{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.864931583404541, "min": 2.864931583404541, "max": 3.2957441806793213, "count": 255 }, "SoccerTwos.Policy.Entropy.sum": { "value": 48864.2734375, "min": 12480.634765625, "max": 178433.421875, "count": 255 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 999.0, "min": 478.3333333333333, "max": 999.0, "count": 255 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19980.0, "min": 9792.0, "max": 29416.0, "count": 255 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1195.30262923943, "min": 1189.6334909643583, "max": 1202.0356094770125, "count": 116 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2390.60525847886, "min": 2380.5412822753306, "max": 12006.791665556262, "count": 116 }, "SoccerTwos.Step.mean": { "value": 2549052.0, "min": 9724.0, "max": 2549052.0, "count": 255 }, "SoccerTwos.Step.sum": { "value": 2549052.0, "min": 9724.0, "max": 2549052.0, "count": 255 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.0002825286064762622, "min": -0.06660731136798859, "max": 0.01318393088877201, "count": 255 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.002825286006554961, "min": -0.757354199886322, "max": 0.15519078075885773, "count": 255 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.0002746201935224235, "min": -0.06658301502466202, "max": 0.013858472928404808, "count": 255 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.0027462018188089132, "min": -0.7921212315559387, "max": 0.1527690440416336, "count": 255 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 255 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 255 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.0, "min": -0.5833333333333334, "max": 0.33981334368387855, "count": 255 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.0, "min": -7.0, "max": 5.097200155258179, "count": 255 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0, "min": -0.5833333333333334, "max": 0.33981334368387855, "count": 255 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.0, "min": -7.0, "max": 5.097200155258179, "count": 255 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 255 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 255 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01995301543114086, "min": 0.011099783669730337, "max": 0.024405772452397893, "count": 118 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01995301543114086, "min": 0.011099783669730337, "max": 0.024405772452397893, "count": 118 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 1.918163589446446e-08, "min": 1.918163589446446e-08, "max": 0.004566526940713326, "count": 118 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 1.918163589446446e-08, "min": 1.918163589446446e-08, "max": 0.004566526940713326, "count": 118 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 2.0073384613776095e-08, "min": 2.0073384613776095e-08, "max": 0.004702418344095349, "count": 118 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 2.0073384613776095e-08, "min": 2.0073384613776095e-08, "max": 0.004702418344095349, "count": 118 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 118 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 118 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 118 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 118 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 118 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 118 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1724170803", "python_version": "3.10.12 (main, Jul 5 2023, 15:02:25) [Clang 14.0.6 ]", "command_line_arguments": "/opt/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos_5M --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.0", "numpy_version": "1.23.5", "end_time_seconds": "1724178754" }, "total": 7950.472635999999, "count": 1, "self": 0.10020720800093841, "children": { "run_training.setup": { "total": 0.015575166995404288, "count": 1, "self": 0.015575166995404288 }, "TrainerController.start_learning": { "total": 7950.356853625002, "count": 1, "self": 1.2982587292717653, "children": { "TrainerController._reset_env": { "total": 2.532843123008206, "count": 13, "self": 2.532843123008206 }, "TrainerController.advance": { "total": 7946.441075480718, "count": 166210, "self": 1.25506760882854, "children": { "env_step": { "total": 6501.729888595008, "count": 166210, "self": 6277.077386762125, "children": { "SubprocessEnvManager._take_step": { "total": 223.76940332233062, "count": 166210, "self": 7.403025823805365, "children": { "TorchPolicy.evaluate": { "total": 216.36637749852525, "count": 330166, "self": 216.36637749852525 } } }, "workers": { "total": 0.8830985105523723, "count": 166209, "self": 0.0, "children": { "worker_root": { "total": 7946.606903452448, "count": 166209, "is_parallel": true, "self": 1893.9419978722435, "children": { "steps_from_proto": { "total": 0.01726654399681138, "count": 26, "is_parallel": true, "self": 0.0021638749822159298, "children": { "_process_rank_one_or_two_observation": { "total": 0.015102669014595449, "count": 104, "is_parallel": true, "self": 0.015102669014595449 } } }, "UnityEnvironment.step": { "total": 6052.647639036208, "count": 166209, "is_parallel": true, "self": 15.642283670429606, "children": { "UnityEnvironment._generate_step_input": { "total": 100.19444427818962, "count": 166209, "is_parallel": true, "self": 100.19444427818962 }, "communicator.exchange": { "total": 5728.305372888979, "count": 166209, "is_parallel": true, "self": 5728.305372888979 }, "steps_from_proto": { "total": 208.50553819860943, "count": 332418, "is_parallel": true, "self": 22.67950864489103, "children": { "_process_rank_one_or_two_observation": { "total": 185.8260295537184, "count": 1329672, "is_parallel": true, "self": 185.8260295537184 } } } } } } } } } } }, "trainer_advance": { "total": 1443.4561192768815, "count": 166209, "self": 14.123393716807186, "children": { "process_trajectory": { "total": 217.66670772805082, "count": 166209, "self": 217.20782285405585, "children": { "RLTrainer._checkpoint": { "total": 0.45888487399497535, "count": 5, "self": 0.45888487399497535 } } }, "_update_policy": { "total": 1211.6660178320235, "count": 118, "self": 143.5592218879101, "children": { "TorchPOCAOptimizer.update": { "total": 1068.1067959441134, "count": 3543, "self": 1068.1067959441134 } } } } } } }, "trainer_threads": { "total": 5.00003807246685e-07, "count": 1, "self": 5.00003807246685e-07 }, "TrainerController._save_models": { "total": 0.08467579200078035, "count": 1, "self": 0.0013275000019348226, "children": { "RLTrainer._checkpoint": { "total": 0.08334829199884553, "count": 1, "self": 0.08334829199884553 } } } } } } }