Search |  Contact |  SRI Home Do not follow this link, or your host will be blocked from this site. This is a spider trap. Do not follow this link, or your host will be blocked from this site. This is a spider trap. Do not follow this link, or your host will be blocked from this site. This is a spider trap.A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A ASRI International.  333 Ravenswood Avenue.  Menlo Park, CA 94025-3493. SRI International is a nonprofit corporation.

AIC Seminar Series

Apprenticeship Learning via Inverse Reinforcement Learning

Pieter AbbeelStanford University

Date:  2004-09-23 at 16:00

Location:  EJ291  (Directions)

   Abstract

In typical decision making and optimal control problems, the goal is to find a policy that performs well under the given dynamics and reward function. In this talk, I will first give a brief introduction on Markov Decision Processes (MDP) and then consider learning in an MDP where we are not explicitly given a reward function, but where instead we can observe an expert demonstrating the task that we want to learn to perform. This setting is useful in applications (such as the task of driving) where it may be difficult to write down an explicit reward function specifying exactly how different desiderata should be traded off. The expert can be seen as trying to maximize a reward function that is expressible as a linear combination of known features, and I will give an algorithm for learning the task demonstrated by the expert. The algorithm is based on using inverse reinforcement learning to try to recover the unknown reward function. I will show that the proposed algorithm terminates in a small number of iterations, and that even though it may never recover the expert’s reward function, the policy output by the algorithm will attain performance close to that of the expert, where here performance is measured with respect to the expert’s unknown reward function. The work I am presenting is joint work with Andrew Ng.

   Bio for Pieter Abbeel

Pieter Abbeel is a Ph.D. student in computer science at Stanford University, working with professor Andrew Ng. His research interests include reinforcement learning, machine learning and graphical models.

   Note for Visitors to SRI

Please arrive at least 10 minutes early as you will need to sign in by following instructions by the lobby phone at Building E. SRI is located at 333 Ravenswood Avenue in Menlo Park. Visitors may park in the parking lots off Fourth Street. Detailed directions to SRI, as well as maps, are available from the Visiting AIC web page. There are two entrances to SRI International located on Ravenswood Ave. Please check the Builing E entrance signage.

SRI International
©2014 SRI International 333 Ravenswood Avenue, Menlo Park, CA 94025-3493
SRI International is an independent, nonprofit corporation. Privacy policy