{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.1886069774627686, "min": 3.178438425064087, "max": 3.295685052871704, "count": 50 }, "SoccerTwos.Policy.Entropy.sum": { "value": 121320.1171875, "min": 102424.25, "max": 183714.671875, "count": 50 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 999.0, "min": 636.4666666666667, "max": 999.0, "count": 50 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 39960.0, "min": 33220.0, "max": 46972.0, "count": 50 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1191.124540593521, "min": 1189.3849419265284, "max": 1199.131082145352, "count": 44 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2382.249081187042, "min": 2378.769883853057, "max": 19131.73953986713, "count": 44 }, "SoccerTwos.Step.mean": { "value": 999962.0, "min": 19136.0, "max": 999962.0, "count": 50 }, "SoccerTwos.Step.sum": { "value": 999962.0, "min": 19136.0, "max": 999962.0, "count": 50 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.0038646706379950047, "min": -0.10353560000658035, "max": 1.3643476449942682e-05, "count": 50 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.07729341089725494, "min": -2.3813188076019287, "max": 0.0002865130081772804, "count": 50 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.003552407491952181, "min": -0.10348793864250183, "max": -5.0115409976569936e-05, "count": 50 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.07104814797639847, "min": -2.3802225589752197, "max": -0.0010524236131459475, "count": 50 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 50 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 50 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.0, "min": -0.31369599997997283, "max": 0.06665454669432207, "count": 50 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.0, "min": -7.842399999499321, "max": 1.4664000272750854, "count": 50 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0, "min": -0.31369599997997283, "max": 0.06665454669432207, "count": 50 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.0, "min": -7.842399999499321, "max": 1.4664000272750854, "count": 50 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.015696508710971103, "min": 0.012041132871915276, "max": 0.02400295213640978, "count": 46 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015696508710971103, "min": 0.012041132871915276, "max": 0.02400295213640978, "count": 46 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 2.8739912431774427e-05, "min": 8.319434111096295e-07, "max": 0.004023755287441115, "count": 46 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 2.8739912431774427e-05, "min": 8.319434111096295e-07, "max": 0.004023755287441115, "count": 46 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 2.3349601330361718e-05, "min": 8.891787956599729e-07, "max": 0.00416152966208756, "count": 46 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 2.3349601330361718e-05, "min": 8.891787956599729e-07, "max": 0.00416152966208756, "count": 46 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 46 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 46 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 46 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 46 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 46 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 46 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1742495369", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /kaggle/working/ml-agents/config/poca/SoccerTwos.yaml --force --env=/kaggle/working/ml-agents/trained-envs-executables/SoccerTwos/SoccerTwos --run-id=SoccerTwos --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1742497321" }, "total": 1951.4146932200001, "count": 1, "self": 0.37536009699988426, "children": { "run_training.setup": { "total": 0.082134858000245, "count": 1, "self": 0.082134858000245 }, "TrainerController.start_learning": { "total": 1950.957198265, "count": 1, "self": 1.4400027930096257, "children": { "TrainerController._reset_env": { "total": 2.600465807999626, "count": 5, "self": 2.600465807999626 }, "TrainerController.advance": { "total": 1946.71187608099, "count": 65062, "self": 1.4846765249099008, "children": { "env_step": { "total": 1591.0226108401089, "count": 65062, "self": 1127.4331228931787, "children": { "SubprocessEnvManager._take_step": { "total": 462.750627608983, "count": 65062, "self": 11.019295506942854, "children": { "TorchPolicy.evaluate": { "total": 451.73133210204014, "count": 129206, "self": 451.73133210204014 } } }, "workers": { "total": 0.8388603379471533, "count": 65062, "self": 0.0, "children": { "worker_root": { "total": 1947.874808758983, "count": 65062, "is_parallel": true, "self": 1012.1501368740314, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0033248380000259203, "count": 2, "is_parallel": true, "self": 0.00087625899914201, "children": { "_process_rank_one_or_two_observation": { "total": 0.0024485790008839103, "count": 8, "is_parallel": true, "self": 0.0024485790008839103 } } }, "UnityEnvironment.step": { "total": 0.029130954000265774, "count": 1, "is_parallel": true, "self": 0.0007091229999787174, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000519690000146511, "count": 1, "is_parallel": true, "self": 0.000519690000146511 }, "communicator.exchange": { "total": 0.025503791000119236, "count": 1, "is_parallel": true, "self": 0.025503791000119236 }, "steps_from_proto": { "total": 0.00239835000002131, "count": 2, "is_parallel": true, "self": 0.0007142930007830728, "children": { "_process_rank_one_or_two_observation": { "total": 0.001684056999238237, "count": 8, "is_parallel": true, "self": 0.001684056999238237 } } } } } } }, "UnityEnvironment.step": { "total": 935.7151354649518, "count": 65061, "is_parallel": true, "self": 51.54217589294831, "children": { "UnityEnvironment._generate_step_input": { "total": 34.732810173004054, "count": 65061, "is_parallel": true, "self": 34.732810173004054 }, "communicator.exchange": { "total": 686.4437392320046, "count": 65061, "is_parallel": true, "self": 686.4437392320046 }, "steps_from_proto": { "total": 162.9964101669948, "count": 130122, "is_parallel": true, "self": 30.736860347916718, "children": { "_process_rank_one_or_two_observation": { "total": 132.25954981907807, "count": 520488, "is_parallel": true, "self": 132.25954981907807 } } } } }, "steps_from_proto": { "total": 0.009536419999676582, "count": 8, "is_parallel": true, "self": 0.0020366909998301708, "children": { "_process_rank_one_or_two_observation": { "total": 0.007499728999846411, "count": 32, "is_parallel": true, "self": 0.007499728999846411 } } } } } } } } }, "trainer_advance": { "total": 354.2045887159711, "count": 65062, "self": 13.669555828984358, "children": { "process_trajectory": { "total": 97.64962769798558, "count": 65062, "self": 97.12873395398537, "children": { "RLTrainer._checkpoint": { "total": 0.5208937440002046, "count": 2, "self": 0.5208937440002046 } } }, "_update_policy": { "total": 242.88540518900118, "count": 46, "self": 139.40624516000253, "children": { "TorchPOCAOptimizer.update": { "total": 103.47916002899865, "count": 1392, "self": 103.47916002899865 } } } } } } }, "trainer_threads": { "total": 9.890000001178123e-07, "count": 1, "self": 9.890000001178123e-07 }, "TrainerController._save_models": { "total": 0.20485259400084033, "count": 1, "self": 0.0018460620012774598, "children": { "RLTrainer._checkpoint": { "total": 0.20300653199956287, "count": 1, "self": 0.20300653199956287 } } } } } } }