STATE-ACTION VALUE FUNCTION MODELED BY ELM IN REINFORCEMENT LEARNING FOR HOSE CONTROL PROBLEMS
José Manuel López-Guede, Borja Lorenzo Fernández, Manuel Graña · International Journal of Uncertainty Fuzziness and Knowledge-Based Systems · 2013
This paper addresses the problem of efficiency in reinforcement learning of Single Robot Hose Transport (SRHT) by training an Extreme Learning Machine (ELM) from the state-action value Q-table, obtaining large reduction in data space requirements because the number of ELM parameters is much less than the Q-table's size. Moreover, ELM implements a continuous map which can produce compact representations of the Q-table, and generalizations to increased space resolution and unknown situations. In this paper we evaluate empirically three strategies to formulate ELM learning to provide approximations to the Q-table, namely as classification, multi-variate regression and several independent regression problems.