{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.9901013374328613, "min": 1.9389210939407349, "max": 3.2957334518432617, "count": 512 }, "SoccerTwos.Policy.Entropy.sum": { "value": 40438.859375, "min": 1898.342529296875, "max": 143398.8125, "count": 512 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 60.358024691358025, "min": 38.79365079365079, "max": 999.0, "count": 512 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19556.0, "min": 11496.0, "max": 28844.0, "count": 512 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1505.1244383951398, "min": 1195.1051539247644, "max": 1515.297245016601, "count": 467 }, "SoccerTwos.Self-play.ELO.sum": { "value": 243830.15902001265, "min": 2390.22845904052, "max": 371883.4278380729, "count": 467 }, "SoccerTwos.Step.mean": { "value": 5119929.0, "min": 9438.0, "max": 5119929.0, "count": 512 }, "SoccerTwos.Step.sum": { "value": 5119929.0, "min": 9438.0, "max": 5119929.0, "count": 512 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.002556137042120099, "min": -0.06864777952432632, "max": 0.14418616890907288, "count": 512 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.4140942096710205, "min": -12.425248146057129, "max": 28.500564575195312, "count": 512 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.00506508257240057, "min": -0.07395259290933609, "max": 0.14162971079349518, "count": 512 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.8205434083938599, "min": -13.713332176208496, "max": 29.499614715576172, "count": 512 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 512 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 512 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.17042716086646656, "min": -0.5333333333333333, "max": 0.37111020939690725, "count": 512 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -27.609200060367584, "min": -39.58359980583191, "max": 56.42540001869202, "count": 512 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.17042716086646656, "min": -0.5333333333333333, "max": 0.37111020939690725, "count": 512 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -27.609200060367584, "min": -39.58359980583191, "max": 56.42540001869202, "count": 512 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 512 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 512 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.013607775752461748, "min": 0.01118276805179145, "max": 0.023236331374694903, "count": 243 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.013607775752461748, "min": 0.01118276805179145, "max": 0.023236331374694903, "count": 243 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09963228876392047, "min": 5.018286249954447e-06, "max": 0.11590451747179031, "count": 243 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09963228876392047, "min": 5.018286249954447e-06, "max": 0.11590451747179031, "count": 243 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10242885425686836, "min": 5.467982835701453e-06, "max": 0.12060089310010275, "count": 243 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10242885425686836, "min": 5.467982835701453e-06, "max": 0.12060089310010275, "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": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 243 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 243 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 243 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 243 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1682198946", "python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]", "command_line_arguments": "/projectnb/noc-lab/aam/.conda/envs/rlcourse/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --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": "1682205606" }, "total": 6659.368711032905, "count": 1, "self": 0.11105239437893033, "children": { "run_training.setup": { "total": 0.03794227633625269, "count": 1, "self": 0.03794227633625269 }, "TrainerController.start_learning": { "total": 6659.2197163621895, "count": 1, "self": 5.339789303950965, "children": { "TrainerController._reset_env": { "total": 9.762862376403064, "count": 26, "self": 9.762862376403064 }, "TrainerController.advance": { "total": 6643.906816115137, "count": 344204, "self": 5.373692670837045, "children": { "env_step": { "total": 5037.232137721032, "count": 344204, "self": 3475.0303481281735, "children": { "SubprocessEnvManager._take_step": { "total": 1558.9712875639088, "count": 344204, "self": 35.936600633431226, "children": { "TorchPolicy.evaluate": { "total": 1523.0346869304776, "count": 651042, "self": 1523.0346869304776 } } }, "workers": { "total": 3.2305020289495587, "count": 344204, "self": 0.0, "children": { "worker_root": { "total": 6649.40442152461, "count": 344204, "is_parallel": true, "self": 3784.3061906751245, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020577101968228817, "count": 2, "is_parallel": true, "self": 0.0005376017652451992, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015201084315776825, "count": 8, "is_parallel": true, "self": 0.0015201084315776825 } } }, "UnityEnvironment.step": { "total": 0.019348828122019768, "count": 1, "is_parallel": true, "self": 0.0005003991536796093, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00037489132955670357, "count": 1, "is_parallel": true, "self": 0.00037489132955670357 }, "communicator.exchange": { "total": 0.017110953573137522, "count": 1, "is_parallel": true, "self": 0.017110953573137522 }, "steps_from_proto": { "total": 0.0013625840656459332, "count": 2, "is_parallel": true, "self": 0.0002985917963087559, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010639922693371773, "count": 8, "is_parallel": true, "self": 0.0010639922693371773 } } } } } } }, "UnityEnvironment.step": { "total": 2865.0657724705525, "count": 344203, "is_parallel": true, "self": 154.13542782748118, "children": { "UnityEnvironment._generate_step_input": { "total": 101.80259552272037, "count": 344203, "is_parallel": true, "self": 101.80259552272037 }, "communicator.exchange": { "total": 2206.215404335875, "count": 344203, "is_parallel": true, "self": 2206.215404335875 }, "steps_from_proto": { "total": 402.91234478447586, "count": 688406, "is_parallel": true, "self": 78.39272690284997, "children": { "_process_rank_one_or_two_observation": { "total": 324.5196178816259, "count": 2753624, "is_parallel": true, "self": 324.5196178816259 } } } } }, "steps_from_proto": { "total": 0.03245837893337011, "count": 50, "is_parallel": true, "self": 0.006525270640850067, "children": { "_process_rank_one_or_two_observation": { "total": 0.025933108292520046, "count": 200, "is_parallel": true, "self": 0.025933108292520046 } } } } } } } } }, "trainer_advance": { "total": 1601.3009857232682, "count": 344204, "self": 41.19085905421525, "children": { "process_trajectory": { "total": 602.666278748773, "count": 344204, "self": 600.2676379620098, "children": { "RLTrainer._checkpoint": { "total": 2.3986407867632806, "count": 10, "self": 2.3986407867632806 } } }, "_update_policy": { "total": 957.44384792028, "count": 244, "self": 611.1208848957904, "children": { "TorchPOCAOptimizer.update": { "total": 346.3229630244896, "count": 7305, "self": 346.3229630244896 } } } } } } }, "trainer_threads": { "total": 8.177012205123901e-07, "count": 1, "self": 8.177012205123901e-07 }, "TrainerController._save_models": { "total": 0.21024774899706244, "count": 1, "self": 0.0035399501211941242, "children": { "RLTrainer._checkpoint": { "total": 0.20670779887586832, "count": 1, "self": 0.20670779887586832 } } } } } } }