A novel policy based on action confidence limit to improve exploration efficiency in reinforcement learning
Fanghui Huang, Xinyang Deng, Yixin He, Wen Jiang
Topics & Concepts
Reinforcement learningComputer scienceConvergence (economics)Artificial intelligenceLimit (mathematics)Action (physics)Q-learningMachine learningValue (mathematics)Markov decision processValue networkMathematical optimizationMathematicsMarkov processStatisticsEconomicsMarketingQuantum mechanicsBusiness modelBusinessMathematical analysisPhysicsEconomic growthReinforcement Learning in RoboticsData Stream Mining TechniquesSmart Grid Energy Management