{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.1234384775161743, "min": 1.1234384775161743, "max": 3.295717477798462, "count": 2500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 22217.119140625, "min": 20717.66015625, "max": 122826.21875, "count": 2500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 62.61538461538461, "min": 49.96, "max": 999.0, "count": 2500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19536.0, "min": 16496.0, "max": 22876.0, "count": 2500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1825.7938991827937, "min": 1185.2835797668943, "max": 1856.6931527929742, "count": 2466 }, "SoccerTwos.Self-play.ELO.sum": { "value": 284823.8482725158, "min": 2377.148258356644, "max": 341921.96813963883, "count": 2466 }, "SoccerTwos.Step.mean": { "value": 24999932.0, "min": 9656.0, "max": 24999932.0, "count": 2500 }, "SoccerTwos.Step.sum": { "value": 24999932.0, "min": 9656.0, "max": 24999932.0, "count": 2500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.02974133938550949, "min": -1.5241801738739014, "max": 1.186009168624878, "count": 2500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -4.639648914337158, "min": -19.358009338378906, "max": 23.737735748291016, "count": 2500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.029097305610775948, "min": -1.6131078004837036, "max": 0.2732936143875122, "count": 2500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -4.539179801940918, "min": -22.36490821838379, "max": 23.503250122070312, "count": 2500 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2500 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2500 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.04126153924526312, "min": -0.6842105263157895, "max": 0.6175052600733021, "count": 2500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 6.436800122261047, "min": -64.91519975662231, "max": 54.3716002702713, "count": 2500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.04126153924526312, "min": -0.6842105263157895, "max": 0.6175052600733021, "count": 2500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 6.436800122261047, "min": -64.91519975662231, "max": 54.3716002702713, "count": 2500 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2500 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2500 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.035445474874368534, "min": 0.029532684385382407, "max": 0.04380931518039105, "count": 932 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.035445474874368534, "min": 0.029532684385382407, "max": 0.04380931518039105, "count": 932 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.05445720377163245, "min": 7.463254202079558e-07, "max": 0.7107169893689644, "count": 932 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.05445720377163245, "min": 7.463254202079558e-07, "max": 0.7107169893689644, "count": 932 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.05484463350895124, "min": 7.923651948453599e-07, "max": 6.126995172256079, "count": 932 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.05484463350895124, "min": 7.923651948453599e-07, "max": 6.126995172256079, "count": 932 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 4.2665994668000927e-07, "min": 4.2665994668000927e-07, "max": 0.0007991250561093682, "count": 932 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 4.2665994668000927e-07, "min": 4.2665994668000927e-07, "max": 0.0007991250561093682, "count": 932 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.10002788209440003, "min": 0.10002788209440003, "max": 0.15223480928544003, "count": 932 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.10002788209440003, "min": 0.10002788209440003, "max": 0.15223480928544003, "count": 932 }, "SoccerTwos.Policy.Beta.mean": { "value": 1.2660668000000057e-05, "min": 1.2660668000000057e-05, "max": 0.0049945425368, "count": 932 }, "SoccerTwos.Policy.Beta.sum": { "value": 1.2660668000000057e-05, "min": 1.2660668000000057e-05, "max": 0.0049945425368, "count": 932 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1719142258", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/gerard/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1719178175" }, "total": 35916.95696124504, "count": 1, "self": 0.21920562500599772, "children": { "run_training.setup": { "total": 0.01551381906028837, "count": 1, "self": 0.01551381906028837 }, "TrainerController.start_learning": { "total": 35916.72224180098, "count": 1, "self": 23.849299312452786, "children": { "TrainerController._reset_env": { "total": 3.327589773456566, "count": 81, "self": 3.327589773456566 }, "TrainerController.advance": { "total": 35889.401946845115, "count": 1696100, "self": 23.199814443127252, "children": { "env_step": { "total": 25058.3524640525, "count": 1696100, "self": 19046.92350125627, "children": { "SubprocessEnvManager._take_step": { "total": 5995.742158797686, "count": 1696100, "self": 137.29762796347495, "children": { "TorchPolicy.evaluate": { "total": 5858.444530834211, "count": 3138294, "self": 5858.444530834211 } } }, "workers": { "total": 15.686803998542018, "count": 1696100, "self": 0.0, "children": { "worker_root": { "total": 35883.286539411056, "count": 1696100, "is_parallel": true, "self": 19771.91978485475, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021088559878990054, "count": 2, "is_parallel": true, "self": 0.0007412320701405406, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013676239177584648, "count": 8, "is_parallel": true, "self": 0.0013676239177584648 } } }, "UnityEnvironment.step": { "total": 0.020144177018664777, "count": 1, "is_parallel": true, "self": 0.0004085621330887079, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00036455795634537935, "count": 1, "is_parallel": true, "self": 0.00036455795634537935 }, "communicator.exchange": { "total": 0.017962728976272047, "count": 1, "is_parallel": true, "self": 0.017962728976272047 }, "steps_from_proto": { "total": 0.0014083279529586434, "count": 2, "is_parallel": true, "self": 0.00032167299650609493, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010866549564525485, "count": 8, "is_parallel": true, "self": 0.0010866549564525485 } } } } } } }, "UnityEnvironment.step": { "total": 16111.253339246032, "count": 1696099, "is_parallel": true, "self": 757.80488253769, "children": { "UnityEnvironment._generate_step_input": { "total": 451.1183807726484, "count": 1696099, "is_parallel": true, "self": 451.1183807726484 }, "communicator.exchange": { "total": 12717.078414023272, "count": 1696099, "is_parallel": true, "self": 12717.078414023272 }, "steps_from_proto": { "total": 2185.2516619124217, "count": 3392198, "is_parallel": true, "self": 402.50320950429887, "children": { "_process_rank_one_or_two_observation": { "total": 1782.7484524081228, "count": 13568792, "is_parallel": true, "self": 1782.7484524081228 } } } } }, "steps_from_proto": { "total": 0.11341531027574092, "count": 160, "is_parallel": true, "self": 0.020305291982367635, "children": { "_process_rank_one_or_two_observation": { "total": 0.09311001829337329, "count": 640, "is_parallel": true, "self": 0.09311001829337329 } } } } } } } } }, "trainer_advance": { "total": 10807.849668349489, "count": 1696100, "self": 173.37280472845305, "children": { "process_trajectory": { "total": 3123.997487073415, "count": 1696100, "self": 3113.1751382783987, "children": { "RLTrainer._checkpoint": { "total": 10.822348795016296, "count": 50, "self": 10.822348795016296 } } }, "_update_policy": { "total": 7510.479376547621, "count": 932, "self": 2139.252104226616, "children": { "TorchPOCAOptimizer.update": { "total": 5371.227272321004, "count": 145728, "self": 5371.227272321004 } } } } } } }, "trainer_threads": { "total": 5.479669198393822e-07, "count": 1, "self": 5.479669198393822e-07 }, "TrainerController._save_models": { "total": 0.14340532198548317, "count": 1, "self": 0.0011018469231203198, "children": { "RLTrainer._checkpoint": { "total": 0.14230347506236285, "count": 1, "self": 0.14230347506236285 } } } } } } }