{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.8989752531051636, "min": 1.874920129776001, "max": 3.295649528503418, "count": 503 }, "SoccerTwos.Policy.Entropy.sum": { "value": 36703.39453125, "min": 23047.001953125, "max": 149144.125, "count": 503 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 60.7037037037037, "min": 45.76851851851852, "max": 999.0, "count": 503 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19668.0, "min": 12040.0, "max": 29340.0, "count": 503 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1535.159289799666, "min": 1193.3844646799969, "max": 1576.6173982585622, "count": 498 }, "SoccerTwos.Self-play.ELO.sum": { "value": 248695.8049475459, "min": 2391.885550734001, "max": 338869.84806884336, "count": 498 }, "SoccerTwos.Step.mean": { "value": 5029966.0, "min": 9686.0, "max": 5029966.0, "count": 503 }, "SoccerTwos.Step.sum": { "value": 5029966.0, "min": 9686.0, "max": 5029966.0, "count": 503 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.05807129666209221, "min": -0.0826704278588295, "max": 0.16211707890033722, "count": 503 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -9.349478721618652, "min": -14.384654998779297, "max": 31.450714111328125, "count": 503 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.05922158807516098, "min": -0.07887663692235947, "max": 0.16130302846431732, "count": 503 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -9.534675598144531, "min": -13.72453498840332, "max": 31.292787551879883, "count": 503 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 503 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 503 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.2695354034441598, "min": -0.5384615384615384, "max": 0.44134400367736815, "count": 503 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -43.395199954509735, "min": -52.89300036430359, "max": 73.22740012407303, "count": 503 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.2695354034441598, "min": -0.5384615384615384, "max": 0.44134400367736815, "count": 503 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -43.395199954509735, "min": -52.89300036430359, "max": 73.22740012407303, "count": 503 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 503 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 503 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.014789016257661084, "min": 0.011286390731887272, "max": 0.023933018437431505, "count": 242 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.014789016257661084, "min": 0.011286390731887272, "max": 0.023933018437431505, "count": 242 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10319915811220805, "min": 4.78353564782689e-05, "max": 0.11067347327868143, "count": 242 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10319915811220805, "min": 4.78353564782689e-05, "max": 0.11067347327868143, "count": 242 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10465494121114413, "min": 4.857856535333364e-05, "max": 0.11234949777523677, "count": 242 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10465494121114413, "min": 4.857856535333364e-05, "max": 0.11234949777523677, "count": 242 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 242 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 242 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 242 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 242 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 242 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 242 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1688640495", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=SoccerTwos.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": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1688651519" }, "total": 11024.467642585001, "count": 1, "self": 0.429065709000497, "children": { "run_training.setup": { "total": 0.0402406199999632, "count": 1, "self": 0.0402406199999632 }, "TrainerController.start_learning": { "total": 11023.998336256001, "count": 1, "self": 7.7194901102848235, "children": { "TrainerController._reset_env": { "total": 5.000056976002384, "count": 26, "self": 5.000056976002384 }, "TrainerController.advance": { "total": 11011.274762366715, "count": 343453, "self": 8.134539232027237, "children": { "env_step": { "total": 8407.070216991939, "count": 343453, "self": 6689.892364141599, "children": { "SubprocessEnvManager._take_step": { "total": 1712.5903909562267, "count": 343453, "self": 52.48040861892514, "children": { "TorchPolicy.evaluate": { "total": 1660.1099823373015, "count": 634724, "self": 1660.1099823373015 } } }, "workers": { "total": 4.587461894113403, "count": 343452, "self": 0.0, "children": { "worker_root": { "total": 11004.388166637087, "count": 343452, "is_parallel": true, "self": 5317.457861080138, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006125395000026401, "count": 2, "is_parallel": true, "self": 0.0038241940001171315, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023012009999092697, "count": 8, "is_parallel": true, "self": 0.0023012009999092697 } } }, "UnityEnvironment.step": { "total": 0.0403233069999942, "count": 1, "is_parallel": true, "self": 0.001106886000002305, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0009362990000454374, "count": 1, "is_parallel": true, "self": 0.0009362990000454374 }, "communicator.exchange": { "total": 0.034861199000033594, "count": 1, "is_parallel": true, "self": 0.034861199000033594 }, "steps_from_proto": { "total": 0.0034189229999128656, "count": 2, "is_parallel": true, "self": 0.0006124419999196107, "children": { "_process_rank_one_or_two_observation": { "total": 0.002806480999993255, "count": 8, "is_parallel": true, "self": 0.002806480999993255 } } } } } } }, "UnityEnvironment.step": { "total": 5686.8759192669495, "count": 343451, "is_parallel": true, "self": 348.9488778605137, "children": { "UnityEnvironment._generate_step_input": { "total": 217.02216981993251, "count": 343451, "is_parallel": true, "self": 217.02216981993251 }, "communicator.exchange": { "total": 4029.27468528195, "count": 343451, "is_parallel": true, "self": 4029.27468528195 }, "steps_from_proto": { "total": 1091.6301863045542, "count": 686902, "is_parallel": true, "self": 183.29490319546403, "children": { "_process_rank_one_or_two_observation": { "total": 908.3352831090901, "count": 2747608, "is_parallel": true, "self": 908.3352831090901 } } } } }, "steps_from_proto": { "total": 0.054386289999797555, "count": 50, "is_parallel": true, "self": 0.009579804985264673, "children": { "_process_rank_one_or_two_observation": { "total": 0.04480648501453288, "count": 200, "is_parallel": true, "self": 0.04480648501453288 } } } } } } } } }, "trainer_advance": { "total": 2596.070006142748, "count": 343452, "self": 64.25883360140915, "children": { "process_trajectory": { "total": 946.7535668233348, "count": 343452, "self": 943.8542154893336, "children": { "RLTrainer._checkpoint": { "total": 2.899351334001267, "count": 10, "self": 2.899351334001267 } } }, "_update_policy": { "total": 1585.0576057180037, "count": 242, "self": 1003.065424554992, "children": { "TorchPOCAOptimizer.update": { "total": 581.9921811630118, "count": 7260, "self": 581.9921811630118 } } } } } } }, "trainer_threads": { "total": 1.1899992387043312e-06, "count": 1, "self": 1.1899992387043312e-06 }, "TrainerController._save_models": { "total": 0.004025612999612349, "count": 1, "self": 4.299700049159583e-05, "children": { "RLTrainer._checkpoint": { "total": 0.003982615999120753, "count": 1, "self": 0.003982615999120753 } } } } } } }