{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.3551076650619507, "min": 1.3005881309509277, "max": 3.217240333557129, "count": 4929 }, "SoccerTwos.Policy.Entropy.sum": { "value": 28186.240234375, "min": 21324.09765625, "max": 120224.3125, "count": 4929 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 54.92134831460674, "min": 41.724137931034484, "max": 999.0, "count": 4929 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19552.0, "min": 7992.0, "max": 31968.0, "count": 4929 }, "SoccerTwos.Step.mean": { "value": 49999828.0, "min": 699059.0, "max": 49999828.0, "count": 4931 }, "SoccerTwos.Step.sum": { "value": 49999828.0, "min": 699059.0, "max": 49999828.0, "count": 4931 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.009020297788083553, "min": -0.12972207367420197, "max": 0.21567855775356293, "count": 4931 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 1.614633321762085, "min": -23.065719604492188, "max": 34.462650299072266, "count": 4931 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.00902334414422512, "min": -0.13501568138599396, "max": 0.2189803421497345, "count": 4931 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 1.6151785850524902, "min": -24.30282211303711, "max": 34.87063217163086, "count": 4931 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 4931 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 4931 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.06246704029637342, "min": -0.6989111105600992, "max": 0.5232327233661305, "count": 4931 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 11.181600213050842, "min": -64.03359979391098, "max": 60.12459993362427, "count": 4931 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.06246704029637342, "min": -0.6989111105600992, "max": 0.5232327233661305, "count": 4931 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 11.181600213050842, "min": -64.03359979391098, "max": 60.12459993362427, "count": 4931 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 4931 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 4931 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1702.6599980680758, "min": 1171.0258805222504, "max": 1763.907757351499, "count": 4856 }, "SoccerTwos.Self-play.ELO.sum": { "value": 303073.4796561175, "min": 2344.7155979355525, "max": 397694.2489781823, "count": 4856 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01681608337094076, "min": 0.009783732601984714, "max": 0.025116191385313867, "count": 2385 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01681608337094076, "min": 0.009783732601984714, "max": 0.025116191385313867, "count": 2385 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09890874822934469, "min": 4.6114543389800625e-07, "max": 0.12489540229241053, "count": 2385 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09890874822934469, "min": 4.6114543389800625e-07, "max": 0.12489540229241053, "count": 2385 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10023266946276028, "min": 5.945804900875373e-07, "max": 0.12647117500503857, "count": 2385 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10023266946276028, "min": 5.945804900875373e-07, "max": 0.12647117500503857, "count": 2385 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2385 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2385 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999993, "max": 0.20000000000000007, "count": 2385 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999993, "max": 0.20000000000000007, "count": 2385 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 2385 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 2385 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1702629464", "python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul 5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\ProgramData\\Anaconda3\\envs\\HuggingMARL\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --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": "2.1.2+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1702797579" }, "total": 168114.168036, "count": 1, "self": 1.027366099995561, "children": { "run_training.setup": { "total": 0.10216080001555383, "count": 1, "self": 0.10216080001555383 }, "TrainerController.start_learning": { "total": 168113.03850909998, "count": 1, "self": 88.98916922067292, "children": { "TrainerController._reset_env": { "total": 9.664814599673264, "count": 248, "self": 9.664814599673264 }, "TrainerController.advance": { "total": 168014.24563167966, "count": 3388847, "self": 90.71629579400178, "children": { "env_step": { "total": 59482.39426160592, "count": 3388847, "self": 44287.60472441348, "children": { "SubprocessEnvManager._take_step": { "total": 15139.790341105894, "count": 3388847, "self": 504.0101298833033, "children": { "TorchPolicy.evaluate": { "total": 14635.78021122259, "count": 6204168, "self": 14635.78021122259 } } }, "workers": { "total": 54.99919608654454, "count": 3388847, "self": 0.0, "children": { "worker_root": { "total": 167990.94669422018, "count": 3388847, "is_parallel": true, "self": 133363.29030840646, "children": { "steps_from_proto": { "total": 0.46730180049780756, "count": 496, "is_parallel": true, "self": 0.10150650062132627, "children": { "_process_rank_one_or_two_observation": { "total": 0.3657952998764813, "count": 1984, "is_parallel": true, "self": 0.3657952998764813 } } }, "UnityEnvironment.step": { "total": 34627.189084013226, "count": 3388847, "is_parallel": true, "self": 1849.7905010344693, "children": { "UnityEnvironment._generate_step_input": { "total": 1517.6188403441338, "count": 3388847, "is_parallel": true, "self": 1517.6188403441338 }, "communicator.exchange": { "total": 25278.275953509496, "count": 3388847, "is_parallel": true, "self": 25278.275953509496 }, "steps_from_proto": { "total": 5981.503789125127, "count": 6777694, "is_parallel": true, "self": 1295.7783491901355, "children": { "_process_rank_one_or_two_observation": { "total": 4685.725439934991, "count": 27110776, "is_parallel": true, "self": 4685.725439934991 } } } } } } } } } } }, "trainer_advance": { "total": 108441.13507427974, "count": 3388847, "self": 615.3841125188628, "children": { "process_trajectory": { "total": 16942.099893463426, "count": 3388847, "self": 16928.103306163917, "children": { "RLTrainer._checkpoint": { "total": 13.996587299508974, "count": 99, "self": 13.996587299508974 } } }, "_update_policy": { "total": 90883.65106829745, "count": 2385, "self": 8150.811721911421, "children": { "TorchPOCAOptimizer.update": { "total": 82732.83934638603, "count": 71580, "self": 82732.83934638603 } } } } } } }, "trainer_threads": { "total": 1.00000761449337e-06, "count": 1, "self": 1.00000761449337e-06 }, "TrainerController._save_models": { "total": 0.13889259996358305, "count": 1, "self": 0.002369800000451505, "children": { "RLTrainer._checkpoint": { "total": 0.13652279996313155, "count": 1, "self": 0.13652279996313155 } } } } } } }