{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.2190001010894775, "min": 3.2146222591400146, "max": 3.2956621646881104, "count": 50 }, "SoccerTwos.Policy.Entropy.sum": { "value": 58714.5625, "min": 20604.1796875, "max": 105461.1015625, "count": 50 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 838.1666666666666, "min": 497.7142857142857, "max": 999.0, "count": 50 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20116.0, "min": 13936.0, "max": 26792.0, "count": 50 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1201.8369019016518, "min": 1199.9974538302758, "max": 1203.738483275568, "count": 39 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2403.6738038033036, "min": 2401.2451378393007, "max": 12020.272556829543, "count": 39 }, "SoccerTwos.Step.mean": { "value": 499256.0, "min": 9412.0, "max": 499256.0, "count": 50 }, "SoccerTwos.Step.sum": { "value": 499256.0, "min": 9412.0, "max": 499256.0, "count": 50 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.003929981496185064, "min": -0.03648779168725014, "max": 0.005335965659469366, "count": 50 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.04715977609157562, "min": -0.5837496519088745, "max": 0.05869562178850174, "count": 50 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.004715268965810537, "min": -0.03699361905455589, "max": 0.006528547499328852, "count": 50 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.0565832257270813, "min": -0.5830723643302917, "max": 0.07509464770555496, "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": 0.16076667110125223, "min": -0.36363636363636365, "max": 0.21583332618077597, "count": 50 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 1.9292000532150269, "min": -5.31879997253418, "max": 2.5899999141693115, "count": 50 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.16076667110125223, "min": -0.36363636363636365, "max": 0.21583332618077597, "count": 50 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 1.9292000532150269, "min": -5.31879997253418, "max": 2.5899999141693115, "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": 0.01742521966419493, "min": 0.010899747181489753, "max": 0.019906042632646857, "count": 23 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01742521966419493, "min": 0.010899747181489753, "max": 0.019906042632646857, "count": 23 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 4.436753109378818e-05, "min": 4.436753109378818e-05, "max": 0.004643983494800826, "count": 23 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 4.436753109378818e-05, "min": 4.436753109378818e-05, "max": 0.004643983494800826, "count": 23 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 4.6020148026097256e-05, "min": 4.6020148026097256e-05, "max": 0.004704619843202333, "count": 23 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 4.6020148026097256e-05, "min": 4.6020148026097256e-05, "max": 0.004704619843202333, "count": 23 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 23 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 23 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 23 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 23 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 23 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 23 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1723896127", "python_version": "3.10.12 (main, Jul 5 2023, 15:02:25) [Clang 14.0.6 ]", "command_line_arguments": "/opt/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos_500k --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.0", "numpy_version": "1.23.5", "end_time_seconds": "1723897671" }, "total": 1544.3516549160004, "count": 1, "self": 0.19264387400062333, "children": { "run_training.setup": { "total": 0.015303666999898269, "count": 1, "self": 0.015303666999898269 }, "TrainerController.start_learning": { "total": 1544.1437073749998, "count": 1, "self": 0.236041730991019, "children": { "TrainerController._reset_env": { "total": 3.2333996659999684, "count": 3, "self": 3.2333996659999684 }, "TrainerController.advance": { "total": 1540.5721868950081, "count": 32470, "self": 0.2287103319868038, "children": { "env_step": { "total": 1265.8492042059684, "count": 32470, "self": 1224.963268646114, "children": { "SubprocessEnvManager._take_step": { "total": 40.71615978791442, "count": 32470, "self": 1.2547693217779852, "children": { "TorchPolicy.evaluate": { "total": 39.461390466136436, "count": 64466, "self": 39.461390466136436 } } }, "workers": { "total": 0.16977577193983961, "count": 32470, "self": 0.0, "children": { "worker_root": { "total": 1541.0070235660392, "count": 32470, "is_parallel": true, "self": 359.2491389039851, "children": { "steps_from_proto": { "total": 0.004023459999189072, "count": 6, "is_parallel": true, "self": 0.0005248799998298637, "children": { "_process_rank_one_or_two_observation": { "total": 0.003498579999359208, "count": 24, "is_parallel": true, "self": 0.003498579999359208 } } }, "UnityEnvironment.step": { "total": 1181.7538612020548, "count": 32470, "is_parallel": true, "self": 2.967346219069441, "children": { "UnityEnvironment._generate_step_input": { "total": 19.23627253198265, "count": 32470, "is_parallel": true, "self": 19.23627253198265 }, "communicator.exchange": { "total": 1119.3004209030373, "count": 32470, "is_parallel": true, "self": 1119.3004209030373 }, "steps_from_proto": { "total": 40.24982154796544, "count": 64940, "is_parallel": true, "self": 4.34371712094071, "children": { "_process_rank_one_or_two_observation": { "total": 35.90610442702473, "count": 259760, "is_parallel": true, "self": 35.90610442702473 } } } } } } } } } } }, "trainer_advance": { "total": 274.494272357053, "count": 32470, "self": 2.5599262690825526, "children": { "process_trajectory": { "total": 41.454520962970946, "count": 32470, "self": 41.345124795970605, "children": { "RLTrainer._checkpoint": { "total": 0.10939616700034094, "count": 1, "self": 0.10939616700034094 } } }, "_update_policy": { "total": 230.47982512499948, "count": 23, "self": 26.765755816004457, "children": { "TorchPOCAOptimizer.update": { "total": 203.71406930899502, "count": 690, "self": 203.71406930899502 } } } } } } }, "trainer_threads": { "total": 3.7500012695090845e-07, "count": 1, "self": 3.7500012695090845e-07 }, "TrainerController._save_models": { "total": 0.10207870800059027, "count": 1, "self": 0.0008593330003350275, "children": { "RLTrainer._checkpoint": { "total": 0.10121937500025524, "count": 1, "self": 0.10121937500025524 } } } } } } }