{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.9123839139938354, "min": 1.8586629629135132, "max": 3.295715093612671, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 41307.4921875, "min": 27052.228515625, "max": 136430.390625, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 57.88636363636363, "min": 38.01550387596899, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20376.0, "min": 14420.0, "max": 25772.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1445.284206837498, "min": 1182.0790663438002, "max": 1445.284206837498, "count": 489 }, "SoccerTwos.Self-play.ELO.sum": { "value": 254370.02040339966, "min": 2367.2119315077525, "max": 359386.85722408467, "count": 489 }, "SoccerTwos.Step.mean": { "value": 4999968.0, "min": 9902.0, "max": 4999968.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999968.0, "min": 9902.0, "max": 4999968.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.004807638004422188, "min": -0.13918200135231018, "max": 0.1848352700471878, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.8461443185806274, "min": -23.674182891845703, "max": 24.404869079589844, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.004330995958298445, "min": -0.13881231844425201, "max": 0.17856308817863464, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.7622553110122681, "min": -22.707561492919922, "max": 25.537357330322266, "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": -0.007961365309628573, "min": -0.4812952393577212, "max": 0.4446526307808725, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -1.401200294494629, "min": -58.43999981880188, "max": 53.03399991989136, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.007961365309628573, "min": -0.4812952393577212, "max": 0.4446526307808725, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -1.401200294494629, "min": -58.43999981880188, "max": 53.03399991989136, "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": 0.019551223715340408, "min": 0.011763235189331074, "max": 0.023467257199808956, "count": 241 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.019551223715340408, "min": 0.011763235189331074, "max": 0.023467257199808956, "count": 241 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10825960362950961, "min": 0.0005028678776094845, "max": 0.12593363150954245, "count": 241 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10825960362950961, "min": 0.0005028678776094845, "max": 0.12593363150954245, "count": 241 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11062059924006462, "min": 0.0005052745740006989, "max": 0.12917420317729314, "count": 241 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11062059924006462, "min": 0.0005052745740006989, "max": 0.12917420317729314, "count": 241 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 241 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 241 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 241 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 241 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 241 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 241 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1675377028", "python_version": "3.8.16 (default, Jan 17 2023, 22:25:28) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\ramon\\anaconda3\\envs\\rl_football\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.13.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1675446459" }, "total": 69430.4055333, "count": 1, "self": 5.4624247000028845, "children": { "run_training.setup": { "total": 0.5304941000000003, "count": 1, "self": 0.5304941000000003 }, "TrainerController.start_learning": { "total": 69424.41261449999, "count": 1, "self": 37.512698197126156, "children": { "TrainerController._reset_env": { "total": 42.70524019994433, "count": 247, "self": 42.70524019994433 }, "TrainerController.advance": { "total": 69343.48036080292, "count": 371942, "self": 38.3307116022479, "children": { "env_step": { "total": 32190.79712180086, "count": 371942, "self": 25245.651534200955, "children": { "SubprocessEnvManager._take_step": { "total": 6921.271136400079, "count": 371942, "self": 225.9350217047422, "children": { "TorchPolicy.evaluate": { "total": 6695.336114695337, "count": 688446, "self": 6695.336114695337 } } }, "workers": { "total": 23.874451199826893, "count": 371942, "self": 0.0, "children": { "worker_root": { "total": 69353.98075460165, "count": 371942, "is_parallel": true, "self": 48812.80978330002, "children": { "steps_from_proto": { "total": 2.2767385000589115, "count": 494, "is_parallel": true, "self": 0.47010410003138325, "children": { "_process_rank_one_or_two_observation": { "total": 1.8066344000275283, "count": 1976, "is_parallel": true, "self": 1.8066344000275283 } } }, "UnityEnvironment.step": { "total": 20538.89423280157, "count": 371942, "is_parallel": true, "self": 1051.736260403508, "children": { "UnityEnvironment._generate_step_input": { "total": 854.3487916006318, "count": 371942, "is_parallel": true, "self": 854.3487916006318 }, "communicator.exchange": { "total": 15088.009963200224, "count": 371942, "is_parallel": true, "self": 15088.009963200224 }, "steps_from_proto": { "total": 3544.7992175972054, "count": 743884, "is_parallel": true, "self": 734.7381438002503, "children": { "_process_rank_one_or_two_observation": { "total": 2810.061073796955, "count": 2975536, "is_parallel": true, "self": 2810.061073796955 } } } } } } } } } } }, "trainer_advance": { "total": 37114.35252739981, "count": 371942, "self": 176.73296379892417, "children": { "process_trajectory": { "total": 8119.682047300889, "count": 371942, "self": 8113.048368300908, "children": { "RLTrainer._checkpoint": { "total": 6.6336789999813845, "count": 10, "self": 6.6336789999813845 } } }, "_update_policy": { "total": 28817.937516299997, "count": 241, "self": 4260.068384399907, "children": { "TorchPOCAOptimizer.update": { "total": 24557.86913190009, "count": 7233, "self": 24557.86913190009 } } } } } } }, "trainer_threads": { "total": 7.199996616691351e-06, "count": 1, "self": 7.199996616691351e-06 }, "TrainerController._save_models": { "total": 0.7143081000103848, "count": 1, "self": 0.14671720001206268, "children": { "RLTrainer._checkpoint": { "total": 0.5675908999983221, "count": 1, "self": 0.5675908999983221 } } } } } } }