{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.6419099569320679, "min": 1.6419099569320679, "max": 3.295757293701172, "count": 583 }, "SoccerTwos.Policy.Entropy.sum": { "value": 30841.63671875, "min": 12586.9140625, "max": 105464.234375, "count": 583 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 47.84313725490196, "min": 38.13953488372093, "max": 999.0, "count": 583 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19520.0, "min": 14620.0, "max": 27144.0, "count": 583 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1589.8209476614618, "min": 1195.0311493738434, "max": 1624.212424863242, "count": 578 }, "SoccerTwos.Self-play.ELO.sum": { "value": 324323.4733229382, "min": 2391.5608596359775, "max": 371390.8554079746, "count": 578 }, "SoccerTwos.Step.mean": { "value": 5829938.0, "min": 9588.0, "max": 5829938.0, "count": 583 }, "SoccerTwos.Step.sum": { "value": 5829938.0, "min": 9588.0, "max": 5829938.0, "count": 583 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.031814150512218475, "min": -0.12275109440088272, "max": 0.16648373007774353, "count": 583 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -6.5219011306762695, "min": -24.427467346191406, "max": 24.573871612548828, "count": 583 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.03891433775424957, "min": -0.12549638748168945, "max": 0.16274768114089966, "count": 583 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -7.977438926696777, "min": -24.97378158569336, "max": 25.92108154296875, "count": 583 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 583 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 583 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.11726341596463831, "min": -0.7142857142857143, "max": 0.5206204090191393, "count": 583 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -24.039000272750854, "min": -62.41359996795654, "max": 65.96000003814697, "count": 583 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.11726341596463831, "min": -0.7142857142857143, "max": 0.5206204090191393, "count": 583 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -24.039000272750854, "min": -62.41359996795654, "max": 65.96000003814697, "count": 583 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 583 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 583 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.015221605898113921, "min": 0.01092262822912744, "max": 0.023748412328617026, "count": 280 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015221605898113921, "min": 0.01092262822912744, "max": 0.023748412328617026, "count": 280 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.11137958690524101, "min": 0.0008556886556713531, "max": 0.12397084087133407, "count": 280 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.11137958690524101, "min": 0.0008556886556713531, "max": 0.12397084087133407, "count": 280 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11331250021855037, "min": 0.0008961730782175437, "max": 0.12599406515558562, "count": 280 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11331250021855037, "min": 0.0008961730782175437, "max": 0.12599406515558562, "count": 280 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 280 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 280 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 280 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 280 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 280 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 280 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1701285198", "python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul 5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\user\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1701333182" }, "total": 47982.489849000005, "count": 1, "self": 0.24068759998772293, "children": { "run_training.setup": { "total": 0.12456259998725727, "count": 1, "self": 0.12456259998725727 }, "TrainerController.start_learning": { "total": 47982.12459880003, "count": 1, "self": 27.5780346042593, "children": { "TrainerController._reset_env": { "total": 9.155859399819747, "count": 30, "self": 9.155859399819747 }, "TrainerController.advance": { "total": 47944.85520439595, "count": 399099, "self": 29.803272486140486, "children": { "env_step": { "total": 20304.866591629398, "count": 399099, "self": 14576.87355039746, "children": { "SubprocessEnvManager._take_step": { "total": 5712.371078997327, "count": 399099, "self": 165.52294571546372, "children": { "TorchPolicy.evaluate": { "total": 5546.848133281863, "count": 735372, "self": 5546.848133281863 } } }, "workers": { "total": 15.621962234610692, "count": 399099, "self": 0.0, "children": { "worker_root": { "total": 47936.45714417251, "count": 399099, "is_parallel": true, "self": 36596.77760363015, "children": { "steps_from_proto": { "total": 0.15410140017047524, "count": 60, "is_parallel": true, "self": 0.03087789920391515, "children": { "_process_rank_one_or_two_observation": { "total": 0.1232235009665601, "count": 240, "is_parallel": true, "self": 0.1232235009665601 } } }, "UnityEnvironment.step": { "total": 11339.525439142191, "count": 399099, "is_parallel": true, "self": 585.7096071103006, "children": { "UnityEnvironment._generate_step_input": { "total": 507.8765655910829, "count": 399099, "is_parallel": true, "self": 507.8765655910829 }, "communicator.exchange": { "total": 8226.763018726895, "count": 399099, "is_parallel": true, "self": 8226.763018726895 }, "steps_from_proto": { "total": 2019.1762477139127, "count": 798198, "is_parallel": true, "self": 389.7491419397411, "children": { "_process_rank_one_or_two_observation": { "total": 1629.4271057741717, "count": 3192792, "is_parallel": true, "self": 1629.4271057741717 } } } } } } } } } } }, "trainer_advance": { "total": 27610.18534028041, "count": 399099, "self": 161.50414524361258, "children": { "process_trajectory": { "total": 5946.397217437276, "count": 399099, "self": 5941.642507737386, "children": { "RLTrainer._checkpoint": { "total": 4.754709699889645, "count": 11, "self": 4.754709699889645 } } }, "_update_policy": { "total": 21502.283977599523, "count": 281, "self": 2456.635687999951, "children": { "TorchPOCAOptimizer.update": { "total": 19045.648289599572, "count": 8403, "self": 19045.648289599572 } } } } } } }, "trainer_threads": { "total": 3.8000289350748062e-06, "count": 1, "self": 3.8000289350748062e-06 }, "TrainerController._save_models": { "total": 0.5354965999722481, "count": 1, "self": 0.007501599960960448, "children": { "RLTrainer._checkpoint": { "total": 0.5279950000112876, "count": 1, "self": 0.5279950000112876 } } } } } } }