Extending BDI plan selection to incorporate learning from experience

Abstract

An important drawback to the popular Belief, Desire, and Intentions (BDI) paradigm is that such systems include no element of learning from experience. We describe a novel BDI execution framework that models context conditions as decision trees, rather than boolean formulae, allowing agents to learn the probability of success for plans based on experience. By using a probabilistic plan selection function, the agents can balance exploration and exploitation of their plans. We extend earlier work to include both parameterised goals and recursion and modify our previous approach to decision tree confidence to include large and even non-finite domains that arise from such consideration. Our evaluation on a pre-existing program that relies heavily on recursion and parametrised goals confirms previous results that naive learning fails in some circumstances, and demonstrates that the improved approach learns relatively well.