Fictitious play based Markov game control for robotic arm manipulator
TL;DR: The work attempts a `safe yet consistent' Markov game controller which advocates a minimax policy during the startup control stages and later moves to a more enterprising policy based on stochastic fictitious play.
Abstract: Markov games can be used as a platform to deal with exogenous disturbances and parametric variations. In this work an attempt has been made to achieve a superior performance with fuzzy Markov game based control by hybridizing two game theory based approaches of ‘fictitious play’ and ‘minimax’. The work attempts a ‘safe yet consistent’ Markov game controller which advocates a minimax policy during the startup control stages and later moves to a more enterprising policy based on stochastic fictitious play. The proposed controller addresses continuous state action space problems wherein we use fuzzy inference system as a universal approximator for generalization with a proportional derivative control in the nested position tracking loop. The proposed controller is simulated on a two link robot and its performance compared against fuzzy Markov game control and fuzzy Q control. Simulation results elucidate the fact that proposed control scheme leads to an improved controller with lower tracking error and torque requirements.
Cites background from "Fictitious play based Markov game c..."
...Sharma and Gopal (2014) tried to achieve a superior performance with fuzzy Markov game-based control by hybridizing two game theory–based approaches of “fictitious play” and “minimax.”...