Accelerating Reinforcement Learning through Implicit Imitation

12 years 10 months ago
Accelerating Reinforcement Learning through Implicit Imitation
Imitation can be viewed as a means of enhancing learning in multiagent environments. It augments an agent’s ability to learn useful behaviors by making intelligent use of the knowledge implicit in behaviors demonstrated by cooperative teachers or other more experienced agents. We propose and study a formal model of implicit imitation that can accelerate reinforcement learning dramatically in certain cases. Roughly, by observing a mentor, a reinforcement-learning agent can extract information about its own capabilities in, and the relative value of, unvisited parts of the state space. We study two specific instantiations of this model, one in which the learning agent and the mentor have identical abilities, and one designed to deal with agents and mentors with different action sets. We illustrate the benefits of implicit imitation by integrating it with prioritized sweeping, and demonstrating improved performance and convergence through observation of single and multiple mentors. ...
Craig Boutilier, Bob Price
Added 19 Aug 2011
Updated 19 Aug 2011
Type Journal
Year 2011
Where CORR
Authors Craig Boutilier, Bob Price
Comments (0)