{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.51484751701355, "min": 2.4968974590301514, "max": 3.2957088947296143, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 48687.44921875, "min": 17183.470703125, "max": 127448.0859375, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 148.15151515151516, "min": 110.6086956521739, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19556.0, "min": 4616.0, "max": 30060.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1205.9946991120182, "min": 1182.7427229333125, "max": 1236.0059830681423, "count": 458 }, "SoccerTwos.Self-play.ELO.sum": { "value": 77183.66074316917, "min": 2365.5766621176053, "max": 109429.25045098405, "count": 458 }, "SoccerTwos.Step.mean": { "value": 4999966.0, "min": 9976.0, "max": 4999966.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999966.0, "min": 9976.0, "max": 4999966.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.011815357953310013, "min": -0.8224837183952332, "max": 0.09149566292762756, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.7679982781410217, "min": -41.33378219604492, "max": 5.38049840927124, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.011457674205303192, "min": -0.8225486874580383, "max": 0.09321700781583786, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.7447488307952881, "min": -41.12950134277344, "max": 5.042311668395996, "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": -0.10054153845860409, "min": -0.6888603781754116, "max": 0.500728577375412, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -6.535199999809265, "min": -36.509600043296814, "max": 22.3924001455307, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.10054153845860409, "min": -0.6888603781754116, "max": 0.500728577375412, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -6.535199999809265, "min": -36.509600043296814, "max": 22.3924001455307, "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": 0.02056941466871649, "min": 0.012793293024878949, "max": 0.028850990000986107, "count": 235 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.02056941466871649, "min": 0.012793293024878949, "max": 0.028850990000986107, "count": 235 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.023601138219237327, "min": 1.9371433760776804e-06, "max": 3.8241605819535573, "count": 235 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.023601138219237327, "min": 1.9371433760776804e-06, "max": 3.8241605819535573, "count": 235 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.025794722388188043, "min": 5.924941281894765e-06, "max": 3.704598916705609, "count": 235 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.025794722388188043, "min": 5.924941281894765e-06, "max": 3.704598916705609, "count": 235 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.003000000000000001, "min": 0.003, "max": 0.003000000000000001, "count": 235 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.003000000000000001, "min": 0.003, "max": 0.003000000000000001, "count": 235 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 235 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 235 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 235 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 235 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1715704230", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/root/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos --run-id=soccer_twos --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": "1715741171" }, "total": 36965.794145468004, "count": 1, "self": 5.352597061006236, "children": { "run_training.setup": { "total": 0.07465267699990363, "count": 1, "self": 0.07465267699990363 }, "TrainerController.start_learning": { "total": 36960.366895729996, "count": 1, "self": 11.881535156600876, "children": { "TrainerController._reset_env": { "total": 15.367443916025877, "count": 99, "self": 15.367443916025877 }, "TrainerController.advance": { "total": 36932.607473506374, "count": 351571, "self": 12.379925891757011, "children": { "env_step": { "total": 9206.65211241196, "count": 351571, "self": 6769.482378721448, "children": { "SubprocessEnvManager._take_step": { "total": 2429.4186117198715, "count": 351571, "self": 95.42245306367113, "children": { "TorchPolicy.evaluate": { "total": 2333.9961586562004, "count": 692016, "self": 2333.9961586562004 } } }, "workers": { "total": 7.751121970641179, "count": 351571, "self": 0.0, "children": { "worker_root": { "total": 36933.626827574946, "count": 351571, "is_parallel": true, "self": 31740.253805830158, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.008072216000982735, "count": 2, "is_parallel": true, "self": 0.0024276560006910586, "children": { "_process_rank_one_or_two_observation": { "total": 0.005644560000291676, "count": 8, "is_parallel": true, "self": 0.005644560000291676 } } }, "UnityEnvironment.step": { "total": 0.036281407000387844, "count": 1, "is_parallel": true, "self": 0.0007422099997711484, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0008546700000806595, "count": 1, "is_parallel": true, "self": 0.0008546700000806595 }, "communicator.exchange": { "total": 0.031440329999895766, "count": 1, "is_parallel": true, "self": 0.031440329999895766 }, "steps_from_proto": { "total": 0.00324419700064027, "count": 2, "is_parallel": true, "self": 0.0006480240017481265, "children": { "_process_rank_one_or_two_observation": { "total": 0.0025961729988921434, "count": 8, "is_parallel": true, "self": 0.0025961729988921434 } } } } } } }, "UnityEnvironment.step": { "total": 5193.080491720794, "count": 351570, "is_parallel": true, "self": 263.54286897053316, "children": { "UnityEnvironment._generate_step_input": { "total": 237.43503371335646, "count": 351570, "is_parallel": true, "self": 237.43503371335646 }, "communicator.exchange": { "total": 3660.8622616610774, "count": 351570, "is_parallel": true, "self": 3660.8622616610774 }, "steps_from_proto": { "total": 1031.2403273758273, "count": 703140, "is_parallel": true, "self": 208.3572503934265, "children": { "_process_rank_one_or_two_observation": { "total": 822.8830769824008, "count": 2812560, "is_parallel": true, "self": 822.8830769824008 } } } } }, "steps_from_proto": { "total": 0.2925300239949138, "count": 196, "is_parallel": true, "self": 0.06102310497772123, "children": { "_process_rank_one_or_two_observation": { "total": 0.23150691901719256, "count": 784, "is_parallel": true, "self": 0.23150691901719256 } } } } } } } } }, "trainer_advance": { "total": 27713.575435202652, "count": 351571, "self": 100.40271507469151, "children": { "process_trajectory": { "total": 2156.992910522981, "count": 351571, "self": 2151.141712407979, "children": { "RLTrainer._checkpoint": { "total": 5.851198115002262, "count": 10, "self": 5.851198115002262 } } }, "_update_policy": { "total": 25456.17980960498, "count": 235, "self": 1327.0889110348544, "children": { "TorchPOCAOptimizer.update": { "total": 24129.090898570124, "count": 7062, "self": 24129.090898570124 } } } } } } }, "trainer_threads": { "total": 1.9069993868470192e-06, "count": 1, "self": 1.9069993868470192e-06 }, "TrainerController._save_models": { "total": 0.510441243997775, "count": 1, "self": 0.024752318997343536, "children": { "RLTrainer._checkpoint": { "total": 0.4856889250004315, "count": 1, "self": 0.4856889250004315 } } } } } } }