{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.2504258155822754, "min": 2.2406411170959473, "max": 3.295703172683716, "count": 498 }, "SoccerTwos.Policy.Entropy.sum": { "value": 49257.3203125, "min": 17408.8671875, "max": 143718.734375, "count": 498 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 46.98076923076923, "min": 44.04504504504504, "max": 999.0, "count": 498 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19544.0, "min": 11988.0, "max": 30232.0, "count": 498 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1320.570440954721, "min": 1190.4467605530663, "max": 1357.0032917139204, "count": 448 }, "SoccerTwos.Self-play.ELO.sum": { "value": 274678.65171858197, "min": 2380.8935211061325, "max": 295071.68388725596, "count": 448 }, "SoccerTwos.Step.mean": { "value": 4999912.0, "min": 19348.0, "max": 4999912.0, "count": 499 }, "SoccerTwos.Step.sum": { "value": 4999912.0, "min": 19348.0, "max": 4999912.0, "count": 499 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.01760864071547985, "min": -0.10719484090805054, "max": 0.10208045691251755, "count": 499 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 3.662597179412842, "min": -21.364421844482422, "max": 16.230792999267578, "count": 499 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.012105396017432213, "min": -0.10655353963375092, "max": 0.1074918583035469, "count": 499 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 2.5179224014282227, "min": -21.351320266723633, "max": 17.091205596923828, "count": 499 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 499 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 499 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.012899998862009782, "min": -0.5, "max": 0.49238332857688266, "count": 499 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 2.6831997632980347, "min": -62.66639965772629, "max": 33.75400006771088, "count": 499 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.012899998862009782, "min": -0.5, "max": 0.49238332857688266, "count": 499 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 2.6831997632980347, "min": -62.66639965772629, "max": 33.75400006771088, "count": 499 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 499 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 499 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01840621409161637, "min": 0.01144604262469026, "max": 0.02546065050216081, "count": 235 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01840621409161637, "min": 0.01144604262469026, "max": 0.02546065050216081, "count": 235 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.1059496375421683, "min": 7.0266638128183935e-06, "max": 0.10933336491386096, "count": 235 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.1059496375421683, "min": 7.0266638128183935e-06, "max": 0.10933336491386096, "count": 235 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10791122342149416, "min": 7.231742567152348e-06, "max": 0.11159076566497485, "count": 235 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10791122342149416, "min": 7.231742567152348e-06, "max": 0.11159076566497485, "count": 235 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 235 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 235 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 235 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 235 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 235 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 235 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1706818769", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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.exe --run-id=SoccerTwos-v1 --no-graphics --resume", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1706829304" }, "total": 10534.375123275, "count": 1, "self": 0.38434738800060586, "children": { "run_training.setup": { "total": 0.048530206000123144, "count": 1, "self": 0.048530206000123144 }, "TrainerController.start_learning": { "total": 10533.942245680999, "count": 1, "self": 6.800330160624071, "children": { "TrainerController._reset_env": { "total": 5.996437451998645, "count": 50, "self": 5.996437451998645 }, "TrainerController.advance": { "total": 10520.923248030374, "count": 335976, "self": 7.670076602416884, "children": { "env_step": { "total": 8520.064524838905, "count": 335976, "self": 6488.256292702765, "children": { "SubprocessEnvManager._take_step": { "total": 2027.6439130718409, "count": 335976, "self": 54.167174102564786, "children": { "TorchPolicy.evaluate": { "total": 1973.476738969276, "count": 652478, "self": 1973.476738969276 } } }, "workers": { "total": 4.164319064298979, "count": 335976, "self": 0.0, "children": { "worker_root": { "total": 10511.723518012013, "count": 335976, "is_parallel": true, "self": 5014.347184072704, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0036401130000740523, "count": 2, "is_parallel": true, "self": 0.0009396940004080534, "children": { "_process_rank_one_or_two_observation": { "total": 0.002700418999665999, "count": 8, "is_parallel": true, "self": 0.002700418999665999 } } }, "UnityEnvironment.step": { "total": 0.04230505899977288, "count": 1, "is_parallel": true, "self": 0.001156691999767645, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00089758800004347, "count": 1, "is_parallel": true, "self": 0.00089758800004347 }, "communicator.exchange": { "total": 0.03632842599972719, "count": 1, "is_parallel": true, "self": 0.03632842599972719 }, "steps_from_proto": { "total": 0.00392235300023458, "count": 2, "is_parallel": true, "self": 0.0006660560002273996, "children": { "_process_rank_one_or_two_observation": { "total": 0.00325629700000718, "count": 8, "is_parallel": true, "self": 0.00325629700000718 } } } } } } }, "UnityEnvironment.step": { "total": 5497.263973634299, "count": 335975, "is_parallel": true, "self": 371.3981966134652, "children": { "UnityEnvironment._generate_step_input": { "total": 244.78737020064864, "count": 335975, "is_parallel": true, "self": 244.78737020064864 }, "communicator.exchange": { "total": 3746.8664326162966, "count": 335975, "is_parallel": true, "self": 3746.8664326162966 }, "steps_from_proto": { "total": 1134.211974203889, "count": 671950, "is_parallel": true, "self": 182.91357044486585, "children": { "_process_rank_one_or_two_observation": { "total": 951.2984037590231, "count": 2687800, "is_parallel": true, "self": 951.2984037590231 } } } } }, "steps_from_proto": { "total": 0.1123603050100428, "count": 98, "is_parallel": true, "self": 0.02305573202056621, "children": { "_process_rank_one_or_two_observation": { "total": 0.08930457298947658, "count": 392, "is_parallel": true, "self": 0.08930457298947658 } } } } } } } } }, "trainer_advance": { "total": 1993.1886465890539, "count": 335976, "self": 59.99784077754566, "children": { "process_trajectory": { "total": 652.5356830295145, "count": 335976, "self": 650.0489997665159, "children": { "RLTrainer._checkpoint": { "total": 2.4866832629986675, "count": 10, "self": 2.4866832629986675 } } }, "_update_policy": { "total": 1280.6551227819937, "count": 235, "self": 751.7631663780435, "children": { "TorchPOCAOptimizer.update": { "total": 528.8919564039502, "count": 7053, "self": 528.8919564039502 } } } } } } }, "trainer_threads": { "total": 1.1650008673314005e-06, "count": 1, "self": 1.1650008673314005e-06 }, "TrainerController._save_models": { "total": 0.22222887300085858, "count": 1, "self": 0.002408819000265794, "children": { "RLTrainer._checkpoint": { "total": 0.2198200540005928, "count": 1, "self": 0.2198200540005928 } } } } } } }