Transfer via soft homomorphisms

13 years 11 months ago

Download www.eecs.umich.edu

The ﬁeld of transfer learning aims to speed up learning across multiple related tasks by transferring knowledge between source and target tasks. Past work has shown that when the tasks are speciﬁed as Markov Decision Processes (MDPs), a function that maps states in the target task to similar states in the source task can be used to transfer many types of knowledge. Current approaches for autonomously learning such functions are ineﬃcient or require domain knowledge and lack theoretical guarantees of performance. We devise a novel approach that learns a stochastic mapping between tasks. Using this mapping, we present two algorithms for autonomous transfer learning – one that has strong convergence guarantees and another approximate method that learns online from experience. Extending existing work on MDP homomorphisms, we present theoretical guarantees for the quality of a transferred value function. Categories and Subject Descriptors I.2.6 [Artiﬁcial Intelligence]: Learning ...

Jonathan Sorg, Satinder Singh

Real-time Traffic