An action-selection strategy insensitive to parameter-settings in reinforcement learning

Markov decision processes are one of the most popular frameworks for reinforcement learning. The entropy of probability density functions of Markov decision processes is referred to as the stochastic complexity. The stochastic complexity is helpful for tuning the parameters of an action-selection strategy to alleviate the exploration-exploitation dilemma. In this paper, we improve an action-selection strategy to make it insensitive to parameter-settings by using the stochastic complexity. This gives better policies for alleviating the above dilemma in most parameter-settings.