{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.292717933654785, "min": 2.2663424015045166, "max": 3.2957677841186523, "count": 566 }, "SoccerTwos.Policy.Entropy.sum": { "value": 44607.12109375, "min": 10051.4208984375, "max": 142803.0625, "count": 566 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 50.618556701030926, "min": 43.97345132743363, "max": 999.0, "count": 566 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19640.0, "min": 15212.0, "max": 24248.0, "count": 566 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1486.4148442009343, "min": 1179.706223024584, "max": 1486.4148442009343, "count": 501 }, "SoccerTwos.Self-play.ELO.sum": { "value": 288364.4797749813, "min": 2360.146349147463, "max": 328342.7055349428, "count": 501 }, "SoccerTwos.Step.mean": { "value": 5659962.0, "min": 9672.0, "max": 5659962.0, "count": 566 }, "SoccerTwos.Step.sum": { "value": 5659962.0, "min": 9672.0, "max": 5659962.0, "count": 566 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.039656296372413635, "min": -0.12947434186935425, "max": 0.1382981240749359, "count": 566 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 7.693321228027344, "min": -18.660633087158203, "max": 21.66172218322754, "count": 566 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.039549946784973145, "min": -0.12532289326190948, "max": 0.1415165513753891, "count": 566 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 7.672689437866211, "min": -17.545204162597656, "max": 21.361865997314453, "count": 566 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 566 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 566 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.1206061864636608, "min": -0.5965846135066106, "max": 0.4601599991321564, "count": 566 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 23.397600173950195, "min": -47.004000186920166, "max": 66.19439995288849, "count": 566 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.1206061864636608, "min": -0.5965846135066106, "max": 0.4601599991321564, "count": 566 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 23.397600173950195, "min": -47.004000186920166, "max": 66.19439995288849, "count": 566 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 566 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 566 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.022239530365914105, "min": 0.010096545951091685, "max": 0.023152435064548626, "count": 267 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.022239530365914105, "min": 0.010096545951091685, "max": 0.023152435064548626, "count": 267 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09612657402952512, "min": 6.308880415417662e-07, "max": 0.10640911161899566, "count": 267 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09612657402952512, "min": 6.308880415417662e-07, "max": 0.10640911161899566, "count": 267 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09836790338158607, "min": 7.920101258681218e-07, "max": 0.10937313909331957, "count": 267 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09836790338158607, "min": 7.920101258681218e-07, "max": 0.10937313909331957, "count": 267 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 267 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 267 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 267 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 267 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 267 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 267 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1677417398", "python_version": "3.9.16 (main, Jan 11 2023, 10:02:19) \n[Clang 14.0.6 ]", "command_line_arguments": "/opt/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.app --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": "1.11.0", "numpy_version": "1.21.2", "end_time_seconds": "1677439701" }, "total": 22303.072364749998, "count": 1, "self": 0.32343374899573973, "children": { "run_training.setup": { "total": 0.2731806670000001, "count": 1, "self": 0.2731806670000001 }, "TrainerController.start_learning": { "total": 22302.475750334, "count": 1, "self": 4.137907545617054, "children": { "TrainerController._reset_env": { "total": 4.081350543002182, "count": 29, "self": 4.081350543002182 }, "TrainerController.advance": { "total": 22294.11792557938, "count": 374061, "self": 4.102707851754531, "children": { "env_step": { "total": 17869.848999263504, "count": 374061, "self": 17274.55872279339, "children": { "SubprocessEnvManager._take_step": { "total": 592.2230997697567, "count": 374061, "self": 18.98845215279391, "children": { "TorchPolicy.evaluate": { "total": 573.2346476169628, "count": 724964, "self": 573.2346476169628 } } }, "workers": { "total": 3.067176700355809, "count": 374060, "self": 0.0, "children": { "worker_root": { "total": 22292.01485277676, "count": 374060, "is_parallel": true, "self": 5553.071921290801, "children": { "steps_from_proto": { "total": 0.045345873008321824, "count": 58, "is_parallel": true, "self": 0.005311340010161203, "children": { "_process_rank_one_or_two_observation": { "total": 0.04003453299816062, "count": 232, "is_parallel": true, "self": 0.04003453299816062 } } }, "UnityEnvironment.step": { "total": 16738.89758561295, "count": 374060, "is_parallel": true, "self": 47.77328840074915, "children": { "UnityEnvironment._generate_step_input": { "total": 298.2748947990431, "count": 374060, "is_parallel": true, "self": 298.2748947990431 }, "communicator.exchange": { "total": 15737.70776385374, "count": 374060, "is_parallel": true, "self": 15737.70776385374 }, "steps_from_proto": { "total": 655.1416385594167, "count": 748120, "is_parallel": true, "self": 70.73070426205845, "children": { "_process_rank_one_or_two_observation": { "total": 584.4109342973583, "count": 2992480, "is_parallel": true, "self": 584.4109342973583 } } } } } } } } } } }, "trainer_advance": { "total": 4420.166218464119, "count": 374060, "self": 42.170455885034244, "children": { "process_trajectory": { "total": 658.6330152480891, "count": 374060, "self": 657.0412877480867, "children": { "RLTrainer._checkpoint": { "total": 1.5917275000024347, "count": 11, "self": 1.5917275000024347 } } }, "_update_policy": { "total": 3719.362747330996, "count": 267, "self": 454.0781210390619, "children": { "TorchPOCAOptimizer.update": { "total": 3265.2846262919343, "count": 8010, "self": 3265.2846262919343 } } } } } } }, "trainer_threads": { "total": 5.830006557516754e-07, "count": 1, "self": 5.830006557516754e-07 }, "TrainerController._save_models": { "total": 0.1385660830019333, "count": 1, "self": 0.0009357080016343389, "children": { "RLTrainer._checkpoint": { "total": 0.13763037500029895, "count": 1, "self": 0.13763037500029895 } } } } } } }