{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.2170403003692627, "min": 3.210686683654785, "max": 3.295807123184204, "count": 600 }, "SoccerTwos.Policy.Entropy.sum": { "value": 117563.5234375, "min": 738.2604370117188, "max": 306377.59375, "count": 600 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 279.1666666666667, "min": 164.06666666666666, "max": 999.0, "count": 600 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20100.0, "min": 11988.0, "max": 35964.0, "count": 600 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1260.4669994441715, "min": 1188.3435977384117, "max": 1269.966926038006, "count": 542 }, "SoccerTwos.Self-play.ELO.sum": { "value": 40334.94398221349, "min": 2377.0453883335113, "max": 57594.24333100366, "count": 542 }, "SoccerTwos.Step.mean": { "value": 5999842.0, "min": 9737.0, "max": 5999842.0, "count": 600 }, "SoccerTwos.Step.sum": { "value": 5999842.0, "min": 9737.0, "max": 5999842.0, "count": 600 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.03188270702958107, "min": -0.004458076320588589, "max": 0.07110652327537537, "count": 600 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 1.1158947944641113, "min": -0.11116751283407211, "max": 2.630938768386841, "count": 600 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.033267438411712646, "min": -0.0063375565223395824, "max": 0.07110591232776642, "count": 600 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 1.1643602848052979, "min": -0.1711140275001526, "max": 2.630913734436035, "count": 600 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 600 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 600 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.3726857134274074, "min": -0.6566933333873749, "max": 0.4008285701274872, "count": 600 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 13.043999969959259, "min": -16.611600041389465, "max": 13.043999969959259, "count": 600 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.3726857134274074, "min": -0.6566933333873749, "max": 0.4008285701274872, "count": 600 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 13.043999969959259, "min": -16.611600041389465, "max": 13.043999969959259, "count": 600 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 600 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 600 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.005646272817587791, "min": 0.0041480708499875615, "max": 0.006441801851421284, "count": 14 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.005646272817587791, "min": 0.0041480708499875615, "max": 0.006441801851421284, "count": 14 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.008752069047962626, "min": 0.0014911757898516953, "max": 0.008752069047962626, "count": 14 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.008752069047962626, "min": 0.0014911757898516953, "max": 0.008752069047962626, "count": 14 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.008801194575304786, "min": 0.001491923942618693, "max": 0.008801194575304786, "count": 14 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.008801194575304786, "min": 0.001491923942618693, "max": 0.008801194575304786, "count": 14 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 1.279289573573335e-05, "min": 1.279289573573335e-05, "max": 0.0002795118068294001, "count": 14 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 1.279289573573335e-05, "min": 1.279289573573335e-05, "max": 0.0002795118068294001, "count": 14 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.10639640000000004, "min": 0.10639640000000004, "max": 0.23975590000000002, "count": 14 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.10639640000000004, "min": 0.10639640000000004, "max": 0.23975590000000002, "count": 14 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.0002227869066666669, "min": 0.0002227869066666669, "max": 0.00465921294, "count": 14 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.0002227869066666669, "min": 0.0002227869066666669, "max": 0.00465921294, "count": 14 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1676324669", "python_version": "3.9.0 (default, Nov 15 2020, 14:28:56) \n[GCC 7.3.0]", "command_line_arguments": "/home/olav/dev/anaconda3/envs/rl/bin/mlagents-learn config.yaml --env=./ml-agents/training-envs-executables/SoccerTwos.x86_64 --run-id=keano013 --no-graphics --results-dir=./ml-agents/results --force", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0", "numpy_version": "1.21.2", "end_time_seconds": "1676328187" }, "total": 3517.620322005, "count": 1, "self": 0.21865244500031622, "children": { "run_training.setup": { "total": 0.010919570000169188, "count": 1, "self": 0.010919570000169188 }, "TrainerController.start_learning": { "total": 3517.3907499899997, "count": 1, "self": 5.51049359318813, "children": { "TrainerController._reset_env": { "total": 8.799978996998561, "count": 30, "self": 8.799978996998561 }, "TrainerController.advance": { "total": 3502.9357951218126, "count": 410687, "self": 5.299476482802675, "children": { "env_step": { "total": 2065.087746583087, "count": 410687, "self": 675.9367244590569, "children": { "SubprocessEnvManager._take_step": { "total": 1386.1235329561441, "count": 417719, "self": 34.93620267124015, "children": { "TorchPolicy.evaluate": { "total": 1351.187330284904, "count": 828506, "self": 1351.187330284904 } } }, "workers": { "total": 3.0274891678861877, "count": 410687, "self": 0.0, "children": { "worker_root": { "total": 10540.580895370504, "count": 417683, "is_parallel": true, "self": 7740.676774716561, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005605342000080782, "count": 6, "is_parallel": true, "self": 0.0015197940003872645, "children": { "_process_rank_one_or_two_observation": { "total": 0.004085547999693517, "count": 24, "is_parallel": true, "self": 0.004085547999693517 } } }, "UnityEnvironment.step": { "total": 0.04558812100003706, "count": 3, "is_parallel": true, "self": 0.0014165630000206875, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0011156590001064615, "count": 3, "is_parallel": true, "self": 0.0011156590001064615 }, "communicator.exchange": { "total": 0.038757408999799736, "count": 3, "is_parallel": true, "self": 0.038757408999799736 }, "steps_from_proto": { "total": 0.004298490000110178, "count": 6, "is_parallel": true, "self": 0.0008910510009627615, "children": { "_process_rank_one_or_two_observation": { "total": 0.0034074389991474163, "count": 24, "is_parallel": true, "self": 0.0034074389991474163 } } } } } } }, "UnityEnvironment.step": { "total": 2799.76479901494, "count": 417680, "is_parallel": true, "self": 192.63248214207442, "children": { "UnityEnvironment._generate_step_input": { "total": 127.23243516599246, "count": 417680, "is_parallel": true, "self": 127.23243516599246 }, "communicator.exchange": { "total": 1882.6873260320533, "count": 417680, "is_parallel": true, "self": 1882.6873260320533 }, "steps_from_proto": { "total": 597.2125556748197, "count": 835360, "is_parallel": true, "self": 114.40165957079125, "children": { "_process_rank_one_or_two_observation": { "total": 482.8108961040284, "count": 3341440, "is_parallel": true, "self": 482.8108961040284 } } } } }, "steps_from_proto": { "total": 0.1393216390026737, "count": 174, "is_parallel": true, "self": 0.02627534199632464, "children": { "_process_rank_one_or_two_observation": { "total": 0.11304629700634905, "count": 696, "is_parallel": true, "self": 0.11304629700634905 } } } } } } } } }, "trainer_advance": { "total": 1432.5485720559225, "count": 410687, "self": 59.45871270904013, "children": { "process_trajectory": { "total": 369.51333314588237, "count": 410687, "self": 367.77558605588297, "children": { "RLTrainer._checkpoint": { "total": 1.7377470899994023, "count": 12, "self": 1.7377470899994023 } } }, "_update_policy": { "total": 1003.576526201, "count": 14, "self": 650.0343098029932, "children": { "TorchPOCAOptimizer.update": { "total": 353.54221639800676, "count": 840, "self": 353.54221639800676 } } } } } } }, "trainer_threads": { "total": 6.000000212225132e-07, "count": 1, "self": 6.000000212225132e-07 }, "TrainerController._save_models": { "total": 0.1444816780003748, "count": 1, "self": 0.001207311000143818, "children": { "RLTrainer._checkpoint": { "total": 0.143274367000231, "count": 1, "self": 0.143274367000231 } } } } } } }