On the many dimensions of Dynamic Programming based Reinforcement Learning algorithms by Prof. Bruno Scherrer

Date

Tuesday, January 21, 2020 - 11:00 to 12:00

Location

C016, Level C, Lab 1

Description

Abstract: 

Starting from the standard Value and Policy Iteration, I shall describe many dimensions of Dynamic Programming algorithms for solving the Reinforcement Learning Problem. I will discuss their sensitivity to errors. I will also explain the connections to some of them to somewhat recent state-of-the-art algorithms.

Biography: 

Bruno Scherrer has been a researcher at INRIA since 2004. He has contributed to the mathematical analysis of Dynamic Programming algorithms applied to Reinforcement Learning, in particular to approximation schemes. 

 

 

All-OIST Category: 

Intra-Group Category


Import this Event: Right-click to download, then open in your calendar application.

Subscribe to the OIST Calendar: Right-click to download, then open in your calendar application.