{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.9276041984558105, "min": 2.4052186012268066, "max": 3.2904653549194336, "count": 100 }, "SoccerTwos.Policy.Entropy.sum": { "value": 291074.125, "min": 238352.21875, "max": 387127.46875, "count": 100 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 209.0252100840336, "min": 209.0252100840336, "max": 999.0, "count": 100 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 99496.0, "min": 96476.0, "max": 103388.0, "count": 100 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1247.5067176617156, "min": 1191.821214563696, "max": 1247.5067176617156, "count": 97 }, "SoccerTwos.Self-play.ELO.sum": { "value": 291916.57193284144, "min": 2400.650068158895, "max": 291916.57193284144, "count": 97 }, "SoccerTwos.Step.mean": { "value": 4999609.0, "min": 49542.0, "max": 4999609.0, "count": 100 }, "SoccerTwos.Step.sum": { "value": 4999609.0, "min": 49542.0, "max": 4999609.0, "count": 100 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.03594151511788368, "min": -0.7357847094535828, "max": 0.025285867974162102, "count": 100 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -8.554080963134766, "min": -43.41129684448242, "max": 1.5930097103118896, "count": 100 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.03636329248547554, "min": -0.8936510682106018, "max": 0.017634503543376923, "count": 100 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -8.654463768005371, "min": -52.72541427612305, "max": 1.1109737157821655, "count": 100 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 100 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 100 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.10871008630184566, "min": -0.33413783843452866, "max": 0.13830344892781357, "count": 100 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -25.873000539839268, "min": -49.45240008831024, "max": 14.424399744719267, "count": 100 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.10871008630184566, "min": -0.33413783843452866, "max": 0.13830344892781357, "count": 100 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -25.873000539839268, "min": -49.45240008831024, "max": 14.424399744719267, "count": 100 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.015674322063245604, "min": 0.013229400619942074, "max": 0.020409159014040293, "count": 100 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.047022966189736816, "min": 0.026458801239884148, "max": 0.06077529178000987, "count": 100 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.03280250411480665, "min": 5.554975217592073e-07, "max": 2.004074016927431, "count": 100 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09840751234441995, "min": 1.1109950435184146e-06, "max": 4.008148033854862, "count": 100 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.03239279271413883, "min": 5.764401040172136e-06, "max": 1.9272995501135788, "count": 100 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09717837814241648, "min": 1.1528802080344273e-05, "max": 3.8545991002271576, "count": 100 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 100 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0009, "min": 0.0006, "max": 0.0009, "count": 100 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 100 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.6000000000000002, "min": 0.40000000000000013, "max": 0.6000000000000002, "count": 100 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 100 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.015000000000000003, "min": 0.010000000000000002, "max": 0.015000000000000003, "count": 100 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1684325861", "python_version": "3.9.16 (main, Mar 8 2023, 10:39:24) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\Flooow\\.conda\\envs\\rl\\Scripts\\mlagents-learn ./ml-agents/config/poca/SoccerTwos.yaml --env=./SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos-10M --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cu117", "numpy_version": "1.21.2", "end_time_seconds": "1684339219" }, "total": 13358.6668326, "count": 1, "self": 2.4185096000001067, "children": { "run_training.setup": { "total": 0.38227429999999885, "count": 1, "self": 0.38227429999999885 }, "TrainerController.start_learning": { "total": 13355.8660487, "count": 1, "self": 9.284362800175586, "children": { "TrainerController._reset_env": { "total": 24.4538974000049, "count": 25, "self": 24.4538974000049 }, "TrainerController.advance": { "total": 13321.34535139982, "count": 325072, "self": 10.613710400095442, "children": { "env_step": { "total": 9782.534153199958, "count": 325072, "self": 6388.8133864996325, "children": { "SubprocessEnvManager._take_step": { "total": 3387.858826500375, "count": 325072, "self": 75.56248100037419, "children": { "TorchPolicy.evaluate": { "total": 3312.296345500001, "count": 644422, "self": 3312.296345500001 } } }, "workers": { "total": 5.861940199950787, "count": 325072, "self": 0.0, "children": { "worker_root": { "total": 13320.95867869975, "count": 325072, "is_parallel": true, "self": 8095.300613399635, "children": { "steps_from_proto": { "total": 0.05063430000442537, "count": 50, "is_parallel": true, "self": 0.010809200011571818, "children": { "_process_rank_one_or_two_observation": { "total": 0.03982509999285355, "count": 200, "is_parallel": true, "self": 0.03982509999285355 } } }, "UnityEnvironment.step": { "total": 5225.60743100011, "count": 325072, "is_parallel": true, "self": 219.4212635013946, "children": { "UnityEnvironment._generate_step_input": { "total": 179.61969119948486, "count": 325072, "is_parallel": true, "self": 179.61969119948486 }, "communicator.exchange": { "total": 4111.38979529952, "count": 325072, "is_parallel": true, "self": 4111.38979529952 }, "steps_from_proto": { "total": 715.1766809997105, "count": 650144, "is_parallel": true, "self": 157.391692098381, "children": { "_process_rank_one_or_two_observation": { "total": 557.7849889013295, "count": 2600576, "is_parallel": true, "self": 557.7849889013295 } } } } } } } } } } }, "trainer_advance": { "total": 3528.1974877997654, "count": 325072, "self": 69.7983735997991, "children": { "process_trajectory": { "total": 770.7547103999628, "count": 325072, "self": 764.2168591999585, "children": { "RLTrainer._checkpoint": { "total": 6.537851200004297, "count": 10, "self": 6.537851200004297 } } }, "_update_policy": { "total": 2687.6444038000036, "count": 233, "self": 1091.2508814999412, "children": { "TorchPOCAOptimizer.update": { "total": 1596.3935223000624, "count": 6990, "self": 1596.3935223000624 } } } } } } }, "trainer_threads": { "total": 1.0000003385357559e-06, "count": 1, "self": 1.0000003385357559e-06 }, "TrainerController._save_models": { "total": 0.7824361000002682, "count": 1, "self": 0.024627300001156982, "children": { "RLTrainer._checkpoint": { "total": 0.7578087999991112, "count": 1, "self": 0.7578087999991112 } } } } } } }