{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.4238530397415161, "min": 1.3219773769378662, "max": 3.295734167098999, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 29388.326171875, "min": 21929.291015625, "max": 136816.265625, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 64.28571428571429, "min": 43.61607142857143, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19800.0, "min": 16116.0, "max": 23628.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1804.0010818763442, "min": 1196.429808537728, "max": 1834.524868904263, "count": 4985 }, "SoccerTwos.Self-play.ELO.sum": { "value": 277816.166608957, "min": 2394.503800970352, "max": 388847.1695145124, "count": 4985 }, "SoccerTwos.Step.mean": { "value": 49999953.0, "min": 9492.0, "max": 49999953.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999953.0, "min": 9492.0, "max": 49999953.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.057602040469646454, "min": -0.15837442874908447, "max": 0.17678283154964447, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -8.87071418762207, "min": -24.713083267211914, "max": 22.09381866455078, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.057413917034864426, "min": -0.1612488180398941, "max": 0.17491061985492706, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -8.841743469238281, "min": -24.67464256286621, "max": 21.55138397216797, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.1592545435800181, "min": -0.5882352941176471, "max": 0.6777454528844717, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -24.525199711322784, "min": -60.133199751377106, "max": 64.71639966964722, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.1592545435800181, "min": -0.5882352941176471, "max": 0.6777454528844717, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -24.525199711322784, "min": -60.133199751377106, "max": 64.71639966964722, "count": 5000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.013663878637210776, "min": 0.009136462559884725, "max": 0.025849049425839137, "count": 2422 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.013663878637210776, "min": 0.009136462559884725, "max": 0.025849049425839137, "count": 2422 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09734399740894635, "min": 4.047849332285599e-06, "max": 0.12036015366514524, "count": 2422 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09734399740894635, "min": 4.047849332285599e-06, "max": 0.12036015366514524, "count": 2422 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09895000184575717, "min": 4.155637104001168e-06, "max": 0.12202610323826472, "count": 2422 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09895000184575717, "min": 4.155637104001168e-06, "max": 0.12202610323826472, "count": 2422 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2422 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2422 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2422 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2422 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2422 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2422 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1706257917", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/leimeng/miniconda3/envs/mlagents/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2", "numpy_version": "1.23.5", "end_time_seconds": "1706377851" }, "total": 119933.24872229001, "count": 1, "self": 0.4917311670142226, "children": { "run_training.setup": { "total": 0.021100579997437308, "count": 1, "self": 0.021100579997437308 }, "TrainerController.start_learning": { "total": 119932.735890543, "count": 1, "self": 75.09795328887412, "children": { "TrainerController._reset_env": { "total": 8.943238677027693, "count": 250, "self": 8.943238677027693 }, "TrainerController.advance": { "total": 119848.4561125391, "count": 3423243, "self": 73.45974579977337, "children": { "env_step": { "total": 95341.30403861389, "count": 3423243, "self": 74637.48223422017, "children": { "SubprocessEnvManager._take_step": { "total": 20652.657046497487, "count": 3423243, "self": 535.3353149352624, "children": { "TorchPolicy.evaluate": { "total": 20117.321731562224, "count": 6284364, "self": 20117.321731562224 } } }, "workers": { "total": 51.164757896229276, "count": 3423243, "self": 0.0, "children": { "worker_root": { "total": 119793.51007925742, "count": 3423243, "is_parallel": true, "self": 59045.858190623745, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022559079989150632, "count": 2, "is_parallel": true, "self": 0.0004673289986385498, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017885790002765134, "count": 8, "is_parallel": true, "self": 0.0017885790002765134 } } }, "UnityEnvironment.step": { "total": 0.048259070001222426, "count": 1, "is_parallel": true, "self": 0.000694906004355289, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005400649970397353, "count": 1, "is_parallel": true, "self": 0.0005400649970397353 }, "communicator.exchange": { "total": 0.04506709400084219, "count": 1, "is_parallel": true, "self": 0.04506709400084219 }, "steps_from_proto": { "total": 0.0019570049989852123, "count": 2, "is_parallel": true, "self": 0.0003445470028964337, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016124579960887786, "count": 8, "is_parallel": true, "self": 0.0016124579960887786 } } } } } } }, "UnityEnvironment.step": { "total": 60747.144195255525, "count": 3423242, "is_parallel": true, "self": 2183.5322492204505, "children": { "UnityEnvironment._generate_step_input": { "total": 1382.1137355629435, "count": 3423242, "is_parallel": true, "self": 1382.1137355629435 }, "communicator.exchange": { "total": 50971.27895054153, "count": 3423242, "is_parallel": true, "self": 50971.27895054153 }, "steps_from_proto": { "total": 6210.219259930596, "count": 6846484, "is_parallel": true, "self": 1020.2074655709439, "children": { "_process_rank_one_or_two_observation": { "total": 5190.011794359652, "count": 27385936, "is_parallel": true, "self": 5190.011794359652 } } } } }, "steps_from_proto": { "total": 0.5076933781529078, "count": 498, "is_parallel": true, "self": 0.08115317787451204, "children": { "_process_rank_one_or_two_observation": { "total": 0.4265402002783958, "count": 1992, "is_parallel": true, "self": 0.4265402002783958 } } } } } } } } }, "trainer_advance": { "total": 24433.692328125442, "count": 3423243, "self": 731.1396055599325, "children": { "process_trajectory": { "total": 11196.064191221769, "count": 3423243, "self": 11175.930647965764, "children": { "RLTrainer._checkpoint": { "total": 20.133543256004486, "count": 100, "self": 20.133543256004486 } } }, "_update_policy": { "total": 12506.48853134374, "count": 2422, "self": 8874.627156804709, "children": { "TorchPOCAOptimizer.update": { "total": 3631.861374539032, "count": 72660, "self": 3631.861374539032 } } } } } } }, "trainer_threads": { "total": 7.909839041531086e-07, "count": 1, "self": 7.909839041531086e-07 }, "TrainerController._save_models": { "total": 0.23858524701790884, "count": 1, "self": 0.0013369439984671772, "children": { "RLTrainer._checkpoint": { "total": 0.23724830301944166, "count": 1, "self": 0.23724830301944166 } } } } } } }