{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.791628360748291, "min": 1.735303282737732, "max": 3.2957119941711426, "count": 879 }, "SoccerTwos.Policy.Entropy.sum": { "value": 34857.921875, "min": 13446.552734375, "max": 141640.171875, "count": 879 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 68.1917808219178, "min": 49.61616161616162, "max": 999.0, "count": 879 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19912.0, "min": 3996.0, "max": 31224.0, "count": 879 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1596.2409319507847, "min": 1186.8126055332164, "max": 1620.3184736724454, "count": 807 }, "SoccerTwos.Self-play.ELO.sum": { "value": 233051.17606481456, "min": 2373.6252110664327, "max": 318548.889616456, "count": 807 }, "SoccerTwos.Step.mean": { "value": 8789938.0, "min": 9148.0, "max": 8789938.0, "count": 879 }, "SoccerTwos.Step.sum": { "value": 8789938.0, "min": 9148.0, "max": 8789938.0, "count": 879 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.015257895924150944, "min": -0.13309119641780853, "max": 0.22954100370407104, "count": 879 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -2.212394952774048, "min": -16.13796615600586, "max": 32.54047775268555, "count": 879 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.015654107555747032, "min": -0.13294994831085205, "max": 0.23057672381401062, "count": 879 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -2.269845724105835, "min": -17.22362518310547, "max": 32.340572357177734, "count": 879 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 879 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 879 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.004852411253698941, "min": -0.6153846153846154, "max": 0.48171628491823065, "count": 879 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.7035996317863464, "min": -52.18440043926239, "max": 65.81360006332397, "count": 879 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.004852411253698941, "min": -0.6153846153846154, "max": 0.48171628491823065, "count": 879 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.7035996317863464, "min": -52.18440043926239, "max": 65.81360006332397, "count": 879 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 879 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 879 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.016110525854552787, "min": 0.011214561320957727, "max": 0.02530888847153013, "count": 419 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016110525854552787, "min": 0.011214561320957727, "max": 0.02530888847153013, "count": 419 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.095163727303346, "min": 2.7799073407663857e-07, "max": 0.10515277435382207, "count": 419 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.095163727303346, "min": 2.7799073407663857e-07, "max": 0.10515277435382207, "count": 419 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09731189881761869, "min": 3.049724206505289e-07, "max": 0.10713796441753705, "count": 419 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09731189881761869, "min": 3.049724206505289e-07, "max": 0.10713796441753705, "count": 419 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 419 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 419 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 419 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 419 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 419 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 419 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1710785195", "python_version": "3.10.12 (main, Jul 5 2023, 15:02:25) [Clang 14.0.6 ]", "command_line_arguments": "/opt/homebrew/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1", "numpy_version": "1.23.5", "end_time_seconds": "1710826245" }, "total": 37501.77599775001, "count": 1, "self": 0.17920458301523468, "children": { "run_training.setup": { "total": 0.03125733300112188, "count": 1, "self": 0.03125733300112188 }, "TrainerController.start_learning": { "total": 37501.56553583399, "count": 1, "self": 7.007030306500383, "children": { "TrainerController._reset_env": { "total": 8.093730084023264, "count": 44, "self": 8.093730084023264 }, "TrainerController.advance": { "total": 37486.349426527464, "count": 591223, "self": 6.801121357726515, "children": { "env_step": { "total": 29141.95539214684, "count": 591223, "self": 28126.724425609842, "children": { "SubprocessEnvManager._take_step": { "total": 1010.812899589393, "count": 591223, "self": 31.608927101558947, "children": { "TorchPolicy.evaluate": { "total": 979.2039724878341, "count": 1116124, "self": 979.2039724878341 } } }, "workers": { "total": 4.41806694760453, "count": 591222, "self": 0.0, "children": { "worker_root": { "total": 37486.50146003467, "count": 591222, "is_parallel": true, "self": 10235.900265968987, "children": { "steps_from_proto": { "total": 0.09003241801110562, "count": 88, "is_parallel": true, "self": 0.010110262002854142, "children": { "_process_rank_one_or_two_observation": { "total": 0.07992215600825148, "count": 352, "is_parallel": true, "self": 0.07992215600825148 } } }, "UnityEnvironment.step": { "total": 27250.51116164767, "count": 591222, "is_parallel": true, "self": 77.03721077784576, "children": { "UnityEnvironment._generate_step_input": { "total": 482.1863650019877, "count": 591222, "is_parallel": true, "self": 482.1863650019877 }, "communicator.exchange": { "total": 25671.4253012892, "count": 591222, "is_parallel": true, "self": 25671.4253012892 }, "steps_from_proto": { "total": 1019.8622845786376, "count": 1182444, "is_parallel": true, "self": 110.07768299250893, "children": { "_process_rank_one_or_two_observation": { "total": 909.7846015861287, "count": 4729776, "is_parallel": true, "self": 909.7846015861287 } } } } } } } } } } }, "trainer_advance": { "total": 8337.592913022898, "count": 591222, "self": 58.09901485214505, "children": { "process_trajectory": { "total": 1213.6244861298765, "count": 591222, "self": 1210.9133504228666, "children": { "RLTrainer._checkpoint": { "total": 2.7111357070098165, "count": 17, "self": 2.7111357070098165 } } }, "_update_policy": { "total": 7065.869412040876, "count": 420, "self": 719.8241967614667, "children": { "TorchPOCAOptimizer.update": { "total": 6346.04521527941, "count": 12612, "self": 6346.04521527941 } } } } } } }, "trainer_threads": { "total": 1.45800004247576e-06, "count": 1, "self": 1.45800004247576e-06 }, "TrainerController._save_models": { "total": 0.11534745800599921, "count": 1, "self": 0.0017820830107666552, "children": { "RLTrainer._checkpoint": { "total": 0.11356537499523256, "count": 1, "self": 0.11356537499523256 } } } } } } }