Reducing the estimation bias and variance in reinforcement learning via Maxmean and Aitken value iteration
Fanghui Huang, Wenqi Han, Xiang Li, Xinyang Deng, Wen Jiang
Topics & Concepts
Computer scienceVariance (accounting)Convergence (economics)Reinforcement learningValue (mathematics)AlgorithmRate of convergenceEstimationMathematical optimizationVariance reductionArtificial intelligenceStability (learning theory)Estimation theoryIterative methodExpected valueReinforcement Learning in RoboticsAdaptive Dynamic Programming ControlTraffic control and management