{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.222886085510254, "min": 3.178148031234741, "max": 3.2957394123077393, "count": 50 }, "SoccerTwos.Policy.Entropy.sum": { "value": 64251.45703125, "min": 24141.8125, "max": 111686.015625, "count": 50 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 999.0, "min": 515.4444444444445, "max": 999.0, "count": 50 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19980.0, "min": 16532.0, "max": 23096.0, "count": 50 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1194.305937242978, "min": 1194.305937242978, "max": 1201.0458342366899, "count": 34 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2388.611874485956, "min": 2388.611874485956, "max": 12009.361480906444, "count": 34 }, "SoccerTwos.Step.mean": { "value": 499752.0, "min": 9963.0, "max": 499752.0, "count": 50 }, "SoccerTwos.Step.sum": { "value": 499752.0, "min": 9963.0, "max": 499752.0, "count": 50 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.0019104421371594071, "min": -0.004330075345933437, "max": 0.0973353311419487, "count": 50 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.019104421138763428, "min": -0.07794135808944702, "max": 1.6546697616577148, "count": 50 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.002890198025852442, "min": -0.004277398809790611, "max": 0.09731447696685791, "count": 50 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.028901979327201843, "min": -0.0769931748509407, "max": 1.6542727947235107, "count": 50 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 50 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 50 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.0, "min": -0.3572363636710427, "max": 0.24661538234123817, "count": 50 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.0, "min": -4.064800024032593, "max": 3.2720000743865967, "count": 50 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0, "min": -0.3572363636710427, "max": 0.24661538234123817, "count": 50 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.0, "min": -4.064800024032593, "max": 3.2720000743865967, "count": 50 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.015863731885231876, "min": 0.012046212951342264, "max": 0.023246557872820026, "count": 23 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015863731885231876, "min": 0.012046212951342264, "max": 0.023246557872820026, "count": 23 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0007692288233859775, "min": 2.1364471285778565e-05, "max": 0.00678142998367548, "count": 23 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0007692288233859775, "min": 2.1364471285778565e-05, "max": 0.00678142998367548, "count": 23 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0007680021929748667, "min": 1.998041240464469e-05, "max": 0.006190592252338926, "count": 23 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0007680021929748667, "min": 1.998041240464469e-05, "max": 0.006190592252338926, "count": 23 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 23 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 23 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 23 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 23 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 23 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 23 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1715746790", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/kmpartner/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1715748486" }, "total": 1696.4477653340437, "count": 1, "self": 0.6252628850052133, "children": { "run_training.setup": { "total": 0.031541642965748906, "count": 1, "self": 0.031541642965748906 }, "TrainerController.start_learning": { "total": 1695.7909608060727, "count": 1, "self": 0.8745869067497551, "children": { "TrainerController._reset_env": { "total": 2.128251589019783, "count": 3, "self": 2.128251589019783 }, "TrainerController.advance": { "total": 1692.405556101352, "count": 32749, "self": 0.974522753385827, "children": { "env_step": { "total": 713.5457443424966, "count": 32749, "self": 550.6820350628113, "children": { "SubprocessEnvManager._take_step": { "total": 162.3319782523904, "count": 32749, "self": 6.4123608890222386, "children": { "TorchPolicy.evaluate": { "total": 155.91961736336816, "count": 65006, "self": 155.91961736336816 } } }, "workers": { "total": 0.5317310272948816, "count": 32749, "self": 0.0, "children": { "worker_root": { "total": 1693.2569843787933, "count": 32749, "is_parallel": true, "self": 1250.2550589101156, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022038460010662675, "count": 2, "is_parallel": true, "self": 0.0005877942312508821, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016160517698153853, "count": 8, "is_parallel": true, "self": 0.0016160517698153853 } } }, "UnityEnvironment.step": { "total": 0.026585781015455723, "count": 1, "is_parallel": true, "self": 0.0006709620356559753, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0012815509689971805, "count": 1, "is_parallel": true, "self": 0.0012815509689971805 }, "communicator.exchange": { "total": 0.02198748104274273, "count": 1, "is_parallel": true, "self": 0.02198748104274273 }, "steps_from_proto": { "total": 0.002645786968059838, "count": 2, "is_parallel": true, "self": 0.0006291840691119432, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020166028989478946, "count": 8, "is_parallel": true, "self": 0.0020166028989478946 } } } } } } }, "UnityEnvironment.step": { "total": 442.9973188138101, "count": 32748, "is_parallel": true, "self": 26.376526315929368, "children": { "UnityEnvironment._generate_step_input": { "total": 19.166821150225587, "count": 32748, "is_parallel": true, "self": 19.166821150225587 }, "communicator.exchange": { "total": 317.7364962728461, "count": 32748, "is_parallel": true, "self": 317.7364962728461 }, "steps_from_proto": { "total": 79.71747507480904, "count": 65496, "is_parallel": true, "self": 16.635344981681556, "children": { "_process_rank_one_or_two_observation": { "total": 63.08213009312749, "count": 261984, "is_parallel": true, "self": 63.08213009312749 } } } } }, "steps_from_proto": { "total": 0.004606654867529869, "count": 4, "is_parallel": true, "self": 0.001007852959446609, "children": { "_process_rank_one_or_two_observation": { "total": 0.00359880190808326, "count": 16, "is_parallel": true, "self": 0.00359880190808326 } } } } } } } } }, "trainer_advance": { "total": 977.8852890054695, "count": 32749, "self": 6.8977531949058175, "children": { "process_trajectory": { "total": 130.68859679682646, "count": 32749, "self": 130.35695404780563, "children": { "RLTrainer._checkpoint": { "total": 0.3316427490208298, "count": 1, "self": 0.3316427490208298 } } }, "_update_policy": { "total": 840.2989390137373, "count": 23, "self": 70.57781462674029, "children": { "TorchPOCAOptimizer.update": { "total": 769.721124386997, "count": 690, "self": 769.721124386997 } } } } } } }, "trainer_threads": { "total": 1.0479707270860672e-06, "count": 1, "self": 1.0479707270860672e-06 }, "TrainerController._save_models": { "total": 0.3825651609804481, "count": 1, "self": 0.002786148921586573, "children": { "RLTrainer._checkpoint": { "total": 0.37977901205886155, "count": 1, "self": 0.37977901205886155 } } } } } } }