input": { "total": 404.3111154488779, "count": 1227162, "is_parallel": true, "self": 404.3111154488779 }, "communicator.exchange": { "total": 6866.09120253997, "count": 1227162, "is_parallel": true, "self": 6866.09120253997 }, "steps_from_proto": { "total": 1826.3848863574958, "count": 2454324, "is_parallel": true, "self": 273.5305021671402, "children": { "_process_rank_one_or_two_observation": { "total": 1552.8543841903556, "count": 9817296, "is_parallel": true, "self": 1552.8543841903556 } } } } } } } } } } }, "trainer_advance": { "total": 5546.82815426224, "count": 1227163, "self": 118.4038750066511, "children": { "process_trajectory": { "total": 2090.1717815966877, "count": 1227163, "self": 2082.9535414856846, "children": { "RLTrainer._checkpoint": { "total": 7.21824011100307, "count": 36, "self": 7.21824011100307 } } }, "_update_policy": { "total": 3338.252497658901, "count": 862, "self": 2212.907532181779, "children": { "TorchPOCAOptimizer.update": { "total": 1125.344965477122, "count": 25840, "self": 1125.344965477122 } } } } } } }, "trainer_threads": { "total": 7.900016498751938e-07, "count": 1, "self": 7.900016498751938e-07 }, "TrainerController._save_models": { "total": 0.201005589999113, "count": 1, "self": 0.0017360519959765952, "children": { "RLTrainer._checkpoint": { "total": 0.1992695380031364, "count": 1, "self": 0.1992695380031364 } } } } } } }