{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.145423650741577, "min": 1.8976856470108032, "max": 3.2957332134246826, "count": 1617 }, "SoccerTwos.Policy.Entropy.sum": { "value": 94614.34375, "min": 14747.623046875, "max": 148500.125, "count": 1617 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 835.0, "min": 402.0, "max": 999.0, "count": 1617 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20040.0, "min": 10652.0, "max": 31928.0, "count": 1617 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1180.6471335450399, "min": 1146.2339914532424, "max": 1198.7535925691843, "count": 821 }, "SoccerTwos.Self-play.ELO.sum": { "value": 7083.882801270239, "min": 2292.467982906485, "max": 23809.432211595293, "count": 821 }, "SoccerTwos.Step.mean": { "value": 16169561.0, "min": 9982.0, "max": 16169561.0, "count": 1617 }, "SoccerTwos.Step.sum": { "value": 16169561.0, "min": 9982.0, "max": 16169561.0, "count": 1617 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.0029534988570958376, "min": -0.07831713557243347, "max": 0.014796069823205471, "count": 1617 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.035441987216472626, "min": -1.0963337421417236, "max": 0.251533180475235, "count": 1617 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.002912085270509124, "min": -0.07828854024410248, "max": 0.014832121320068836, "count": 1617 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.03494502231478691, "min": -1.095876693725586, "max": 0.2784641981124878, "count": 1617 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1617 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1617 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.08931666721279423, "min": -0.6428571428571429, "max": 0.3695625017862767, "count": 1617 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -1.0718000065535307, "min": -9.821200013160706, "max": 5.913000028580427, "count": 1617 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.08931666721279423, "min": -0.6428571428571429, "max": 0.3695625017862767, "count": 1617 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -1.0718000065535307, "min": -9.821200013160706, "max": 5.913000028580427, "count": 1617 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1617 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1617 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.02138557273040836, "min": 0.010244516965515989, "max": 0.02537590628877903, "count": 748 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.02138557273040836, "min": 0.010244516965515989, "max": 0.02537590628877903, "count": 748 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 1.8619036211475758e-06, "min": 1.0458391153100877e-09, "max": 0.008836940381055076, "count": 748 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 1.8619036211475758e-06, "min": 1.0458391153100877e-09, "max": 0.008836940381055076, "count": 748 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 1.912558618262968e-06, "min": 1.1789494972861784e-09, "max": 0.00915419169080754, "count": 748 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 1.912558618262968e-06, "min": 1.1789494972861784e-09, "max": 0.00915419169080754, "count": 748 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 748 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 748 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 748 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 748 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 748 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 748 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1716968595", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/user/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1717064626" }, "total": 94847.630679923, "count": 1, "self": 0.20160856099391822, "children": { "run_training.setup": { "total": 0.020598568999957934, "count": 1, "self": 0.020598568999957934 }, "TrainerController.start_learning": { "total": 94847.408472793, "count": 1, "self": 29.471138336739386, "children": { "TrainerController._reset_env": { "total": 11.30946469198716, "count": 81, "self": 11.30946469198716 }, "TrainerController.advance": { "total": 94806.34087721028, "count": 1052407, "self": 31.4315624179726, "children": { "env_step": { "total": 20936.987311033437, "count": 1052407, "self": 15893.566943548358, "children": { "SubprocessEnvManager._take_step": { "total": 5023.696336873699, "count": 1052407, "self": 187.9025867474311, "children": { "TorchPolicy.evaluate": { "total": 4835.793750126268, "count": 2090378, "self": 4835.793750126268 } } }, "workers": { "total": 19.72403061137993, "count": 1052406, "self": 0.0, "children": { "worker_root": { "total": 94790.56055745442, "count": 1052406, "is_parallel": true, "self": 82165.24918971091, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003582917000130692, "count": 2, "is_parallel": true, "self": 0.001412645000982593, "children": { "_process_rank_one_or_two_observation": { "total": 0.002170271999148099, "count": 8, "is_parallel": true, "self": 0.002170271999148099 } } }, "UnityEnvironment.step": { "total": 0.028860425999937434, "count": 1, "is_parallel": true, "self": 0.0005274099999041937, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045789799969497835, "count": 1, "is_parallel": true, "self": 0.00045789799969497835 }, "communicator.exchange": { "total": 0.026198995999948238, "count": 1, "is_parallel": true, "self": 0.026198995999948238 }, "steps_from_proto": { "total": 0.0016761220003900235, "count": 2, "is_parallel": true, "self": 0.0003571830006876553, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013189389997023682, "count": 8, "is_parallel": true, "self": 0.0013189389997023682 } } } } } } }, "UnityEnvironment.step": { "total": 12625.131369670502, "count": 1052405, "is_parallel": true, "self": 652.73928951362, "children": { "UnityEnvironment._generate_step_input": { "total": 457.4250036561489, "count": 1052405, "is_parallel": true, "self": 457.4250036561489 }, "communicator.exchange": { "total": 9403.652389351964, "count": 1052405, "is_parallel": true, "self": 9403.652389351964 }, "steps_from_proto": { "total": 2111.3146871487706, "count": 2104810, "is_parallel": true, "self": 427.4679599568731, "children": { "_process_rank_one_or_two_observation": { "total": 1683.8467271918976, "count": 8419240, "is_parallel": true, "self": 1683.8467271918976 } } } } }, "steps_from_proto": { "total": 0.17999807300520843, "count": 160, "is_parallel": true, "self": 0.03715480606524579, "children": { "_process_rank_one_or_two_observation": { "total": 0.14284326693996263, "count": 640, "is_parallel": true, "self": 0.14284326693996263 } } } } } } } } }, "trainer_advance": { "total": 73837.92200375887, "count": 1052406, "self": 221.0813891531434, "children": { "process_trajectory": { "total": 4764.590263265625, "count": 1052406, "self": 4756.58690631963, "children": { "RLTrainer._checkpoint": { "total": 8.00335694599562, "count": 32, "self": 8.00335694599562 } } }, "_update_policy": { "total": 68852.2503513401, "count": 748, "self": 2333.930492313637, "children": { "TorchPOCAOptimizer.update": { "total": 66518.31985902647, "count": 22443, "self": 66518.31985902647 } } } } } } }, "trainer_threads": { "total": 2.344997483305633e-06, "count": 1, "self": 2.344997483305633e-06 }, "TrainerController._save_models": { "total": 0.2869902089878451, "count": 1, "self": 0.005619421994197182, "children": { "RLTrainer._checkpoint": { "total": 0.2813707869936479, "count": 1, "self": 0.2813707869936479 } } } } } } }