{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.2040687799453735, "min": 1.1219825744628906, "max": 3.2958030700683594, "count": 2640 }, "SoccerTwos.Policy.Entropy.sum": { "value": 22771.34765625, "min": 18050.201171875, "max": 114194.09375, "count": 2640 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 122.09756097560975, "min": 61.6025641025641, "max": 999.0, "count": 2640 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20024.0, "min": 14192.0, "max": 26196.0, "count": 2640 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1301.0902970657933, "min": 1194.7567604058934, "max": 1433.9689477036732, "count": 2629 }, "SoccerTwos.Self-play.ELO.sum": { "value": 106689.40435939505, "min": 2390.665136762985, "max": 222596.79464384494, "count": 2629 }, "SoccerTwos.Step.mean": { "value": 26399966.0, "min": 9118.0, "max": 26399966.0, "count": 2640 }, "SoccerTwos.Step.sum": { "value": 26399966.0, "min": 9118.0, "max": 26399966.0, "count": 2640 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.020633932203054428, "min": -0.1691311001777649, "max": 0.18548260629177094, "count": 2640 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -1.691982388496399, "min": -17.420503616333008, "max": 21.19671630859375, "count": 2640 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.025985613465309143, "min": -0.1659875512123108, "max": 0.18798771500587463, "count": 2640 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -2.1308202743530273, "min": -17.096717834472656, "max": 21.21693992614746, "count": 2640 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2640 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2640 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.05973658910611781, "min": -0.5882352941176471, "max": 0.589699998497963, "count": 2640 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 4.89840030670166, "min": -53.241200149059296, "max": 50.68460041284561, "count": 2640 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.05973658910611781, "min": -0.5882352941176471, "max": 0.589699998497963, "count": 2640 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 4.89840030670166, "min": -53.241200149059296, "max": 50.68460041284561, "count": 2640 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2640 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2640 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.05916573769878596, "min": 0.014727666127146221, "max": 0.06476284949108958, "count": 1274 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.05916573769878596, "min": 0.014727666127146221, "max": 0.06476284949108958, "count": 1274 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.036328843757510186, "min": 3.303538255750027e-05, "max": 0.04980021875351667, "count": 1274 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.036328843757510186, "min": 3.303538255750027e-05, "max": 0.04980021875351667, "count": 1274 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.040351981054991486, "min": 3.0598190978707865e-05, "max": 0.06439892433583737, "count": 1274 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.040351981054991486, "min": 3.0598190978707865e-05, "max": 0.06439892433583737, "count": 1274 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.00030000000000000003, "min": 0.00030000000000000003, "max": 0.00030000000000000003, "count": 1274 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.00030000000000000003, "min": 0.00030000000000000003, "max": 0.00030000000000000003, "count": 1274 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.19999999999999996, "min": 0.19999999999999996, "max": 0.19999999999999996, "count": 1274 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.19999999999999996, "min": 0.19999999999999996, "max": 0.19999999999999996, "count": 1274 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.004999999999999999, "min": 0.004999999999999999, "max": 0.004999999999999999, "count": 1274 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.004999999999999999, "min": 0.004999999999999999, "max": 0.004999999999999999, "count": 1274 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1675281728", "python_version": "3.8.16 (default, Jan 17 2023, 23:13:24) \n[GCC 11.2.0]", "command_line_arguments": "/home/scronberg/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTows.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": "1.8.1+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1675326155" }, "total": 44427.014995833, "count": 1, "self": 0.0036816049978369847, "children": { "run_training.setup": { "total": 0.00895804600440897, "count": 1, "self": 0.00895804600440897 }, "TrainerController.start_learning": { "total": 44427.002356182, "count": 1, "self": 26.85775732066395, "children": { "TrainerController._reset_env": { "total": 4.629524488998868, "count": 132, "self": 4.629524488998868 }, "TrainerController.advance": { "total": 44395.08597004933, "count": 1755849, "self": 27.14806772385782, "children": { "env_step": { "total": 25248.474443247353, "count": 1755849, "self": 19771.718410271133, "children": { "SubprocessEnvManager._take_step": { "total": 5460.537820406556, "count": 1755849, "self": 143.82949247430952, "children": { "TorchPolicy.evaluate": { "total": 5316.708327932247, "count": 3327573, "self": 5316.708327932247 } } }, "workers": { "total": 16.218212569663592, "count": 1755848, "self": 0.0, "children": { "worker_root": { "total": 44393.28487471762, "count": 1755848, "is_parallel": true, "self": 27634.41306151142, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.03541345099074533, "count": 2, "is_parallel": true, "self": 0.0003729880045284517, "children": { "_process_rank_one_or_two_observation": { "total": 0.03504046298621688, "count": 8, "is_parallel": true, "self": 0.03504046298621688 } } }, "UnityEnvironment.step": { "total": 0.020131671997660305, "count": 1, "is_parallel": true, "self": 0.00048455199430463836, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00033487100154161453, "count": 1, "is_parallel": true, "self": 0.00033487100154161453 }, "communicator.exchange": { "total": 0.017845364003733266, "count": 1, "is_parallel": true, "self": 0.017845364003733266 }, "steps_from_proto": { "total": 0.0014668849980807863, "count": 2, "is_parallel": true, "self": 0.00032007699337555096, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011468080047052354, "count": 8, "is_parallel": true, "self": 0.0011468080047052354 } } } } } } }, "UnityEnvironment.step": { "total": 16758.665657927115, "count": 1755847, "is_parallel": true, "self": 829.5780516541345, "children": { "UnityEnvironment._generate_step_input": { "total": 522.5357124114307, "count": 1755847, "is_parallel": true, "self": 522.5357124114307 }, "communicator.exchange": { "total": 12678.727184324693, "count": 1755847, "is_parallel": true, "self": 12678.727184324693 }, "steps_from_proto": { "total": 2727.824709536857, "count": 3511694, "is_parallel": true, "self": 463.8954271825496, "children": { "_process_rank_one_or_two_observation": { "total": 2263.9292823543074, "count": 14046776, "is_parallel": true, "self": 2263.9292823543074 } } } } }, "steps_from_proto": { "total": 0.20615527908375952, "count": 262, "is_parallel": true, "self": 0.03483163588680327, "children": { "_process_rank_one_or_two_observation": { "total": 0.17132364319695625, "count": 1048, "is_parallel": true, "self": 0.17132364319695625 } } } } } } } } }, "trainer_advance": { "total": 19119.46345907812, "count": 1755848, "self": 164.2737193386056, "children": { "process_trajectory": { "total": 2554.9596213254845, "count": 1755848, "self": 2534.7993398674516, "children": { "RLTrainer._checkpoint": { "total": 20.16028145803284, "count": 52, "self": 20.16028145803284 } } }, "_update_policy": { "total": 16400.23011841403, "count": 1274, "self": 8568.021764169462, "children": { "TorchPOCAOptimizer.update": { "total": 7832.208354244569, "count": 127400, "self": 7832.208354244569 } } } } } } }, "trainer_threads": { "total": 6.589980330318213e-07, "count": 1, "self": 6.589980330318213e-07 }, "TrainerController._save_models": { "total": 0.42910366400610656, "count": 1, "self": 0.003340544004458934, "children": { "RLTrainer._checkpoint": { "total": 0.4257631200016476, "count": 1, "self": 0.4257631200016476 } } } } } } }