{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.164323329925537, "min": 3.0928449630737305, "max": 3.2957217693328857, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 55388.31640625, "min": 10912.0078125, "max": 129053.296875, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 999.0, "min": 400.0833333333333, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19980.0, "min": 14580.0, "max": 28012.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1149.7682774714995, "min": 1149.7682774714995, "max": 1201.137815359693, "count": 320 }, "SoccerTwos.Self-play.ELO.sum": { "value": 4599.073109885998, "min": 2300.0323146105325, "max": 20930.96935664103, "count": 320 }, "SoccerTwos.Step.mean": { "value": 4999376.0, "min": 9024.0, "max": 4999376.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999376.0, "min": 9024.0, "max": 4999376.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -3.603884397307411e-05, "min": -0.09072059392929077, "max": 0.027004892006516457, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.00036038842517882586, "min": -1.5422500371932983, "max": 0.41970595717430115, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 1.9964592866017483e-05, "min": -0.09072178602218628, "max": 0.027272654697299004, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.00019964593229815364, "min": -1.5422704219818115, "max": 0.4313048720359802, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.0, "min": -0.6470588235294118, "max": 0.5052952425820487, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.0, "min": -12.437999963760376, "max": 10.611200094223022, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0, "min": -0.6470588235294118, "max": 0.5052952425820487, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.0, "min": -12.437999963760376, "max": 10.611200094223022, "count": 500 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.018709923633529493, "min": 0.01063105077870811, "max": 0.023163213063768732, "count": 232 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.018709923633529493, "min": 0.01063105077870811, "max": 0.023163213063768732, "count": 232 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.00034979778768805166, "min": 1.63063542994261e-07, "max": 0.011673605938752493, "count": 232 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.00034979778768805166, "min": 1.63063542994261e-07, "max": 0.011673605938752493, "count": 232 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0003490819447809675, "min": 1.8509832671043115e-07, "max": 0.011708052518467108, "count": 232 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0003490819447809675, "min": 1.8509832671043115e-07, "max": 0.011708052518467108, "count": 232 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 232 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 232 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 232 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 232 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 232 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 232 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1717063740", "python_version": "3.10.12 (main, May 30 2024, 14:02:56) [GCC 13.2.0]", "command_line_arguments": "/home/nd/venv.p3.10.12/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=poca-SoccerTwos-R001 --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1717084560" }, "total": 20819.851152959, "count": 1, "self": 0.3272028319988749, "children": { "run_training.setup": { "total": 0.02025466399936704, "count": 1, "self": 0.02025466399936704 }, "TrainerController.start_learning": { "total": 20819.503695463, "count": 1, "self": 8.347392137588031, "children": { "TrainerController._reset_env": { "total": 16.526013859005616, "count": 25, "self": 16.526013859005616 }, "TrainerController.advance": { "total": 20794.455769170407, "count": 325401, "self": 8.309603589452308, "children": { "env_step": { "total": 8885.983593393432, "count": 325401, "self": 7135.185549223557, "children": { "SubprocessEnvManager._take_step": { "total": 1745.3680530970323, "count": 325401, "self": 66.09837459260598, "children": { "TorchPolicy.evaluate": { "total": 1679.2696785044263, "count": 646064, "self": 1679.2696785044263 } } }, "workers": { "total": 5.429991072842313, "count": 325401, "self": 0.0, "children": { "worker_root": { "total": 20797.802154064208, "count": 325401, "is_parallel": true, "self": 14948.512903780369, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006107459001214011, "count": 2, "is_parallel": true, "self": 0.0014541330019710585, "children": { "_process_rank_one_or_two_observation": { "total": 0.004653325999242952, "count": 8, "is_parallel": true, "self": 0.004653325999242952 } } }, "UnityEnvironment.step": { "total": 0.031485810000958736, "count": 1, "is_parallel": true, "self": 0.0015579760001855902, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0013911239984736312, "count": 1, "is_parallel": true, "self": 0.0013911239984736312 }, "communicator.exchange": { "total": 0.02363527500165219, "count": 1, "is_parallel": true, "self": 0.02363527500165219 }, "steps_from_proto": { "total": 0.004901435000647325, "count": 2, "is_parallel": true, "self": 0.0009859730016614776, "children": { "_process_rank_one_or_two_observation": { "total": 0.0039154619989858475, "count": 8, "is_parallel": true, "self": 0.0039154619989858475 } } } } } } }, "UnityEnvironment.step": { "total": 5849.170611908841, "count": 325400, "is_parallel": true, "self": 388.1314371114222, "children": { "UnityEnvironment._generate_step_input": { "total": 349.65917279288624, "count": 325400, "is_parallel": true, "self": 349.65917279288624 }, "communicator.exchange": { "total": 3888.7275167286934, "count": 325400, "is_parallel": true, "self": 3888.7275167286934 }, "steps_from_proto": { "total": 1222.6524852758394, "count": 650800, "is_parallel": true, "self": 237.08203115258948, "children": { "_process_rank_one_or_two_observation": { "total": 985.5704541232499, "count": 2603200, "is_parallel": true, "self": 985.5704541232499 } } } } }, "steps_from_proto": { "total": 0.11863837499731744, "count": 48, "is_parallel": true, "self": 0.023050587997204275, "children": { "_process_rank_one_or_two_observation": { "total": 0.09558778700011317, "count": 192, "is_parallel": true, "self": 0.09558778700011317 } } } } } } } } }, "trainer_advance": { "total": 11900.162572187524, "count": 325401, "self": 68.83784118523727, "children": { "process_trajectory": { "total": 1592.1178049082755, "count": 325401, "self": 1589.9666067502767, "children": { "RLTrainer._checkpoint": { "total": 2.151198157998806, "count": 10, "self": 2.151198157998806 } } }, "_update_policy": { "total": 10239.206926094012, "count": 232, "self": 1233.9792235539826, "children": { "TorchPOCAOptimizer.update": { "total": 9005.227702540029, "count": 6963, "self": 9005.227702540029 } } } } } } }, "trainer_threads": { "total": 1.2800010154023767e-06, "count": 1, "self": 1.2800010154023767e-06 }, "TrainerController._save_models": { "total": 0.17451901599997655, "count": 1, "self": 0.002160292999178637, "children": { "RLTrainer._checkpoint": { "total": 0.1723587230007979, "count": 1, "self": 0.1723587230007979 } } } } } } }