{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.8141875267028809, "min": 1.7874311208724976, "max": 3.295750141143799, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 33613.265625, "min": 26185.03515625, "max": 130983.578125, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 63.69230769230769, "min": 41.125, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19872.0, "min": 11860.0, "max": 29656.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1634.744360154731, "min": 1198.0995707076597, "max": 1642.147074983002, "count": 492 }, "SoccerTwos.Self-play.ELO.sum": { "value": 255020.12018413807, "min": 2399.9631171357605, "max": 368758.81542560615, "count": 492 }, "SoccerTwos.Step.mean": { "value": 4999948.0, "min": 9692.0, "max": 4999948.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999948.0, "min": 9692.0, "max": 4999948.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.02642429806292057, "min": -0.08815421909093857, "max": 0.2629711329936981, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 4.122190475463867, "min": -15.806486129760742, "max": 34.6436882019043, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.022039806470274925, "min": -0.08511468768119812, "max": 0.25583186745643616, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 3.4382097721099854, "min": -15.384428024291992, "max": 35.561279296875, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.02235897611349057, "min": -0.8181818181818182, "max": 0.591736844757147, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 3.488000273704529, "min": -59.77039957046509, "max": 70.58960044384003, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.02235897611349057, "min": -0.8181818181818182, "max": 0.591736844757147, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 3.488000273704529, "min": -59.77039957046509, "max": 70.58960044384003, "count": 500 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.015741291203691315, "min": 0.011714390382015457, "max": 0.02364399277139455, "count": 239 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015741291203691315, "min": 0.011714390382015457, "max": 0.02364399277139455, "count": 239 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10384118780493737, "min": 6.701165815078032e-05, "max": 0.11815073440472285, "count": 239 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10384118780493737, "min": 6.701165815078032e-05, "max": 0.11815073440472285, "count": 239 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10519942566752434, "min": 7.277867262018844e-05, "max": 0.12029852569103242, "count": 239 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10519942566752434, "min": 7.277867262018844e-05, "max": 0.12029852569103242, "count": 239 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 239 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 239 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 239 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 239 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 239 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 239 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1709517974", "python_version": "3.10.12 (main, Aug 16 2023, 20:18:15) [GCC 10.2.1 20210110]", "command_line_arguments": "/home/hf/.local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1709527562" }, "total": 9587.241177209013, "count": 1, "self": 0.5314833370503038, "children": { "run_training.setup": { "total": 0.035167681984603405, "count": 1, "self": 0.035167681984603405 }, "TrainerController.start_learning": { "total": 9586.674526189978, "count": 1, "self": 5.782015811128076, "children": { "TrainerController._reset_env": { "total": 3.1628817589371465, "count": 25, "self": 3.1628817589371465 }, "TrainerController.advance": { "total": 9577.524895150913, "count": 340347, "self": 5.872761982289376, "children": { "env_step": { "total": 5401.460176069988, "count": 340347, "self": 4707.99512681755, "children": { "SubprocessEnvManager._take_step": { "total": 689.4457047251344, "count": 340347, "self": 32.467159908497706, "children": { "TorchPolicy.evaluate": { "total": 656.9785448166367, "count": 631960, "self": 656.9785448166367 } } }, "workers": { "total": 4.019344527303474, "count": 340347, "self": 0.0, "children": { "worker_root": { "total": 9575.290859081695, "count": 340347, "is_parallel": true, "self": 5505.455079673382, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017033430049195886, "count": 2, "is_parallel": true, "self": 0.0004915839817840606, "children": { "_process_rank_one_or_two_observation": { "total": 0.001211759023135528, "count": 8, "is_parallel": true, "self": 0.001211759023135528 } } }, "UnityEnvironment.step": { "total": 0.02182876502047293, "count": 1, "is_parallel": true, "self": 0.0003339580143801868, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00024807400768622756, "count": 1, "is_parallel": true, "self": 0.00024807400768622756 }, "communicator.exchange": { "total": 0.020199930004309863, "count": 1, "is_parallel": true, "self": 0.020199930004309863 }, "steps_from_proto": { "total": 0.0010468029940966517, "count": 2, "is_parallel": true, "self": 0.0002818449283950031, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007649580657016486, "count": 8, "is_parallel": true, "self": 0.0007649580657016486 } } } } } } }, "UnityEnvironment.step": { "total": 4069.80994430423, "count": 340346, "is_parallel": true, "self": 119.39099005129538, "children": { "UnityEnvironment._generate_step_input": { "total": 77.58837799314642, "count": 340346, "is_parallel": true, "self": 77.58837799314642 }, "communicator.exchange": { "total": 3510.695543169859, "count": 340346, "is_parallel": true, "self": 3510.695543169859 }, "steps_from_proto": { "total": 362.1350330899295, "count": 680692, "is_parallel": true, "self": 81.05877564667026, "children": { "_process_rank_one_or_two_observation": { "total": 281.07625744325924, "count": 2722768, "is_parallel": true, "self": 281.07625744325924 } } } } }, "steps_from_proto": { "total": 0.02583510408294387, "count": 48, "is_parallel": true, "self": 0.0060898262017872185, "children": { "_process_rank_one_or_two_observation": { "total": 0.019745277881156653, "count": 192, "is_parallel": true, "self": 0.019745277881156653 } } } } } } } } }, "trainer_advance": { "total": 4170.191957098636, "count": 340347, "self": 45.29780760707217, "children": { "process_trajectory": { "total": 687.7706350488006, "count": 340347, "self": 686.3132269807975, "children": { "RLTrainer._checkpoint": { "total": 1.457408068003133, "count": 10, "self": 1.457408068003133 } } }, "_update_policy": { "total": 3437.123514442763, "count": 239, "self": 489.62579111676314, "children": { "TorchPOCAOptimizer.update": { "total": 2947.4977233259997, "count": 7173, "self": 2947.4977233259997 } } } } } } }, "trainer_threads": { "total": 7.079797796905041e-07, "count": 1, "self": 7.079797796905041e-07 }, "TrainerController._save_models": { "total": 0.20473276101984084, "count": 1, "self": 0.04719769299845211, "children": { "RLTrainer._checkpoint": { "total": 0.15753506802138872, "count": 1, "self": 0.15753506802138872 } } } } } } }