Structured models of decision making often assume an agent is aware of all possible states and actions in advance. This assumption is sometimes untenable. In this paper, we learn Bayesian Decision Networks from both domain exploration and expert assertions in a way which guarantees convergence to optimal behaviour, even when the agent starts unaware of actions or belief variables that are critical to success. Our experiments show that our agent learns optimal behaviour on both small and large decision problems, and that allowing an agent to conserve information upon making new discoveries results in faster convergence.
Craig Innes (University of Edinburgh)
Alex Lascarides (University of Edinburgh)
Related Events (a corresponding poster, oral, or spotlight)
2019 Oral: Learning Structured Decision Problems with Unawareness »
Thu Jun 13th 09:35 -- 09:40 AM Room Hall B