A Novel approach in Fuzzy Reinforcement Learning

In this paper، we present a novel continuous reinforcement learning approach. The proposed approach، called «Fuzzy Least Squares Policy Iteration (FLSPI)»، is obtained from combination of «Least Squares Policy Iteration (LSPI)» and a zero order Takagi Sugeno fuzzy system. We define state-action basis function based on fuzzy system so that LSPI conditions are satisfied. It is proven that there is an error bound for difference of the exact state-action value function and approximated state-action value function obtained by FLSPI. Simulation results show that learning speed and operation quality for FLSPI are higher than two previous critic-only fuzzy reinforcement learning approaches i. e. fuzzy Q-learning and fuzzy Sarsa learning. Another advantage of this approach is needlessness to learning rate determination.