{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.5738945007324219, "min": 1.5237869024276733, "max": 3.2956762313842773, "count": 1000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 32485.18359375, "min": 29301.408203125, "max": 118666.1953125, "count": 1000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 51.114583333333336, "min": 36.714285714285715, "max": 999.0, "count": 1000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19628.0, "min": 16584.0, "max": 23412.0, "count": 1000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1609.0753915115758, "min": 1200.7014028759634, "max": 1646.3782379510135, "count": 996 }, "SoccerTwos.Self-play.ELO.sum": { "value": 308942.4751702226, "min": 2401.46427285754, "max": 419436.3779901329, "count": 996 }, "SoccerTwos.Step.mean": { "value": 9999994.0, "min": 9668.0, "max": 9999994.0, "count": 1000 }, "SoccerTwos.Step.sum": { "value": 9999994.0, "min": 9668.0, "max": 9999994.0, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.0031829916406422853, "min": -0.1322135627269745, "max": 0.1488342136144638, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.6079514026641846, "min": -23.525894165039062, "max": 20.707191467285156, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0020964820869266987, "min": -0.13126525282859802, "max": 0.1425919383764267, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.40042805671691895, "min": -23.625579833984375, "max": 21.237531661987305, "count": 1000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.09033926775318166, "min": -0.7722559976577759, "max": 0.5600877956646245, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -17.254800140857697, "min": -74.97280025482178, "max": 58.74560010433197, "count": 1000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.09033926775318166, "min": -0.7722559976577759, "max": 0.5600877956646245, "count": 1000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -17.254800140857697, "min": -74.97280025482178, "max": 58.74560010433197, "count": 1000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.019742212165147065, "min": 0.010487141778382163, "max": 0.02462120314594358, "count": 484 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.019742212165147065, "min": 0.010487141778382163, "max": 0.02462120314594358, "count": 484 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.11819523374239603, "min": 0.0005782351916423067, "max": 0.13054038484891256, "count": 484 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.11819523374239603, "min": 0.0005782351916423067, "max": 0.13054038484891256, "count": 484 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.12017655968666077, "min": 0.0005785436709023392, "max": 0.13289712543288867, "count": 484 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.12017655968666077, "min": 0.0005785436709023392, "max": 0.13289712543288867, "count": 484 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 484 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 484 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 484 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 484 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 484 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 484 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1686385158", "python_version": "3.9.17 (main, Jun 8 2023, 18:11:37) \n[GCC 11.3.0]", "command_line_arguments": "/home/andrea/.pyenv/versions/mlagents/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --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+cu113", "numpy_version": "1.21.2", "end_time_seconds": "1686400709" }, "total": 15550.957326357002, "count": 1, "self": 0.13102179300221906, "children": { "run_training.setup": { "total": 0.015120217999992747, "count": 1, "self": 0.015120217999992747 }, "TrainerController.start_learning": { "total": 15550.811184346, "count": 1, "self": 10.68883243397977, "children": { "TrainerController._reset_env": { "total": 4.497990563000485, "count": 50, "self": 4.497990563000485 }, "TrainerController.advance": { "total": 15535.43158599702, "count": 695024, "self": 10.334974799399788, "children": { "env_step": { "total": 11345.737655229153, "count": 695024, "self": 7466.494106970407, "children": { "SubprocessEnvManager._take_step": { "total": 3873.124861928006, "count": 695024, "self": 58.69447412351701, "children": { "TorchPolicy.evaluate": { "total": 3814.430387804489, "count": 1257440, "self": 3814.430387804489 } } }, "workers": { "total": 6.118686330740502, "count": 695024, "self": 0.0, "children": { "worker_root": { "total": 15527.686329719989, "count": 695024, "is_parallel": true, "self": 9186.96451050693, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00291210300019884, "count": 2, "is_parallel": true, "self": 0.0016854140001214546, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012266890000773856, "count": 8, "is_parallel": true, "self": 0.0012266890000773856 } } }, "UnityEnvironment.step": { "total": 0.024254306000102588, "count": 1, "is_parallel": true, "self": 0.00041687600014483905, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00034187300002486154, "count": 1, "is_parallel": true, "self": 0.00034187300002486154 }, "communicator.exchange": { "total": 0.022058946000015567, "count": 1, "is_parallel": true, "self": 0.022058946000015567 }, "steps_from_proto": { "total": 0.0014366109999173204, "count": 2, "is_parallel": true, "self": 0.0003356940001140174, "children": { "_process_rank_one_or_two_observation": { "total": 0.001100916999803303, "count": 8, "is_parallel": true, "self": 0.001100916999803303 } } } } } } }, "UnityEnvironment.step": { "total": 6340.665112867048, "count": 695023, "is_parallel": true, "self": 226.09785983979145, "children": { "UnityEnvironment._generate_step_input": { "total": 195.71891309470584, "count": 695023, "is_parallel": true, "self": 195.71891309470584 }, "communicator.exchange": { "total": 5170.741093881722, "count": 695023, "is_parallel": true, "self": 5170.741093881722 }, "steps_from_proto": { "total": 748.107246050829, "count": 1390046, "is_parallel": true, "self": 161.01895230273703, "children": { "_process_rank_one_or_two_observation": { "total": 587.0882937480919, "count": 5560184, "is_parallel": true, "self": 587.0882937480919 } } } } }, "steps_from_proto": { "total": 0.05670634601005986, "count": 98, "is_parallel": true, "self": 0.012092947029259449, "children": { "_process_rank_one_or_two_observation": { "total": 0.04461339898080041, "count": 392, "is_parallel": true, "self": 0.04461339898080041 } } } } } } } } }, "trainer_advance": { "total": 4179.358955968466, "count": 695024, "self": 70.38557393695555, "children": { "process_trajectory": { "total": 1910.0570792335259, "count": 695024, "self": 1906.526984832523, "children": { "RLTrainer._checkpoint": { "total": 3.5300944010027706, "count": 20, "self": 3.5300944010027706 } } }, "_update_policy": { "total": 2198.916302797985, "count": 484, "self": 1270.4455030588672, "children": { "TorchPOCAOptimizer.update": { "total": 928.4707997391176, "count": 14523, "self": 928.4707997391176 } } } } } } }, "trainer_threads": { "total": 6.320005923043936e-07, "count": 1, "self": 6.320005923043936e-07 }, "TrainerController._save_models": { "total": 0.19277471999885165, "count": 1, "self": 0.0013728139965678565, "children": { "RLTrainer._checkpoint": { "total": 0.1914019060022838, "count": 1, "self": 0.1914019060022838 } } } } } } }