An approach to the design of reinforcement functions in real world, agent-based applications

The success of any reinforcement learning (RL) application is in large part due to the design of an appropriate reinforcement Function. A methodologic al framework to support the design of reinforcement functions has not been defined yet, and this critical and often underestimated activity is left to the ability of the RL application designer, We propose an approach to supp ort reinforcement function design in RL applications concerning learning be haviors for autonomous agents. We define some dimensions along which we can describe reinforcement functions; we consider the distribution of reinforc ement values, their coherence and their matching with the designer's perspe ctive. We give hints to define measures that objectively describe the reinf orcement function; we discuss the trade-offs that should be considered to i mprove learning and we introduce the dimensions along which this improvemen t can be expected. The approach we are presenting is general enough to be a dopted in a large number of RL projects. We show how to apply it in the des ign of learning classifier systems (LCS) applications, We consider a simple , but quite complete case study in evolutionary robotics, and we discuss re inforcement function design issues in this sample context.