Learning to evaluate conditional partial plans

We study agents situated in partially observable environments, who do not have sufficient resources to create conformant plans. Instead, they generate plans which are conditional and partial, execute or simulate them, and learn to evaluate their quality from experience. Our agent employs an incomplete symbolic deduction system based on active logic and situation calculus for reasoning about actions and their consequences. An inductive logic programming algorithm generalises observations and deduced knowledge, allowing the agent to execute a good plan. We show results of using PROGOL learning algorithm to distinguish "bad" plans early in the reasoning process, before too many resources are wasted on considering them. We show that additional knowledge needs to be provided before learning can be successful, but argue that the benefits achieved make it worthwhile. Finally, we identify several assumptions made by PROGOL, shared by other similarly universal algorithms, which are well justified in general, but fail to exploit the properties of the class of problems faced by rational agents.