{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.6256906986236572, "min": 1.5151653289794922, "max": 3.2957353591918945, "count": 1154 }, "SoccerTwos.Policy.Entropy.sum": { "value": 33138.078125, "min": 13666.1015625, "max": 118539.6875, "count": 1154 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 57.37931034482759, "min": 40.30578512396694, "max": 999.0, "count": 1154 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19968.0, "min": 15708.0, "max": 25472.0, "count": 1154 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1645.624387676063, "min": 1199.5057223791089, "max": 1669.7630272282447, "count": 1140 }, "SoccerTwos.Self-play.ELO.sum": { "value": 286338.64345563494, "min": 2404.2031305023047, "max": 375012.08373040194, "count": 1140 }, "SoccerTwos.Step.mean": { "value": 11539989.0, "min": 9520.0, "max": 11539989.0, "count": 1154 }, "SoccerTwos.Step.sum": { "value": 11539989.0, "min": 9520.0, "max": 11539989.0, "count": 1154 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.019805457442998886, "min": -0.11690514534711838, "max": 0.19465824961662292, "count": 1154 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -3.4659550189971924, "min": -23.752120971679688, "max": 31.145320892333984, "count": 1154 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.02072952315211296, "min": -0.11703426390886307, "max": 0.1865769624710083, "count": 1154 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -3.627666473388672, "min": -24.734535217285156, "max": 29.852313995361328, "count": 1154 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1154 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1154 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.0650217124394008, "min": -0.47911351496303406, "max": 0.46066511855569, "count": 1154 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 11.378799676895142, "min": -63.05960011482239, "max": 51.5588002204895, "count": 1154 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0650217124394008, "min": -0.47911351496303406, "max": 0.46066511855569, "count": 1154 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 11.378799676895142, "min": -63.05960011482239, "max": 51.5588002204895, "count": 1154 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1154 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1154 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.015679552406072616, "min": 0.010357148100592895, "max": 0.026769747784904516, "count": 557 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015679552406072616, "min": 0.010357148100592895, "max": 0.026769747784904516, "count": 557 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09584968760609627, "min": 7.58380077968468e-05, "max": 0.1247166780134042, "count": 557 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09584968760609627, "min": 7.58380077968468e-05, "max": 0.1247166780134042, "count": 557 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.096784957498312, "min": 7.545345603527191e-05, "max": 0.12721291308601698, "count": 557 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.096784957498312, "min": 7.545345603527191e-05, "max": 0.12721291308601698, "count": 557 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 557 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 557 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 557 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 557 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 557 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 557 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1731096002", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]", "command_line_arguments": "/home/bruno/.local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/linux/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "1.1.0", "mlagents_envs_version": "1.1.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1731108295" }, "total": 12293.145396513999, "count": 1, "self": 0.10250656699827232, "children": { "run_training.setup": { "total": 0.04124298799979442, "count": 1, "self": 0.04124298799979442 }, "TrainerController.start_learning": { "total": 12293.001646959001, "count": 1, "self": 12.606341991941008, "children": { "TrainerController._reset_env": { "total": 3.6790765220048343, "count": 58, "self": 3.6790765220048343 }, "TrainerController.advance": { "total": 12276.601408473056, "count": 796136, "self": 14.037701958906837, "children": { "env_step": { "total": 9077.855338799312, "count": 796136, "self": 6440.073907020722, "children": { "SubprocessEnvManager._take_step": { "total": 2629.75552052446, "count": 796136, "self": 75.34004229852508, "children": { "TorchPolicy.evaluate": { "total": 2554.4154782259347, "count": 1453228, "self": 2554.4154782259347 } } }, "workers": { "total": 8.025911254130278, "count": 796135, "self": 0.0, "children": { "worker_root": { "total": 12271.393248586126, "count": 796135, "is_parallel": true, "self": 7142.085683102685, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003926381000383117, "count": 2, "is_parallel": true, "self": 0.0010260030003337306, "children": { "_process_rank_one_or_two_observation": { "total": 0.002900378000049386, "count": 8, "is_parallel": true, "self": 0.002900378000049386 } } }, "UnityEnvironment.step": { "total": 0.037870615999963775, "count": 1, "is_parallel": true, "self": 0.0008947249998527695, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006014400000822206, "count": 1, "is_parallel": true, "self": 0.0006014400000822206 }, "communicator.exchange": { "total": 0.03402241999992839, "count": 1, "is_parallel": true, "self": 0.03402241999992839 }, "steps_from_proto": { "total": 0.0023520310001003963, "count": 2, "is_parallel": true, "self": 0.00045028300019112066, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019017479999092757, "count": 8, "is_parallel": true, "self": 0.0019017479999092757 } } } } } } }, "UnityEnvironment.step": { "total": 5129.247043940451, "count": 796134, "is_parallel": true, "self": 302.1264598935504, "children": { "UnityEnvironment._generate_step_input": { "total": 172.57972834578413, "count": 796134, "is_parallel": true, "self": 172.57972834578413 }, "communicator.exchange": { "total": 3833.6327489276505, "count": 796134, "is_parallel": true, "self": 3833.6327489276505 }, "steps_from_proto": { "total": 820.9081067734655, "count": 1592268, "is_parallel": true, "self": 164.48092725723473, "children": { "_process_rank_one_or_two_observation": { "total": 656.4271795162308, "count": 6369072, "is_parallel": true, "self": 656.4271795162308 } } } } }, "steps_from_proto": { "total": 0.060521542990500166, "count": 114, "is_parallel": true, "self": 0.011821879970739246, "children": { "_process_rank_one_or_two_observation": { "total": 0.04869966301976092, "count": 456, "is_parallel": true, "self": 0.04869966301976092 } } } } } } } } }, "trainer_advance": { "total": 3184.7083677148376, "count": 796135, "self": 88.46047877437559, "children": { "process_trajectory": { "total": 1355.7992229554516, "count": 796135, "self": 1352.8841532714537, "children": { "RLTrainer._checkpoint": { "total": 2.915069683997899, "count": 23, "self": 2.915069683997899 } } }, "_update_policy": { "total": 1740.4486659850104, "count": 557, "self": 766.7064941201447, "children": { "TorchPOCAOptimizer.update": { "total": 973.7421718648657, "count": 16710, "self": 973.7421718648657 } } } } } } }, "trainer_threads": { "total": 5.469992174766958e-07, "count": 1, "self": 5.469992174766958e-07 }, "TrainerController._save_models": { "total": 0.11481942499995057, "count": 1, "self": 0.001115167999159894, "children": { "RLTrainer._checkpoint": { "total": 0.11370425700079068, "count": 1, "self": 0.11370425700079068 } } } } } } }