Sciweavers

Share
KCAP
2009
ACM

Interactively shaping agents via human reinforcement: the TAMER framework

9 years 10 months ago
Interactively shaping agents via human reinforcement: the TAMER framework
As computational learning agents move into domains that incur real costs (e.g., autonomous driving or financial investment), it will be necessary to learn good policies without numerous high-cost learning trials. One promising approach to reducing sample complexity of learning a task is knowledge transfer from humans to agents. Ideally, methods of transfer should be accessible to anyone with task knowledge, regardless of that person’s expertise in programming and AI. This paper focuses on allowing a human trainer to interactively shape an agent’s policy via reinforcement signals. Specifically, the paper introduces “Training an Agent Manually via Evaluative Reinforcement,” or tamer, a framework that enables such shaping. Differing from previous approaches to interactive shaping, a tamer agent models the human’s reinforcement and exploits its model by choosing actions expected to be most highly reinforced. Results from two domains demonstrate that lay users can train tamer ...
W. Bradley Knox, Peter Stone
Added 28 May 2010
Updated 28 May 2010
Type Conference
Year 2009
Where KCAP
Authors W. Bradley Knox, Peter Stone
Comments (0)
books