{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.5426337718963623, "min": 1.531245470046997, "max": 3.2957189083099365, "count": 1000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 33320.890625, "min": 7970.23046875, "max": 128600.515625, "count": 1000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 55.26966292134831, "min": 39.30952380952381, "max": 999.0, "count": 1000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19676.0, "min": 3996.0, "max": 31656.0, "count": 1000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1607.90912761641, "min": 1194.6670111711967, "max": 1637.0180950971917, "count": 972 }, "SoccerTwos.Self-play.ELO.sum": { "value": 286207.82471572096, "min": 2395.925075993749, "max": 404377.00081549096, "count": 972 }, "SoccerTwos.Step.mean": { "value": 9999966.0, "min": 9846.0, "max": 9999966.0, "count": 1000 }, "SoccerTwos.Step.sum": { "value": 9999966.0, "min": 9846.0, "max": 9999966.0, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.034293223172426224, "min": -0.12104719877243042, "max": 0.1903175264596939, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -6.138486862182617, "min": -23.874568939208984, "max": 24.74559211730957, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.03585423529148102, "min": -0.12008939683437347, "max": 0.18938793241977692, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -6.417908191680908, "min": -23.972457885742188, "max": 24.840940475463867, "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": -0.022670391551609145, "min": -0.6, "max": 0.5419545437801968, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -4.058000087738037, "min": -67.45359998941422, "max": 61.70399987697601, "count": 1000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.022670391551609145, "min": -0.6, "max": 0.5419545437801968, "count": 1000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -4.058000087738037, "min": -67.45359998941422, "max": 61.70399987697601, "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": 0.0185897947793516, "min": 0.009789575341468055, "max": 0.02578884911102553, "count": 481 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.0185897947793516, "min": 0.009789575341468055, "max": 0.02578884911102553, "count": 481 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.1093875877559185, "min": 7.906696979868382e-06, "max": 0.13266134212414424, "count": 481 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.1093875877559185, "min": 7.906696979868382e-06, "max": 0.13266134212414424, "count": 481 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11060970971981685, "min": 7.798433792534827e-06, "max": 0.1361390066643556, "count": 481 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11060970971981685, "min": 7.798433792534827e-06, "max": 0.1361390066643556, "count": 481 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 481 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 481 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 481 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 481 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 481 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 481 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1676842658", "python_version": "3.9.16 | packaged by conda-forge | (main, Feb 1 2023, 21:42:20) \n[Clang 14.0.6 ]", "command_line_arguments": "/Users/menoua/opt/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --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", "numpy_version": "1.21.2", "end_time_seconds": "1676876978" }, "total": 34320.636995194, "count": 1, "self": 0.4771618579979986, "children": { "run_training.setup": { "total": 0.03024002799999992, "count": 1, "self": 0.03024002799999992 }, "TrainerController.start_learning": { "total": 34320.129593308004, "count": 1, "self": 14.530758860259084, "children": { "TrainerController._reset_env": { "total": 4.604821874000669, "count": 50, "self": 4.604821874000669 }, "TrainerController.advance": { "total": 34300.73496561474, "count": 683570, "self": 13.87728839054762, "children": { "env_step": { "total": 10032.80140380752, "count": 683570, "self": 8270.437985418914, "children": { "SubprocessEnvManager._take_step": { "total": 1753.8916824040134, "count": 683570, "self": 73.03562723059713, "children": { "TorchPolicy.evaluate": { "total": 1680.8560551734163, "count": 1263360, "self": 1680.8560551734163 } } }, "workers": { "total": 8.471735984593252, "count": 683570, "self": 0.0, "children": { "worker_root": { "total": 34292.74253611004, "count": 683570, "is_parallel": true, "self": 27553.653667206636, "children": { "steps_from_proto": { "total": 0.09807239999482897, "count": 100, "is_parallel": true, "self": 0.021308775045160377, "children": { "_process_rank_one_or_two_observation": { "total": 0.0767636249496686, "count": 400, "is_parallel": true, "self": 0.0767636249496686 } } }, "UnityEnvironment.step": { "total": 6738.99079650341, "count": 683570, "is_parallel": true, "self": 365.7697535714806, "children": { "UnityEnvironment._generate_step_input": { "total": 219.35635614431862, "count": 683570, "is_parallel": true, "self": 219.35635614431862 }, "communicator.exchange": { "total": 5042.1411571002, "count": 683570, "is_parallel": true, "self": 5042.1411571002 }, "steps_from_proto": { "total": 1111.7235296874107, "count": 1367140, "is_parallel": true, "self": 231.5280831352045, "children": { "_process_rank_one_or_two_observation": { "total": 880.1954465522062, "count": 5468560, "is_parallel": true, "self": 880.1954465522062 } } } } } } } } } } }, "trainer_advance": { "total": 24254.05627341667, "count": 683570, "self": 90.9083377452589, "children": { "process_trajectory": { "total": 3033.4117440054147, "count": 683570, "self": 3027.4671627154057, "children": { "RLTrainer._checkpoint": { "total": 5.944581290008955, "count": 20, "self": 5.944581290008955 } } }, "_update_policy": { "total": 21129.736191665997, "count": 481, "self": 1550.1056513753756, "children": { "TorchPOCAOptimizer.update": { "total": 19579.630540290622, "count": 14442, "self": 19579.630540290622 } } } } } } }, "trainer_threads": { "total": 1.0829971870407462e-06, "count": 1, "self": 1.0829971870407462e-06 }, "TrainerController._save_models": { "total": 0.25904587600234663, "count": 1, "self": 0.008322439003677573, "children": { "RLTrainer._checkpoint": { "total": 0.25072343699866906, "count": 1, "self": 0.25072343699866906 } } } } } } }