{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.4397377967834473, "min": 2.3143255710601807, "max": 3.2371737957000732, "count": 1000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 48794.7578125, "min": 5251.326171875, "max": 117436.7109375, "count": 1000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 73.43283582089552, "min": 46.91919191919192, "max": 999.0, "count": 1000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19680.0, "min": 7992.0, "max": 31780.0, "count": 1000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1531.167342426032, "min": 1207.752528171942, "max": 1574.1534336682091, "count": 962 }, "SoccerTwos.Self-play.ELO.sum": { "value": 205176.4238850883, "min": 2415.505056343884, "max": 307319.6599696821, "count": 962 }, "SoccerTwos.Step.mean": { "value": 10499974.0, "min": 499734.0, "max": 10499974.0, "count": 1001 }, "SoccerTwos.Step.sum": { "value": 10499974.0, "min": 499734.0, "max": 10499974.0, "count": 1001 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.05285456031560898, "min": -0.15564526617527008, "max": 0.13551953434944153, "count": 1001 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -7.1353654861450195, "min": -24.747596740722656, "max": 20.919309616088867, "count": 1001 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.05140404403209686, "min": -0.15863391757011414, "max": 0.14230753481388092, "count": 1001 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -6.93954610824585, "min": -25.222793579101562, "max": 22.070335388183594, "count": 1001 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1001 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1001 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.12560740576850044, "min": -0.540971428155899, "max": 0.401263155435261, "count": 1001 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -16.95699977874756, "min": -50.82279992103577, "max": 65.16880011558533, "count": 1001 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.12560740576850044, "min": -0.540971428155899, "max": 0.401263155435261, "count": 1001 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -16.95699977874756, "min": -50.82279992103577, "max": 65.16880011558533, "count": 1001 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1001 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1001 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.016887286700269517, "min": 0.011112152040974857, "max": 0.02375900255938177, "count": 482 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016887286700269517, "min": 0.011112152040974857, "max": 0.02375900255938177, "count": 482 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09483099778493245, "min": 1.0459893114026878e-06, "max": 0.12906097347537676, "count": 482 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09483099778493245, "min": 1.0459893114026878e-06, "max": 0.12906097347537676, "count": 482 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09558213179310163, "min": 1.0327452438711285e-06, "max": 0.13083152001102766, "count": 482 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09558213179310163, "min": 1.0327452438711285e-06, "max": 0.13083152001102766, "count": 482 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 482 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 482 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.30000000000000004, "min": 0.30000000000000004, "max": 0.30000000000000004, "count": 482 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.30000000000000004, "min": 0.30000000000000004, "max": 0.30000000000000004, "count": 482 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.010000000000000002, "min": 0.010000000000000002, "max": 0.010000000000000002, "count": 482 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.010000000000000002, "min": 0.010000000000000002, "max": 0.010000000000000002, "count": 482 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1683839191", "python_version": "3.9.16 (main, Mar 8 2023, 10:39:24) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\alica\\anaconda3\\envs\\soccer_rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1683897272" }, "total": 58080.5491508, "count": 1, "self": 3.364133299997775, "children": { "run_training.setup": { "total": 0.15131649999999963, "count": 1, "self": 0.15131649999999963 }, "TrainerController.start_learning": { "total": 58077.033701, "count": 1, "self": 28.36459649718745, "children": { "TrainerController._reset_env": { "total": 7.703580700025107, "count": 68, "self": 7.703580700025107 }, "TrainerController.advance": { "total": 58040.60999380278, "count": 681485, "self": 30.837599103950197, "children": { "env_step": { "total": 21412.92841939736, "count": 681485, "self": 16694.588936696888, "children": { "SubprocessEnvManager._take_step": { "total": 4701.072346798175, "count": 681485, "self": 185.5707896962267, "children": { "TorchPolicy.evaluate": { "total": 4515.5015571019485, "count": 1264528, "self": 4515.5015571019485 } } }, "workers": { "total": 17.26713590229859, "count": 681484, "self": 0.0, "children": { "worker_root": { "total": 58032.03187709827, "count": 681484, "is_parallel": true, "self": 44532.123092398644, "children": { "steps_from_proto": { "total": 0.25089240001161706, "count": 136, "is_parallel": true, "self": 0.04736130005872319, "children": { "_process_rank_one_or_two_observation": { "total": 0.20353109995289387, "count": 544, "is_parallel": true, "self": 0.20353109995289387 } } }, "UnityEnvironment.step": { "total": 13499.65789229961, "count": 681484, "is_parallel": true, "self": 801.3268785012751, "children": { "UnityEnvironment._generate_step_input": { "total": 575.217196400056, "count": 681484, "is_parallel": true, "self": 575.217196400056 }, "communicator.exchange": { "total": 9556.806738498799, "count": 681484, "is_parallel": true, "self": 9556.806738498799 }, "steps_from_proto": { "total": 2566.307078899482, "count": 1362968, "is_parallel": true, "self": 487.2911451955056, "children": { "_process_rank_one_or_two_observation": { "total": 2079.0159337039763, "count": 5451872, "is_parallel": true, "self": 2079.0159337039763 } } } } } } } } } } }, "trainer_advance": { "total": 36596.84397530147, "count": 681484, "self": 187.30504210065556, "children": { "process_trajectory": { "total": 4954.835507400845, "count": 681484, "self": 4949.422675500855, "children": { "RLTrainer._checkpoint": { "total": 5.412831899990039, "count": 21, "self": 5.412831899990039 } } }, "_update_policy": { "total": 31454.70342579997, "count": 482, "self": 2522.0402537999544, "children": { "TorchPOCAOptimizer.update": { "total": 28932.663172000015, "count": 14472, "self": 28932.663172000015 } } } } } } }, "trainer_threads": { "total": 5.30000397702679e-06, "count": 1, "self": 5.30000397702679e-06 }, "TrainerController._save_models": { "total": 0.35552470000402536, "count": 1, "self": 0.02085079999960726, "children": { "RLTrainer._checkpoint": { "total": 0.3346739000044181, "count": 1, "self": 0.3346739000044181 } } } } } } }