\dm_csml_event_details UCL ELLIS

Combining state abstraction and temporal abstraction in MDP solving


Speaker

Kamil Ciosek

Affiliation

UCL, Computer Science

Date

Friday, 16 January 2015

Time

13:00-14:00

Location

Zoom

Link

Roberts G08 (Sir David Davies lecture theatre)

Event series

Jump Trading/ELLIS CSML Seminar Series

Abstract

The talk presents a way of solving Markov Decision Processes that
combines state abstraction and temporal abstraction. Specifically, we
combine state aggregation with the options framework and demonstrate
that they work well together and indeed it is only after one combines
the two that the full benefit of each is realized. We introduce a
hierarchical value iteration algorithm where we first coarsely solve
subgoals and then use these approximate solutions to exactly solve the
MDP. This algorithm solves several problems faster than vanilla value
iteration.

About the speaker: Kamil Ciosek (ciosek.net) is a PhD student at CSML specialising in approximate approaches to solving MDPs.

Biography