Journal of Advanced Computational Intelligence and Intelligent Informatics · 2009 · 34 citations · 15 references
BusinessComputer ScienceArtificial IntelligenceMarkov Decision ProcessesMemoryDecision-making ModelsExploration-exploitation TradeoffPartially Observable Markov Decision ProcessesPolicy LearningReinforcement LearningReinforcement Learning FoundationsContinual Reinforcement LearningExploitation LearningGoal-directed LearningMarkov Decision ModelsReinforcement Learning ModelsReinforcement Learning Theory
Exploitation-oriented learning (XoL) is a novel approach to goal-directed learning from interaction. Reinforcement learning is much more focused on learning and ensures optimality in Markov decision process (MDP) environments, XoL involves learning a rational policy that obtains rewards continuously and very quickly. PS-r * , a form of XoL, involves learning a useful rational policy not inferior to the random walk in the partially observed Markov decision process (POMDP) where reward types number one. PS-r * , however, requires O(MN 2 ) memory where N is the number of sensory input types and M is an action. We propose PS-r # for learning a useful rational policy in the POMDP using O(MN) memory. PS-r # effectiveness is confirmed in numerical examples.
15
Reinforcement Learning: An Introduction
Richard S. Sutton, Andy Barto · IEEE Transactions on Neural Networks · 1998 · 27.1K citations