AI Seminar

Toyota AI Seminar: The Optimal Reward Problem

Satinder Singh BavejaProfessorUniversity of Michigan, CSE

Impressive results have been obtained by research approaches to autonomous agents that start with a given reward function and then focus on developing theory and algorithms for learning or planning policies that lead to high cumulative reward. In a departure from this work, we recognize that in many situations the starting point is an agent designer with a reward function seeking to build an autonomous agent to act on its behalf. What reward function should the designer build into the autonomous agent? In this new view, setting the parameters (agent's reward function) equal to the given preferences (designer's reward function) implements a preferences-parameters confound. If an agent is bounded, as most agents are in practice, we expect that breaking the preferences-parameters confound would be beneficial. We define the optimal reward problem, that of designing the agent's reward function given a designer's reward function, an agent architecture, and a distribution over environments. The main focus of the talk will be on a discussion of some empirical and theoretical insights obtained by solving the optimal reward problem.

** This is joint work with Jonathan Sorg and Richard Lewis at the University of Michigan.

Sponsored by