{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.6160085201263428, "min": 2.5309042930603027, "max": 3.2958028316497803, "count": 1200 }, "SoccerTwos.Policy.Entropy.sum": { "value": 28127.32421875, "min": 1142.884033203125, "max": 103250.796875, "count": 1200 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 140.41176470588235, "min": 71.33333333333333, "max": 999.0, "count": 1200 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 9548.0, "min": 3996.0, "max": 15984.0, "count": 1200 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1293.0965716918265, "min": 1181.2921910083294, "max": 1299.4242601266078, "count": 924 }, "SoccerTwos.Self-play.ELO.sum": { "value": 43965.2834375221, "min": 2365.186011911509, "max": 85501.7490598387, "count": 924 }, "SoccerTwos.Step.mean": { "value": 5999994.0, "min": 4064.0, "max": 5999994.0, "count": 1200 }, "SoccerTwos.Step.sum": { "value": 5999994.0, "min": 4064.0, "max": 5999994.0, "count": 1200 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.0478287935256958, "min": -0.07056863605976105, "max": 0.0990050733089447, "count": 1200 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 1.5783501863479614, "min": -3.28068470954895, "max": 3.465177536010742, "count": 1200 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.047932833433151245, "min": -0.07096714526414871, "max": 0.10634422302246094, "count": 1200 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 1.5817835330963135, "min": -3.3354556560516357, "max": 3.722047805786133, "count": 1200 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1200 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1200 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.3155103104584145, "min": -0.6666666766007742, "max": 0.5640228674525306, "count": 1200 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 10.411840245127678, "min": -20.109760403633118, "max": 13.496320486068726, "count": 1200 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.3943878809611003, "min": -0.8333333333333334, "max": 0.7050285736719767, "count": 1200 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 13.014800071716309, "min": -25.137200117111206, "max": 16.870399951934814, "count": 1200 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1200 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1200 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.023117861443461153, "min": 0.021430131281699797, "max": 0.02991539443033483, "count": 143 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.023117861443461153, "min": 0.021430131281699797, "max": 0.02991539443033483, "count": 143 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.018350337455049156, "min": 0.00023209207139643695, "max": 0.30159230546389776, "count": 143 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.018350337455049156, "min": 0.00023209207139643695, "max": 0.30159230546389776, "count": 143 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.01843568489421159, "min": 0.0002673177294468587, "max": 0.04010890867055689, "count": 143 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.01843568489421159, "min": 0.0002673177294468587, "max": 0.04010890867055689, "count": 143 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 2.2414328850666505e-06, "min": 2.2414328850666505e-06, "max": 0.0004963543340624668, "count": 143 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 2.2414328850666505e-06, "min": 2.2414328850666505e-06, "max": 0.0004963543340624668, "count": 143 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.1, "min": 0.1, "max": 0.1, "count": 143 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.1, "min": 0.1, "max": 0.1, "count": 143 }, "SoccerTwos.Policy.Beta.mean": { "value": 5.47818399999997e-05, "min": 5.47818399999997e-05, "max": 0.009927159579999997, "count": 143 }, "SoccerTwos.Policy.Beta.sum": { "value": 5.47818399999997e-05, "min": 5.47818399999997e-05, "max": 0.009927159579999997, "count": 143 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1697705386", "python_version": "3.10.10 | packaged by Anaconda, Inc. | (main, Mar 21 2023, 18:39:17) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\uzi\\.conda\\envs\\mlagents\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1697744881" }, "total": 39494.87471559999, "count": 1, "self": 1.6276554999640211, "children": { "run_training.setup": { "total": 0.06667810003273189, "count": 1, "self": 0.06667810003273189 }, "TrainerController.start_learning": { "total": 39493.18038199999, "count": 1, "self": 5.84308449953096, "children": { "TrainerController._reset_env": { "total": 7.211642399954144, "count": 60, "self": 7.211642399954144 }, "TrainerController.advance": { "total": 39479.90466690052, "count": 402382, "self": 6.35884719598107, "children": { "env_step": { "total": 5687.911550901015, "count": 402382, "self": 3965.454874078918, "children": { "SubprocessEnvManager._take_step": { "total": 1718.4236765305395, "count": 402382, "self": 36.77869198168628, "children": { "TorchPolicy.evaluate": { "total": 1681.6449845488532, "count": 793854, "self": 1681.6449845488532 } } }, "workers": { "total": 4.033000291557983, "count": 402382, "self": 0.0, "children": { "worker_root": { "total": 39478.93575890345, "count": 402382, "is_parallel": true, "self": 36286.98941390769, "children": { "steps_from_proto": { "total": 0.06628599960822612, "count": 120, "is_parallel": true, "self": 0.015201199566945434, "children": { "_process_rank_one_or_two_observation": { "total": 0.05108480004128069, "count": 480, "is_parallel": true, "self": 0.05108480004128069 } } }, "UnityEnvironment.step": { "total": 3191.8800589961465, "count": 402382, "is_parallel": true, "self": 126.63717696699314, "children": { "UnityEnvironment._generate_step_input": { "total": 108.40029989677714, "count": 402382, "is_parallel": true, "self": 108.40029989677714 }, "communicator.exchange": { "total": 2530.9522374179214, "count": 402382, "is_parallel": true, "self": 2530.9522374179214 }, "steps_from_proto": { "total": 425.89034471445484, "count": 804764, "is_parallel": true, "self": 92.46972756035393, "children": { "_process_rank_one_or_two_observation": { "total": 333.4206171541009, "count": 3219056, "is_parallel": true, "self": 333.4206171541009 } } } } } } } } } } }, "trainer_advance": { "total": 33785.63426880352, "count": 402382, "self": 48.6818082081154, "children": { "process_trajectory": { "total": 1255.7951576953637, "count": 402382, "self": 1253.0429551952984, "children": { "RLTrainer._checkpoint": { "total": 2.752202500065323, "count": 12, "self": 2.752202500065323 } } }, "_update_policy": { "total": 32481.157302900043, "count": 143, "self": 942.4680457977229, "children": { "TorchPOCAOptimizer.update": { "total": 31538.68925710232, "count": 28860, "self": 31538.68925710232 } } } } } } }, "trainer_threads": { "total": 8.00006091594696e-07, "count": 1, "self": 8.00006091594696e-07 }, "TrainerController._save_models": { "total": 0.22098739998182282, "count": 1, "self": 0.007894299982581288, "children": { "RLTrainer._checkpoint": { "total": 0.21309309999924153, "count": 1, "self": 0.21309309999924153 } } } } } } }