{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.863402843475342, "min": 2.8418586254119873, "max": 3.2956948280334473, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 57909.45703125, "min": 16824.85546875, "max": 148237.46875, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 86.92857142857143, "min": 72.04411764705883, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19472.0, "min": 4884.0, "max": 29948.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1318.5978989021112, "min": 1194.0640425488612, "max": 1323.746780218973, "count": 398 }, "SoccerTwos.Self-play.ELO.sum": { "value": 147682.96467703645, "min": 2388.1280850977223, "max": 178693.59971130683, "count": 398 }, "SoccerTwos.Step.mean": { "value": 4999998.0, "min": 9258.0, "max": 4999998.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999998.0, "min": 9258.0, "max": 4999998.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.0024093177635222673, "min": -0.060914769768714905, "max": 0.16929885745048523, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.2722529172897339, "min": -8.284408569335938, "max": 14.221104621887207, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.009136270731687546, "min": -0.06261375546455383, "max": 0.1744844764471054, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 1.0323985815048218, "min": -8.515470504760742, "max": 14.656696319580078, "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": 0.0307398222189034, "min": -0.5333333333333333, "max": 0.4670666642487049, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 3.473599910736084, "min": -40.27520024776459, "max": 36.327200055122375, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0307398222189034, "min": -0.5333333333333333, "max": 0.4670666642487049, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 3.473599910736084, "min": -40.27520024776459, "max": 36.327200055122375, "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": 0.017211358656641095, "min": 0.011587637230210628, "max": 0.02452330959883208, "count": 232 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017211358656641095, "min": 0.011587637230210628, "max": 0.02452330959883208, "count": 232 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.05854383024076621, "min": 1.005996855004317e-06, "max": 0.0648781197766463, "count": 232 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.05854383024076621, "min": 1.005996855004317e-06, "max": 0.0648781197766463, "count": 232 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.05999068741997083, "min": 1.3523445394033237e-06, "max": 0.06687828612824281, "count": 232 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.05999068741997083, "min": 1.3523445394033237e-06, "max": 0.06687828612824281, "count": 232 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 232 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 232 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 232 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 232 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 232 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 232 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1702284732", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", "command_line_arguments": "/home/giulia/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwosN --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1702298193" }, "total": 13460.7845673, "count": 1, "self": 1.7956099999992148, "children": { "run_training.setup": { "total": 0.0414395999999968, "count": 1, "self": 0.0414395999999968 }, "TrainerController.start_learning": { "total": 13458.9475177, "count": 1, "self": 7.450014800146164, "children": { "TrainerController._reset_env": { "total": 13.12735950000279, "count": 25, "self": 13.12735950000279 }, "TrainerController.advance": { "total": 13437.849233499852, "count": 326343, "self": 9.080444799572433, "children": { "env_step": { "total": 10943.651513499686, "count": 326343, "self": 6875.888252799553, "children": { "SubprocessEnvManager._take_step": { "total": 4062.7215727999906, "count": 326343, "self": 64.16633119938297, "children": { "TorchPolicy.evaluate": { "total": 3998.5552416006076, "count": 645142, "self": 3998.5552416006076 } } }, "workers": { "total": 5.041687900142634, "count": 326343, "self": 0.0, "children": { "worker_root": { "total": 13440.917202100192, "count": 326343, "is_parallel": true, "self": 7507.967370800142, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003072199999998304, "count": 2, "is_parallel": true, "self": 0.001370099999981278, "children": { "_process_rank_one_or_two_observation": { "total": 0.001702100000017026, "count": 8, "is_parallel": true, "self": 0.001702100000017026 } } }, "UnityEnvironment.step": { "total": 0.02837019999999768, "count": 1, "is_parallel": true, "self": 0.0004579000000006772, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00034999999999740794, "count": 1, "is_parallel": true, "self": 0.00034999999999740794 }, "communicator.exchange": { "total": 0.026116500000000542, "count": 1, "is_parallel": true, "self": 0.026116500000000542 }, "steps_from_proto": { "total": 0.0014457999999990534, "count": 2, "is_parallel": true, "self": 0.00034640000002639226, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010993999999726611, "count": 8, "is_parallel": true, "self": 0.0010993999999726611 } } } } } } }, "UnityEnvironment.step": { "total": 5932.910143500053, "count": 326342, "is_parallel": true, "self": 178.9587261008901, "children": { "UnityEnvironment._generate_step_input": { "total": 135.33032190009277, "count": 326342, "is_parallel": true, "self": 135.33032190009277 }, "communicator.exchange": { "total": 5027.371411200163, "count": 326342, "is_parallel": true, "self": 5027.371411200163 }, "steps_from_proto": { "total": 591.2496842989079, "count": 652684, "is_parallel": true, "self": 134.45183469819182, "children": { "_process_rank_one_or_two_observation": { "total": 456.7978496007161, "count": 2610736, "is_parallel": true, "self": 456.7978496007161 } } } } }, "steps_from_proto": { "total": 0.03968779999763683, "count": 48, "is_parallel": true, "self": 0.00879139999221934, "children": { "_process_rank_one_or_two_observation": { "total": 0.03089640000541749, "count": 192, "is_parallel": true, "self": 0.03089640000541749 } } } } } } } } }, "trainer_advance": { "total": 2485.1172752005928, "count": 326343, "self": 57.36275270098531, "children": { "process_trajectory": { "total": 939.5547369996184, "count": 326343, "self": 935.2898431996175, "children": { "RLTrainer._checkpoint": { "total": 4.264893800000891, "count": 10, "self": 4.264893800000891 } } }, "_update_policy": { "total": 1488.1997854999888, "count": 232, "self": 659.7722875999405, "children": { "TorchPOCAOptimizer.update": { "total": 828.4274979000484, "count": 6975, "self": 828.4274979000484 } } } } } } }, "trainer_threads": { "total": 8.999995770864189e-07, "count": 1, "self": 8.999995770864189e-07 }, "TrainerController._save_models": { "total": 0.5209090000007564, "count": 1, "self": 0.08256520000031742, "children": { "RLTrainer._checkpoint": { "total": 0.43834380000043893, "count": 1, "self": 0.43834380000043893 } } } } } } }