{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.206989049911499, "min": 3.182180643081665, "max": 3.2956318855285645, "count": 50 }, "SoccerTwos.Policy.Entropy.sum": { "value": 86203.8671875, "min": 19453.03125, "max": 108857.234375, "count": 50 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 995.0, "min": 453.8888888888889, "max": 999.0, "count": 50 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19900.0, "min": 12768.0, "max": 24492.0, "count": 50 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1199.958622767334, "min": 1196.1996665131562, "max": 1204.027309616533, "count": 44 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2399.917245534668, "min": 2394.2346338381494, "max": 16783.12381066186, "count": 44 }, "SoccerTwos.Step.mean": { "value": 499596.0, "min": 9266.0, "max": 499596.0, "count": 50 }, "SoccerTwos.Step.sum": { "value": 499596.0, "min": 9266.0, "max": 499596.0, "count": 50 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.00031406013295054436, "min": -0.10571954399347305, "max": 0.002136609982699156, "count": 50 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.0031406013295054436, "min": -1.7972322702407837, "max": 0.021366100758314133, "count": 50 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0005671166582033038, "min": -0.10568708181381226, "max": 0.0021674628369510174, "count": 50 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.005671166814863682, "min": -1.7966804504394531, "max": 0.023842090740799904, "count": 50 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 50 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 50 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.2, "min": -0.3506399989128113, "max": 0.2194769290777353, "count": 50 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -2.0, "min": -6.3043999671936035, "max": 2.853200078010559, "count": 50 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.2, "min": -0.3506399989128113, "max": 0.2194769290777353, "count": 50 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -2.0, "min": -6.3043999671936035, "max": 2.853200078010559, "count": 50 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.0172808788503365, "min": 0.011181986787899707, "max": 0.021416104515083134, "count": 23 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.0172808788503365, "min": 0.011181986787899707, "max": 0.021416104515083134, "count": 23 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.00012632979778572916, "min": 0.00012632979778572916, "max": 0.005331645393744111, "count": 23 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.00012632979778572916, "min": 0.00012632979778572916, "max": 0.005331645393744111, "count": 23 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0001269832447481652, "min": 0.0001269832447481652, "max": 0.005064081563614309, "count": 23 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0001269832447481652, "min": 0.0001269832447481652, "max": 0.005064081563614309, "count": 23 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 23 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 23 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 23 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 23 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 23 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 23 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1736361874", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/poca/SoccerTwos.yaml --env=./ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1736364827" }, "total": 2952.499174379, "count": 1, "self": 0.5391467840004225, "children": { "run_training.setup": { "total": 0.0759220820000337, "count": 1, "self": 0.0759220820000337 }, "TrainerController.start_learning": { "total": 2951.8841055129997, "count": 1, "self": 1.3362193020229824, "children": { "TrainerController._reset_env": { "total": 2.8965241150006023, "count": 3, "self": 2.8965241150006023 }, "TrainerController.advance": { "total": 2947.402874003975, "count": 33045, "self": 1.4921521010519427, "children": { "env_step": { "total": 1191.708055407971, "count": 33045, "self": 950.9774194538936, "children": { "SubprocessEnvManager._take_step": { "total": 239.91204395007117, "count": 33045, "self": 9.822502055141513, "children": { "TorchPolicy.evaluate": { "total": 230.08954189492965, "count": 65648, "self": 230.08954189492965 } } }, "workers": { "total": 0.8185920040061774, "count": 33045, "self": 0.0, "children": { "worker_root": { "total": 2945.72382157698, "count": 33045, "is_parallel": true, "self": 2159.1547858829445, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005547320999994554, "count": 2, "is_parallel": true, "self": 0.0013821049999478419, "children": { "_process_rank_one_or_two_observation": { "total": 0.004165216000046712, "count": 8, "is_parallel": true, "self": 0.004165216000046712 } } }, "UnityEnvironment.step": { "total": 0.049177277000126196, "count": 1, "is_parallel": true, "self": 0.001637429000084012, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0009495540000443725, "count": 1, "is_parallel": true, "self": 0.0009495540000443725 }, "communicator.exchange": { "total": 0.042250820999925054, "count": 1, "is_parallel": true, "self": 0.042250820999925054 }, "steps_from_proto": { "total": 0.004339473000072758, "count": 2, "is_parallel": true, "self": 0.0007464210004854976, "children": { "_process_rank_one_or_two_observation": { "total": 0.00359305199958726, "count": 8, "is_parallel": true, "self": 0.00359305199958726 } } } } } } }, "UnityEnvironment.step": { "total": 786.5623676610358, "count": 33044, "is_parallel": true, "self": 48.89758802614347, "children": { "UnityEnvironment._generate_step_input": { "total": 31.411882251939915, "count": 33044, "is_parallel": true, "self": 31.411882251939915 }, "communicator.exchange": { "total": 556.7501894689528, "count": 33044, "is_parallel": true, "self": 556.7501894689528 }, "steps_from_proto": { "total": 149.50270791399953, "count": 66088, "is_parallel": true, "self": 25.88476159195193, "children": { "_process_rank_one_or_two_observation": { "total": 123.6179463220476, "count": 264352, "is_parallel": true, "self": 123.6179463220476 } } } } }, "steps_from_proto": { "total": 0.006668032999641582, "count": 4, "is_parallel": true, "self": 0.0011941750003643392, "children": { "_process_rank_one_or_two_observation": { "total": 0.005473857999277243, "count": 16, "is_parallel": true, "self": 0.005473857999277243 } } } } } } } } }, "trainer_advance": { "total": 1754.2026664949517, "count": 33045, "self": 11.597254912981043, "children": { "process_trajectory": { "total": 219.39166443496947, "count": 33045, "self": 219.14087492596923, "children": { "RLTrainer._checkpoint": { "total": 0.2507895090002421, "count": 1, "self": 0.2507895090002421 } } }, "_update_policy": { "total": 1523.2137471470012, "count": 23, "self": 109.92705568399015, "children": { "TorchPOCAOptimizer.update": { "total": 1413.286691463011, "count": 693, "self": 1413.286691463011 } } } } } } }, "trainer_threads": { "total": 1.4260003808885813e-06, "count": 1, "self": 1.4260003808885813e-06 }, "TrainerController._save_models": { "total": 0.24848666600064462, "count": 1, "self": 0.0033228570009669056, "children": { "RLTrainer._checkpoint": { "total": 0.2451638089996777, "count": 1, "self": 0.2451638089996777 } } } } } } }