{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.3761804103851318, "min": 1.2631044387817383, "max": 3.2265355587005615, "count": 4971 }, "SoccerTwos.Policy.Entropy.sum": { "value": 28316.2890625, "min": 17019.6796875, "max": 150990.5, "count": 4971 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 67.17333333333333, "min": 39.91056910569106, "max": 999.0, "count": 4971 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20152.0, "min": 3996.0, "max": 28824.0, "count": 4971 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1604.7737147595917, "min": 1199.96886069913, "max": 1640.1715364329625, "count": 4929 }, "SoccerTwos.Self-play.ELO.sum": { "value": 240716.05721393877, "min": 2399.93772139826, "max": 370623.75222788996, "count": 4929 }, "SoccerTwos.Step.mean": { "value": 49999952.0, "min": 299872.0, "max": 49999952.0, "count": 4971 }, "SoccerTwos.Step.sum": { "value": 49999952.0, "min": 299872.0, "max": 49999952.0, "count": 4971 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.0015191533602774143, "min": -0.1431598961353302, "max": 0.1542806625366211, "count": 4971 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.22635385394096375, "min": -26.77090072631836, "max": 26.600690841674805, "count": 4971 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.0005422470276243985, "min": -0.1447911113500595, "max": 0.15689249336719513, "count": 4971 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.0807948112487793, "min": -27.075939178466797, "max": 25.363061904907227, "count": 4971 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 4971 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 4971 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.014016104224544244, "min": -0.521614286516394, "max": 0.5449043531780657, "count": 4971 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -2.0883995294570923, "min": -66.97000014781952, "max": 60.846800088882446, "count": 4971 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.014016104224544244, "min": -0.521614286516394, "max": 0.5449043531780657, "count": 4971 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -2.0883995294570923, "min": -66.97000014781952, "max": 60.846800088882446, "count": 4971 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 4971 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 4971 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.014142204541713, "min": 0.009799522332226236, "max": 0.0267679325149705, "count": 2408 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.014142204541713, "min": 0.009799522332226236, "max": 0.0267679325149705, "count": 2408 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10160003652175267, "min": 2.031721411791902e-06, "max": 0.1267216054101785, "count": 2408 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10160003652175267, "min": 2.031721411791902e-06, "max": 0.1267216054101785, "count": 2408 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10274398898084959, "min": 2.15020634565614e-06, "max": 0.12920666510860127, "count": 2408 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10274398898084959, "min": 2.15020634565614e-06, "max": 0.12920666510860127, "count": 2408 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2408 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2408 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 2408 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 2408 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 2408 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 2408 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1732029339", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/unixzfh22/miniconda3/envs/mlagents/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "1.1.0", "mlagents_envs_version": "1.1.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1732151599" }, "total": 122259.551097819, "count": 1, "self": 10.011794625999755, "children": { "run_training.setup": { "total": 0.01922519999970973, "count": 1, "self": 0.01922519999970973 }, "TrainerController.start_learning": { "total": 122249.520077993, "count": 1, "self": 76.70826766763639, "children": { "TrainerController._reset_env": { "total": 8.170237198038649, "count": 250, "self": 8.170237198038649 }, "TrainerController.advance": { "total": 122164.45999892833, "count": 3425075, "self": 70.84432571071375, "children": { "env_step": { "total": 94213.21812950721, "count": 3425075, "self": 64615.71328118044, "children": { "SubprocessEnvManager._take_step": { "total": 29553.616612041806, "count": 3425075, "self": 434.5647605536615, "children": { "TorchPolicy.evaluate": { "total": 29119.051851488144, "count": 6243720, "self": 29119.051851488144 } } }, "workers": { "total": 43.888236284960385, "count": 3425075, "self": 0.0, "children": { "worker_root": { "total": 122067.26906153935, "count": 3425075, "is_parallel": true, "self": 65761.7854423774, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0026282000003448047, "count": 2, "is_parallel": true, "self": 0.0008011000008991687, "children": { "_process_rank_one_or_two_observation": { "total": 0.001827099999445636, "count": 8, "is_parallel": true, "self": 0.001827099999445636 } } }, "UnityEnvironment.step": { "total": 0.03541209900004105, "count": 1, "is_parallel": true, "self": 0.0005117000000609551, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047289999974964303, "count": 1, "is_parallel": true, "self": 0.00047289999974964303 }, "communicator.exchange": { "total": 0.032579198999883374, "count": 1, "is_parallel": true, "self": 0.032579198999883374 }, "steps_from_proto": { "total": 0.0018483000003470806, "count": 2, "is_parallel": true, "self": 0.000439399999777379, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014089000005697017, "count": 8, "is_parallel": true, "self": 0.0014089000005697017 } } } } } } }, "steps_from_proto": { "total": 0.41644879781279087, "count": 498, "is_parallel": true, "self": 0.09592689975033863, "children": { "_process_rank_one_or_two_observation": { "total": 0.32052189806245224, "count": 1992, "is_parallel": true, "self": 0.32052189806245224 } } }, "UnityEnvironment.step": { "total": 56305.06717036414, "count": 3425074, "is_parallel": true, "self": 1660.8235693412207, "children": { "UnityEnvironment._generate_step_input": { "total": 1252.8835098944314, "count": 3425074, "is_parallel": true, "self": 1252.8835098944314 }, "communicator.exchange": { "total": 47754.147135892345, "count": 3425074, "is_parallel": true, "self": 47754.147135892345 }, "steps_from_proto": { "total": 5637.212955236141, "count": 6850148, "is_parallel": true, "self": 1295.617839018828, "children": { "_process_rank_one_or_two_observation": { "total": 4341.595116217313, "count": 27400592, "is_parallel": true, "self": 4341.595116217313 } } } } } } } } } } }, "trainer_advance": { "total": 27880.397543710413, "count": 3425075, "self": 512.855235648105, "children": { "process_trajectory": { "total": 14236.222138614488, "count": 3425075, "self": 14218.347538145466, "children": { "RLTrainer._checkpoint": { "total": 17.87460046902197, "count": 100, "self": 17.87460046902197 } } }, "_update_policy": { "total": 13131.32016944782, "count": 2408, "self": 5745.6498621564715, "children": { "TorchPOCAOptimizer.update": { "total": 7385.670307291348, "count": 72246, "self": 7385.670307291348 } } } } } } }, "trainer_threads": { "total": 8.999923011288047e-07, "count": 1, "self": 8.999923011288047e-07 }, "TrainerController._save_models": { "total": 0.18157329900714103, "count": 1, "self": 0.0015121000178623945, "children": { "RLTrainer._checkpoint": { "total": 0.18006119898927864, "count": 1, "self": 0.18006119898927864 } } } } } } }