{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.2273454666137695, "min": 2.2175986766815186, "max": 3.227695941925049, "count": 517 }, "SoccerTwos.Policy.Entropy.sum": { "value": 43335.234375, "min": 10667.50390625, "max": 119745.4765625, "count": 517 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 53.561797752808985, "min": 40.925619834710744, "max": 999.0, "count": 517 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19068.0, "min": 1056.0, "max": 31968.0, "count": 517 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1504.1926838586373, "min": 1186.0004903836195, "max": 1512.4895715871382, "count": 464 }, "SoccerTwos.Self-play.ELO.sum": { "value": 267746.29772683745, "min": 2372.000980767239, "max": 351916.06924432574, "count": 464 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 517 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 517 }, "SoccerTwos.Step.mean": { "value": 5659954.0, "min": 509744.0, "max": 5659954.0, "count": 516 }, "SoccerTwos.Step.sum": { "value": 5659954.0, "min": 509744.0, "max": 5659954.0, "count": 516 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.08629171550273895, "min": -0.11334313452243805, "max": 0.23142051696777344, "count": 516 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 15.359925270080566, "min": -20.5283203125, "max": 44.441707611083984, "count": 516 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.07696717232465744, "min": -0.1191025823354721, "max": 0.228508859872818, "count": 516 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 13.700156211853027, "min": -19.5948429107666, "max": 44.568458557128906, "count": 516 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 516 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 516 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.11198651522732853, "min": -0.7142857142857143, "max": 0.46606250293552876, "count": 516 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 19.933599710464478, "min": -44.531199753284454, "max": 97.17799997329712, "count": 516 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.11198651522732853, "min": -0.7142857142857143, "max": 0.46606250293552876, "count": 516 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 19.933599710464478, "min": -44.531199753284454, "max": 97.17799997329712, "count": 516 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01888621726927037, "min": 0.010425080761585074, "max": 0.02376857806618015, "count": 244 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01888621726927037, "min": 0.010425080761585074, "max": 0.02376857806618015, "count": 244 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10987885296344757, "min": 1.714208913957312e-06, "max": 0.10987885296344757, "count": 244 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10987885296344757, "min": 1.714208913957312e-06, "max": 0.10987885296344757, "count": 244 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11204245090484619, "min": 1.4393047194971586e-06, "max": 0.11204245090484619, "count": 244 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11204245090484619, "min": 1.4393047194971586e-06, "max": 0.11204245090484619, "count": 244 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 244 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 244 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 244 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 244 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 244 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 244 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1689386118", "python_version": "3.9.17 (main, Jul 5 2023, 20:47:11) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\hsujs\\miniconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1689405283" }, "total": 19164.951590700002, "count": 1, "self": 0.2140637999982573, "children": { "run_training.setup": { "total": 0.12235099999999965, "count": 1, "self": 0.12235099999999965 }, "TrainerController.start_learning": { "total": 19164.615175900002, "count": 1, "self": 9.635304699608241, "children": { "TrainerController._reset_env": { "total": 6.171220099996478, "count": 27, "self": 6.171220099996478 }, "TrainerController.advance": { "total": 19148.602981200394, "count": 342530, "self": 9.946182800293172, "children": { "env_step": { "total": 7370.093500300388, "count": 342530, "self": 5722.4948751995435, "children": { "SubprocessEnvManager._take_step": { "total": 1641.3676411007264, "count": 342530, "self": 56.48914060115112, "children": { "TorchPolicy.evaluate": { "total": 1584.8785004995752, "count": 659218, "self": 1584.8785004995752 } } }, "workers": { "total": 6.230984000118375, "count": 342529, "self": 0.0, "children": { "worker_root": { "total": 19146.92048600019, "count": 342529, "is_parallel": true, "self": 14552.490896399906, "children": { "steps_from_proto": { "total": 0.053192699994924375, "count": 54, "is_parallel": true, "self": 0.011896599984961398, "children": { "_process_rank_one_or_two_observation": { "total": 0.04129610000996298, "count": 216, "is_parallel": true, "self": 0.04129610000996298 } } }, "UnityEnvironment.step": { "total": 4594.376396900288, "count": 342529, "is_parallel": true, "self": 222.08454690051894, "children": { "UnityEnvironment._generate_step_input": { "total": 198.59745240033703, "count": 342529, "is_parallel": true, "self": 198.59745240033703 }, "communicator.exchange": { "total": 3446.9493110000635, "count": 342529, "is_parallel": true, "self": 3446.9493110000635 }, "steps_from_proto": { "total": 726.7450865993674, "count": 685058, "is_parallel": true, "self": 154.0908538017153, "children": { "_process_rank_one_or_two_observation": { "total": 572.6542327976521, "count": 2740232, "is_parallel": true, "self": 572.6542327976521 } } } } } } } } } } }, "trainer_advance": { "total": 11768.563298099714, "count": 342529, "self": 65.42690689986557, "children": { "process_trajectory": { "total": 1471.5374333998707, "count": 342529, "self": 1469.5611095998727, "children": { "RLTrainer._checkpoint": { "total": 1.97632379999801, "count": 11, "self": 1.97632379999801 } } }, "_update_policy": { "total": 10231.598957799979, "count": 244, "self": 977.9501888999621, "children": { "TorchPOCAOptimizer.update": { "total": 9253.648768900017, "count": 7332, "self": 9253.648768900017 } } } } } } }, "trainer_threads": { "total": 1.7000020307023078e-06, "count": 1, "self": 1.7000020307023078e-06 }, "TrainerController._save_models": { "total": 0.20566820000021835, "count": 1, "self": 0.025601700002880534, "children": { "RLTrainer._checkpoint": { "total": 0.18006649999733781, "count": 1, "self": 0.18006649999733781 } } } } } } }