{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.5075193643569946, "min": 1.4223438501358032, "max": 3.29575777053833, "count": 1684 }, "SoccerTwos.Policy.Entropy.sum": { "value": 30536.3125, "min": 21724.7421875, "max": 172076.078125, "count": 1684 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 49.628865979381445, "min": 36.97727272727273, "max": 999.0, "count": 1684 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19256.0, "min": 16400.0, "max": 24280.0, "count": 1684 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1548.8406443673402, "min": 1202.9386188779174, "max": 1588.4355426754382, "count": 1616 }, "SoccerTwos.Self-play.ELO.sum": { "value": 300475.085007264, "min": 2405.877237755835, "max": 404247.29001054686, "count": 1616 }, "SoccerTwos.Step.mean": { "value": 16839944.0, "min": 9162.0, "max": 16839944.0, "count": 1684 }, "SoccerTwos.Step.sum": { "value": 16839944.0, "min": 9162.0, "max": 16839944.0, "count": 1684 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.010396160185337067, "min": -0.13093166053295135, "max": 0.16393695771694183, "count": 1684 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 2.016855001449585, "min": -24.76071548461914, "max": 27.682390213012695, "count": 1684 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.012765331193804741, "min": -0.12848448753356934, "max": 0.18016555905342102, "count": 1684 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 2.4764742851257324, "min": -25.138809204101562, "max": 27.552812576293945, "count": 1684 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1684 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1684 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.02118144330290175, "min": -0.6553411764257094, "max": 0.46176469939596515, "count": 1684 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 4.1092000007629395, "min": -56.14080011844635, "max": 59.756800055503845, "count": 1684 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.02118144330290175, "min": -0.6553411764257094, "max": 0.46176469939596515, "count": 1684 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 4.1092000007629395, "min": -56.14080011844635, "max": 59.756800055503845, "count": 1684 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1684 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1684 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.020544298365712164, "min": 0.00970811143379251, "max": 0.025192880642134697, "count": 809 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.020544298365712164, "min": 0.00970811143379251, "max": 0.025192880642134697, "count": 809 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.11354104181130727, "min": 8.301274097751351e-07, "max": 0.12650607749819756, "count": 809 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.11354104181130727, "min": 8.301274097751351e-07, "max": 0.12650607749819756, "count": 809 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11532666459679604, "min": 9.456767202209449e-07, "max": 0.12839160487055779, "count": 809 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11532666459679604, "min": 9.456767202209449e-07, "max": 0.12839160487055779, "count": 809 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 809 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 809 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 809 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 809 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 809 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 809 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1729838318", "python_version": "3.10.12 (main, Jul 5 2023, 15:02:25) [Clang 14.0.6 ]", "command_line_arguments": "/opt/anaconda3/envs/rl3/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.0", "numpy_version": "1.23.5", "end_time_seconds": "1729885903" }, "total": 47583.77235337498, "count": 1, "self": 0.15778812498319894, "children": { "run_training.setup": { "total": 0.014746833010576665, "count": 1, "self": 0.014746833010576665 }, "TrainerController.start_learning": { "total": 47583.59981841699, "count": 1, "self": 10.320242145215161, "children": { "TrainerController._reset_env": { "total": 5.96240825462155, "count": 85, "self": 5.96240825462155 }, "TrainerController.advance": { "total": 47567.240067725186, "count": 1155809, "self": 8.499234364717267, "children": { "env_step": { "total": 38672.649586675456, "count": 1155809, "self": 37406.00112313824, "children": { "SubprocessEnvManager._take_step": { "total": 1260.434232891188, "count": 1155809, "self": 39.95918971253559, "children": { "TorchPolicy.evaluate": { "total": 1220.4750431786524, "count": 2128420, "self": 1220.4750431786524 } } }, "workers": { "total": 6.214230646030046, "count": 1155809, "self": 0.0, "children": { "worker_root": { "total": 47565.91652237286, "count": 1155809, "is_parallel": true, "self": 11339.841364476248, "children": { "steps_from_proto": { "total": 0.09973392367828637, "count": 170, "is_parallel": true, "self": 0.012506206054240465, "children": { "_process_rank_one_or_two_observation": { "total": 0.08722771762404591, "count": 680, "is_parallel": true, "self": 0.08722771762404591 } } }, "UnityEnvironment.step": { "total": 36225.97542397294, "count": 1155809, "is_parallel": true, "self": 100.28258109081071, "children": { "UnityEnvironment._generate_step_input": { "total": 645.6035189076792, "count": 1155809, "is_parallel": true, "self": 645.6035189076792 }, "communicator.exchange": { "total": 34217.75499016093, "count": 1155809, "is_parallel": true, "self": 34217.75499016093 }, "steps_from_proto": { "total": 1262.3343338135164, "count": 2311618, "is_parallel": true, "self": 148.4430766660953, "children": { "_process_rank_one_or_two_observation": { "total": 1113.8912571474211, "count": 9246472, "is_parallel": true, "self": 1113.8912571474211 } } } } } } } } } } }, "trainer_advance": { "total": 8886.091246685013, "count": 1155809, "self": 74.03028768778313, "children": { "process_trajectory": { "total": 1645.7643202384934, "count": 1155809, "self": 1642.761222984409, "children": { "RLTrainer._checkpoint": { "total": 3.003097254084423, "count": 33, "self": 3.003097254084423 } } }, "_update_policy": { "total": 7166.296638758737, "count": 810, "self": 825.5450803557178, "children": { "TorchPOCAOptimizer.update": { "total": 6340.751558403019, "count": 24300, "self": 6340.751558403019 } } } } } } }, "trainer_threads": { "total": 5.420297384262085e-07, "count": 1, "self": 5.420297384262085e-07 }, "TrainerController._save_models": { "total": 0.07709974993485957, "count": 1, "self": 0.0006019159918650985, "children": { "RLTrainer._checkpoint": { "total": 0.07649783394299448, "count": 1, "self": 0.07649783394299448 } } } } } } }