Adapting Behaviour via Intrinsic Reward: A Survey and Empirical Study

Understand

Learning about many things can provide numerous benefits to a reinforcement learning system.

• For example, learning many auxiliary value functions, in addition to optimizing the environmental reward, appears to improve both exploration and representation learning.
• The question we tackle in this paper is how to sculpt the stream of experience---how to adapt the learning system's behavior---to optimize the learning of a collection of value functions.
• A simple answer is to compute an intrinsic reward based on the statistics of each auxiliary learner, and use reinforcement learning to maximize that intrinsic reward.