{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.5888909101486206, "min": 1.571339726448059, "max": 3.2957446575164795, "count": 1000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 31879.5078125, "min": 28644.826171875, "max": 147545.90625, "count": 1000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 49.22222222222222, "min": 40.51260504201681, "max": 999.0, "count": 1000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19492.0, "min": 5084.0, "max": 30192.0, "count": 1000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1679.0176978760417, "min": 1194.7070766179352, "max": 1704.459136388523, "count": 986 }, "SoccerTwos.Self-play.ELO.sum": { "value": 332445.5041794563, "min": 2390.9871681159348, "max": 398753.2600412559, "count": 986 }, "SoccerTwos.Step.mean": { "value": 9999946.0, "min": 9512.0, "max": 9999946.0, "count": 1000 }, "SoccerTwos.Step.sum": { "value": 9999946.0, "min": 9512.0, "max": 9999946.0, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.06979527324438095, "min": -0.13052012026309967, "max": 0.1664070039987564, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -13.819464683532715, "min": -22.579980850219727, "max": 25.442827224731445, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.07360540330410004, "min": -0.12285048514604568, "max": 0.16845263540744781, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -14.573869705200195, "min": -21.351919174194336, "max": 26.163158416748047, "count": 1000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.09636161483899512, "min": -0.5333333333333333, "max": 0.40000701996318083, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -19.079599738121033, "min": -58.31099957227707, "max": 56.07600039243698, "count": 1000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.09636161483899512, "min": -0.5333333333333333, "max": 0.40000701996318083, "count": 1000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -19.079599738121033, "min": -58.31099957227707, "max": 56.07600039243698, "count": 1000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.015936278041044714, "min": 0.010288070857253235, "max": 0.02491610542492708, "count": 482 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015936278041044714, "min": 0.010288070857253235, "max": 0.02491610542492708, "count": 482 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.11955500766634941, "min": 6.951558937847343e-06, "max": 0.12987020537257193, "count": 482 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.11955500766634941, "min": 6.951558937847343e-06, "max": 0.12987020537257193, "count": 482 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.12300647149483362, "min": 1.128340013565321e-05, "max": 0.1324800950785478, "count": 482 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.12300647149483362, "min": 1.128340013565321e-05, "max": 0.1324800950785478, "count": 482 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 482 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 482 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 482 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 482 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 482 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 482 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1677295731", "python_version": "3.10.6 (main, Nov 14 2022, 16:10:14) [GCC 11.3.0]", "command_line_arguments": "/home/zipbomb/.local/share/virtualenvs/HF-RL-faxHmpJw/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env ../SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu113", "numpy_version": "1.21.2", "end_time_seconds": "1677320404" }, "total": 24673.064149468002, "count": 1, "self": 0.26983999599906383, "children": { "run_training.setup": { "total": 0.009792885000024398, "count": 1, "self": 0.009792885000024398 }, "TrainerController.start_learning": { "total": 24672.784516587002, "count": 1, "self": 11.13979328739515, "children": { "TrainerController._reset_env": { "total": 5.506416542994089, "count": 50, "self": 5.506416542994089 }, "TrainerController.advance": { "total": 24655.923696224614, "count": 685977, "self": 9.669845434505987, "children": { "env_step": { "total": 19836.44688725222, "count": 685977, "self": 12664.629140945897, "children": { "SubprocessEnvManager._take_step": { "total": 7164.484170848609, "count": 685977, "self": 60.2685017676431, "children": { "TorchPolicy.evaluate": { "total": 7104.215669080966, "count": 1258688, "self": 7104.215669080966 } } }, "workers": { "total": 7.333575457713664, "count": 685977, "self": 0.0, "children": { "worker_root": { "total": 24643.533769548787, "count": 685977, "is_parallel": true, "self": 13214.31041869205, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021718269999837503, "count": 2, "is_parallel": true, "self": 0.0006294349999507176, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015423920000330327, "count": 8, "is_parallel": true, "self": 0.0015423920000330327 } } }, "UnityEnvironment.step": { "total": 0.036916527000016686, "count": 1, "is_parallel": true, "self": 0.000653515999715637, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006365070000811102, "count": 1, "is_parallel": true, "self": 0.0006365070000811102 }, "communicator.exchange": { "total": 0.03375780500005021, "count": 1, "is_parallel": true, "self": 0.03375780500005021 }, "steps_from_proto": { "total": 0.0018686990001697268, "count": 2, "is_parallel": true, "self": 0.0004022280004392087, "children": { "_process_rank_one_or_two_observation": { "total": 0.001466470999730518, "count": 8, "is_parallel": true, "self": 0.001466470999730518 } } } } } } }, "UnityEnvironment.step": { "total": 11429.15689735272, "count": 685976, "is_parallel": true, "self": 345.7586457823545, "children": { "UnityEnvironment._generate_step_input": { "total": 211.27631940359606, "count": 685976, "is_parallel": true, "self": 211.27631940359606 }, "communicator.exchange": { "total": 9902.177730124135, "count": 685976, "is_parallel": true, "self": 9902.177730124135 }, "steps_from_proto": { "total": 969.9442020426347, "count": 1371952, "is_parallel": true, "self": 168.79481287256135, "children": { "_process_rank_one_or_two_observation": { "total": 801.1493891700734, "count": 5487808, "is_parallel": true, "self": 801.1493891700734 } } } } }, "steps_from_proto": { "total": 0.0664535040177725, "count": 98, "is_parallel": true, "self": 0.011357043998032168, "children": { "_process_rank_one_or_two_observation": { "total": 0.055096460019740334, "count": 392, "is_parallel": true, "self": 0.055096460019740334 } } } } } } } } }, "trainer_advance": { "total": 4809.806963537888, "count": 685977, "self": 85.04995679648437, "children": { "process_trajectory": { "total": 2660.789986080395, "count": 685977, "self": 2656.5308116764036, "children": { "RLTrainer._checkpoint": { "total": 4.259174403991437, "count": 20, "self": 4.259174403991437 } } }, "_update_policy": { "total": 2063.967020661008, "count": 482, "self": 1139.4434591519298, "children": { "TorchPOCAOptimizer.update": { "total": 924.5235615090783, "count": 14469, "self": 924.5235615090783 } } } } } } }, "trainer_threads": { "total": 7.300004654098302e-07, "count": 1, "self": 7.300004654098302e-07 }, "TrainerController._save_models": { "total": 0.21460980199844926, "count": 1, "self": 0.00179122999907122, "children": { "RLTrainer._checkpoint": { "total": 0.21281857199937804, "count": 1, "self": 0.21281857199937804 } } } } } } }