Timezone: »

Interactive Learning from Policy-Dependent Human Feedback
James MacGlashan · Mark Ho · Robert Loftin · Bei Peng · Guan Wang · David L Roberts · Matthew E. Taylor · Michael L. Littman

Mon Aug 07 01:30 AM -- 05:00 AM (PDT) @ Gallery #97

This paper investigates the problem of interactively learning behaviors communicated by a human teacher using positive and negative feedback. Much previous work on this problem has made the assumption that people provide feedback for decisions that is dependent on the behavior they are teaching and is independent from the learner's current policy. We present empirical results that show this assumption to be false---whether human trainers give a positive or negative feedback for a decision is influenced by the learner's current policy. Based on this insight, we introduce Convergent Actor-Critic by Humans (COACH), an algorithm for learning from policy-dependent feedback that converges to a local optimum. Finally, we demonstrate that COACH can successfully learn multiple behaviors on a physical robot.

Author Information

James MacGlashan (Cogitai)
Mark Ho (Brown University)
Robert Loftin (North Carolina State University)
Bei Peng (Washington State University)
Guan Wang (Brown University)
David L Roberts (North Carolina State University)
Matthew E. Taylor (Washington State University)
Michael L. Littman (Brown University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors