{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.6904041767120361, "min": 1.6904041767120361, "max": 3.295828342437744, "count": 1000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 31373.90234375, "min": 30855.255859375, "max": 107373.4921875, "count": 1000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 62.223684210526315, "min": 41.042735042735046, "max": 999.0, "count": 1000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 18916.0, "min": 14456.0, "max": 25876.0, "count": 1000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1505.5654356524688, "min": 1190.9937210547932, "max": 1528.816168391446, "count": 998 }, "SoccerTwos.Self-play.ELO.sum": { "value": 228845.94621917524, "min": 2384.1991119945988, "max": 341659.6208856196, "count": 998 }, "SoccerTwos.Step.mean": { "value": 9999960.0, "min": 9684.0, "max": 9999960.0, "count": 1000 }, "SoccerTwos.Step.sum": { "value": 9999960.0, "min": 9684.0, "max": 9999960.0, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.021533388644456863, "min": -0.14438019692897797, "max": 0.18974851071834564, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -3.2946083545684814, "min": -20.496976852416992, "max": 23.52881622314453, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.020931841805577278, "min": -0.138943612575531, "max": 0.18486110866069794, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -3.2025718688964844, "min": -20.91425323486328, "max": 22.92277717590332, "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": 0.009445750635433821, "min": -0.625, "max": 0.4306620667720663, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 1.4451998472213745, "min": -69.94459998607635, "max": 42.50040006637573, "count": 1000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.009445750635433821, "min": -0.625, "max": 0.4306620667720663, "count": 1000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 1.4451998472213745, "min": -69.94459998607635, "max": 42.50040006637573, "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": 0.013262719112390187, "min": 0.007267597714962904, "max": 0.017278411099687217, "count": 243 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.013262719112390187, "min": 0.007267597714962904, "max": 0.017278411099687217, "count": 243 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.08443939536809922, "min": 0.0016251095352345147, "max": 0.11132827904075385, "count": 243 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.08443939536809922, "min": 0.0016251095352345147, "max": 0.11132827904075385, "count": 243 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.08609315231442452, "min": 0.001621522156347055, "max": 0.11312161087989807, "count": 243 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.08609315231442452, "min": 0.001621522156347055, "max": 0.11312161087989807, "count": 243 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 243 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 243 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.2, "min": 0.2, "max": 0.2, "count": 243 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.2, "min": 0.2, "max": 0.2, "count": 243 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005, "min": 0.005, "max": 0.005, "count": 243 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005, "min": 0.005, "max": 0.005, "count": 243 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1681400793", "python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]", "command_line_arguments": "/anaconda/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --force --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+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1681418891" }, "total": 18097.326334434, "count": 1, "self": 1.4654128270012734, "children": { "run_training.setup": { "total": 0.06966816799968001, "count": 1, "self": 0.06966816799968001 }, "TrainerController.start_learning": { "total": 18095.791253439, "count": 1, "self": 14.124513753697101, "children": { "TrainerController._reset_env": { "total": 13.560869624994666, "count": 100, "self": 13.560869624994666 }, "TrainerController.advance": { "total": 18066.703308018306, "count": 690896, "self": 14.496848152270104, "children": { "env_step": { "total": 12382.015595357303, "count": 690896, "self": 8790.504927490492, "children": { "SubprocessEnvManager._take_step": { "total": 3583.6868403290887, "count": 690896, "self": 89.14229998571545, "children": { "TorchPolicy.evaluate": { "total": 3494.5445403433732, "count": 1266756, "self": 3494.5445403433732 } } }, "workers": { "total": 7.823827537722082, "count": 690896, "self": 0.0, "children": { "worker_root": { "total": 18068.245141560226, "count": 690896, "is_parallel": true, "self": 10914.655148137948, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003106338000179676, "count": 2, "is_parallel": true, "self": 0.0008824550004646881, "children": { "_process_rank_one_or_two_observation": { "total": 0.002223882999714988, "count": 8, "is_parallel": true, "self": 0.002223882999714988 } } }, "UnityEnvironment.step": { "total": 0.025750114999937068, "count": 1, "is_parallel": true, "self": 0.0006053669999346312, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005618700001832622, "count": 1, "is_parallel": true, "self": 0.0005618700001832622 }, "communicator.exchange": { "total": 0.022749475999717106, "count": 1, "is_parallel": true, "self": 0.022749475999717106 }, "steps_from_proto": { "total": 0.001833402000102069, "count": 2, "is_parallel": true, "self": 0.0004115790002288122, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014218229998732568, "count": 8, "is_parallel": true, "self": 0.0014218229998732568 } } } } } } }, "UnityEnvironment.step": { "total": 7153.403618047258, "count": 690895, "is_parallel": true, "self": 391.8650398342852, "children": { "UnityEnvironment._generate_step_input": { "total": 271.32354886834355, "count": 690895, "is_parallel": true, "self": 271.32354886834355 }, "communicator.exchange": { "total": 5322.061446691012, "count": 690895, "is_parallel": true, "self": 5322.061446691012 }, "steps_from_proto": { "total": 1168.153582653616, "count": 1381790, "is_parallel": true, "self": 249.47668309119263, "children": { "_process_rank_one_or_two_observation": { "total": 918.6768995624234, "count": 5527160, "is_parallel": true, "self": 918.6768995624234 } } } } }, "steps_from_proto": { "total": 0.18637537501990664, "count": 198, "is_parallel": true, "self": 0.03953962803598188, "children": { "_process_rank_one_or_two_observation": { "total": 0.14683574698392476, "count": 792, "is_parallel": true, "self": 0.14683574698392476 } } } } } } } } }, "trainer_advance": { "total": 5670.190864508732, "count": 690896, "self": 105.78475479125427, "children": { "process_trajectory": { "total": 2497.7491164954786, "count": 690896, "self": 2469.2401843234825, "children": { "RLTrainer._checkpoint": { "total": 28.508932171996094, "count": 20, "self": 28.508932171996094 } } }, "_update_policy": { "total": 3066.6569932219995, "count": 243, "self": 2197.973723531895, "children": { "TorchPOCAOptimizer.update": { "total": 868.6832696901047, "count": 9720, "self": 868.6832696901047 } } } } } } }, "trainer_threads": { "total": 1.1000010999850929e-06, "count": 1, "self": 1.1000010999850929e-06 }, "TrainerController._save_models": { "total": 1.4025609420023102, "count": 1, "self": 0.1260476670031494, "children": { "RLTrainer._checkpoint": { "total": 1.2765132749991608, "count": 1, "self": 1.2765132749991608 } } } } } } }