{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.101351261138916, "min": 3.054426670074463, "max": 3.295708417892456, "count": 250 }, "SoccerTwos.Policy.Entropy.sum": { "value": 55080.0, "min": 20167.59375, "max": 150900.4375, "count": 250 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 999.0, "min": 470.3333333333333, "max": 999.0, "count": 250 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19980.0, "min": 16040.0, "max": 31968.0, "count": 250 }, "SoccerTwos.Step.mean": { "value": 2509756.0, "min": 9000.0, "max": 2509756.0, "count": 251 }, "SoccerTwos.Step.sum": { "value": 2509756.0, "min": 9000.0, "max": 2509756.0, "count": 251 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 9.941160533344373e-05, "min": -0.01774565503001213, "max": 0.10760049521923065, "count": 251 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.0009941160678863525, "min": -0.23319688439369202, "max": 1.722970962524414, "count": 251 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.00017016730271279812, "min": -0.017709609121084213, "max": 0.10757717490196228, "count": 251 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.0017016730271279812, "min": -0.21772049367427826, "max": 1.6970899105072021, "count": 251 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 251 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 251 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.0, "min": -0.4666666666666667, "max": 0.29162856936454773, "count": 251 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.0, "min": -7.0, "max": 4.082799971103668, "count": 251 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0, "min": -0.4666666666666667, "max": 0.29162856936454773, "count": 251 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.0, "min": -7.0, "max": 4.082799971103668, "count": 251 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 251 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 251 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.021670383154802644, "min": 0.01110799467326918, "max": 0.022893946474262825, "count": 116 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.021670383154802644, "min": 0.01110799467326918, "max": 0.022893946474262825, "count": 116 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 4.298182193451794e-06, "min": 6.954269515802025e-08, "max": 0.0046996509113038576, "count": 116 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 4.298182193451794e-06, "min": 6.954269515802025e-08, "max": 0.0046996509113038576, "count": 116 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 4.265978623152477e-06, "min": 8.857286554568115e-08, "max": 0.004718441826601823, "count": 116 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 4.265978623152477e-06, "min": 8.857286554568115e-08, "max": 0.004718441826601823, "count": 116 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 116 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 116 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999993, "max": 0.20000000000000007, "count": 116 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999993, "max": 0.20000000000000007, "count": 116 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 116 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 116 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1179.9717510387964, "min": 1176.6649807854974, "max": 1200.4971269630323, "count": 127 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2359.9435020775927, "min": 2353.329961570995, "max": 16800.0, "count": 127 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1726771424", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/loboronan/miniconda3/envs/unityrl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1726777445" }, "total": 6021.641882481, "count": 1, "self": 0.04719205899982626, "children": { "run_training.setup": { "total": 0.012762701000156085, "count": 1, "self": 0.012762701000156085 }, "TrainerController.start_learning": { "total": 6021.581927720999, "count": 1, "self": 3.5443163798727255, "children": { "TrainerController._reset_env": { "total": 3.5546105259995784, "count": 13, "self": 3.5546105259995784 }, "TrainerController.advance": { "total": 6014.262929808127, "count": 163635, "self": 4.22816758198951, "children": { "env_step": { "total": 4987.2101655220795, "count": 163635, "self": 3139.435143158827, "children": { "SubprocessEnvManager._take_step": { "total": 1845.3918190261047, "count": 163635, "self": 23.4835447971368, "children": { "TorchPolicy.evaluate": { "total": 1821.908274228968, "count": 325022, "self": 1821.908274228968 } } }, "workers": { "total": 2.3832033371477337, "count": 163634, "self": 0.0, "children": { "worker_root": { "total": 6012.734764201937, "count": 163634, "is_parallel": true, "self": 3303.017431428965, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002960332999464299, "count": 2, "is_parallel": true, "self": 0.0011569969988158846, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018033360006484145, "count": 8, "is_parallel": true, "self": 0.0018033360006484145 } } }, "UnityEnvironment.step": { "total": 0.027680839999902673, "count": 1, "is_parallel": true, "self": 0.0004136850002396386, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00039316999982474954, "count": 1, "is_parallel": true, "self": 0.00039316999982474954 }, "communicator.exchange": { "total": 0.025436268000248674, "count": 1, "is_parallel": true, "self": 0.025436268000248674 }, "steps_from_proto": { "total": 0.001437716999589611, "count": 2, "is_parallel": true, "self": 0.0003472859993962629, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010904310001933482, "count": 8, "is_parallel": true, "self": 0.0010904310001933482 } } } } } } }, "UnityEnvironment.step": { "total": 2709.699229369971, "count": 163633, "is_parallel": true, "self": 76.63292334552898, "children": { "UnityEnvironment._generate_step_input": { "total": 56.14572497215113, "count": 163633, "is_parallel": true, "self": 56.14572497215113 }, "communicator.exchange": { "total": 2316.4550215803497, "count": 163633, "is_parallel": true, "self": 2316.4550215803497 }, "steps_from_proto": { "total": 260.4655594719411, "count": 327266, "is_parallel": true, "self": 58.7047048213708, "children": { "_process_rank_one_or_two_observation": { "total": 201.7608546505703, "count": 1309064, "is_parallel": true, "self": 201.7608546505703 } } } } }, "steps_from_proto": { "total": 0.018103403000623075, "count": 24, "is_parallel": true, "self": 0.004023700000743702, "children": { "_process_rank_one_or_two_observation": { "total": 0.014079702999879373, "count": 96, "is_parallel": true, "self": 0.014079702999879373 } } } } } } } } }, "trainer_advance": { "total": 1022.8245967040584, "count": 163634, "self": 28.723119664031856, "children": { "process_trajectory": { "total": 397.0067258050244, "count": 163634, "self": 395.9022162810252, "children": { "RLTrainer._checkpoint": { "total": 1.1045095239992406, "count": 5, "self": 1.1045095239992406 } } }, "_update_policy": { "total": 597.0947512350021, "count": 116, "self": 242.8269063930552, "children": { "TorchPOCAOptimizer.update": { "total": 354.26784484194695, "count": 3495, "self": 354.26784484194695 } } } } } } }, "trainer_threads": { "total": 8.540000635548495e-07, "count": 1, "self": 8.540000635548495e-07 }, "TrainerController._save_models": { "total": 0.2200701530000515, "count": 1, "self": 0.002833712000210653, "children": { "RLTrainer._checkpoint": { "total": 0.21723644099984085, "count": 1, "self": 0.21723644099984085 } } } } } } }