"Cultivating Desired Behaviour:
Policy Teaching Via Environment-Dynamics Tweaks"

Speaker: Zinovi Rabinovich, University of Southampton
Date: Thursday, 18 March 2010
Time: 4pm
Place: Ross 201

Abstract:

In this work we study, for the first time explicitly, the implications
of endowing an interested party (i.e. a teacher) with the ability to
modify the underlying dynamics of the environment, in order to
encourage an agent to learn to follow a specific policy. We introduce
a cost function which can be used by the teacher to balance the
modifications it makes to the underlying environment dynamics, with
the learner's performance compared to some ideal, desired, policy. We
formulate teacher's problem of determining optimal environment changes
as a planning and control problem, and empirically validate the
effectiveness of our model.

This is a joint work with Kate Larson, Lachlan Dufton and Nick Jennings.