{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.6364408731460571, "min": 1.2111297845840454, "max": 3.295790433883667, "count": 29261 }, "SoccerTwos.Policy.Entropy.sum": { "value": 1256.78662109375, "min": 38.75615310668945, "max": 75934.9140625, "count": 29261 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 107.5, "min": 1.5, "max": 999.0, "count": 29815 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 860.0, "min": 12.0, "max": 19980.0, "count": 29815 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1681.6275089035726, "min": 1189.5147432814815, "max": 1744.6113248627523, "count": 29560 }, "SoccerTwos.Self-play.ELO.sum": { "value": 6726.51003561429, "min": 2379.029486562963, "max": 23797.706080004307, "count": 29560 }, "SoccerTwos.Step.mean": { "value": 7999830.0, "min": 66.0, "max": 7999830.0, "count": 35757 }, "SoccerTwos.Step.sum": { "value": 7999830.0, "min": 66.0, "max": 7999830.0, "count": 35757 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.2291768193244934, "min": -0.6357744336128235, "max": 0.5942150354385376, "count": 35757 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.2291768193244934, "min": -2.943234920501709, "max": 4.191102027893066, "count": 35757 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.2442202866077423, "min": -0.6416802406311035, "max": 0.6011806726455688, "count": 35757 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.2442202866077423, "min": -2.953758955001831, "max": 4.2166595458984375, "count": 35757 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 35757 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 35757 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -1.0, "min": -1.0, "max": 0.9932000041007996, "count": 35757 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -1.0, "min": -9.0, "max": 8.780399978160858, "count": 35757 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -1.0, "min": -1.0, "max": 0.9932000041007996, "count": 35757 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -1.0, "min": -9.0, "max": 8.780399978160858, "count": 35757 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 35757 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 35757 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.023088003506321304, "min": 0.012560889627153907, "max": 0.027914463468672088, "count": 386 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.023088003506321304, "min": 0.012560889627153907, "max": 0.027914463468672088, "count": 386 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.08402285973230998, "min": 5.7798829341966966e-05, "max": 0.10703929290175437, "count": 386 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.08402285973230998, "min": 5.7798829341966966e-05, "max": 0.10703929290175437, "count": 386 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0861522302031517, "min": 5.083439458151891e-05, "max": 0.1108598418533802, "count": 386 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0861522302031517, "min": 5.083439458151891e-05, "max": 0.1108598418533802, "count": 386 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 386 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 386 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 386 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 386 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 386 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 386 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1681975243", "python_version": "3.9.16 (main, Mar 8 2023, 10:39:24) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\andre\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos_2 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.0+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1682024082" }, "total": 48839.2381127, "count": 1, "self": 1.5360641999941436, "children": { "run_training.setup": { "total": 0.23951239999999885, "count": 1, "self": 0.23951239999999885 }, "TrainerController.start_learning": { "total": 48837.4625361, "count": 1, "self": 18.071318898437312, "children": { "TrainerController._reset_env": { "total": 22.469729600012784, "count": 40, "self": 22.469729600012784 }, "TrainerController.advance": { "total": 48796.55171660154, "count": 544485, "self": 18.84643090087775, "children": { "env_step": { "total": 13480.940880298956, "count": 544485, "self": 9624.141251096935, "children": { "SubprocessEnvManager._take_step": { "total": 3845.350842202946, "count": 544485, "self": 125.70891010125706, "children": { "TorchPolicy.evaluate": { "total": 3719.641932101689, "count": 1006372, "self": 3719.641932101689 } } }, "workers": { "total": 11.44878699907548, "count": 544485, "self": 0.0, "children": { "worker_root": { "total": 48790.7222916014, "count": 544485, "is_parallel": true, "self": 41243.46022880326, "children": { "steps_from_proto": { "total": 0.10577209997159187, "count": 80, "is_parallel": true, "self": 0.021406299991507893, "children": { "_process_rank_one_or_two_observation": { "total": 0.08436579998008398, "count": 320, "is_parallel": true, "self": 0.08436579998008398 } } }, "UnityEnvironment.step": { "total": 7547.156290698165, "count": 544485, "is_parallel": true, "self": 433.1522372964082, "children": { "UnityEnvironment._generate_step_input": { "total": 388.46125400078466, "count": 544485, "is_parallel": true, "self": 388.46125400078466 }, "communicator.exchange": { "total": 5352.378265900363, "count": 544485, "is_parallel": true, "self": 5352.378265900363 }, "steps_from_proto": { "total": 1373.1645335006097, "count": 1088970, "is_parallel": true, "self": 279.40359070710474, "children": { "_process_rank_one_or_two_observation": { "total": 1093.760942793505, "count": 4355880, "is_parallel": true, "self": 1093.760942793505 } } } } } } } } } } }, "trainer_advance": { "total": 35296.76440540171, "count": 544485, "self": 131.58449890200427, "children": { "process_trajectory": { "total": 6924.779084599799, "count": 544485, "self": 6919.675474399804, "children": { "RLTrainer._checkpoint": { "total": 5.103610199994364, "count": 16, "self": 5.103610199994364 } } }, "_update_policy": { "total": 28240.400821899908, "count": 386, "self": 1867.136166400087, "children": { "TorchPOCAOptimizer.update": { "total": 26373.26465549982, "count": 11598, "self": 26373.26465549982 } } } } } } }, "trainer_threads": { "total": 1.500004145782441e-06, "count": 1, "self": 1.500004145782441e-06 }, "TrainerController._save_models": { "total": 0.3697695000009844, "count": 1, "self": 0.07219520000217017, "children": { "RLTrainer._checkpoint": { "total": 0.29757429999881424, "count": 1, "self": 0.29757429999881424 } } } } } } }