Roy Fox, Oct 2014

From MurrayWiki
Revision as of 18:05, 29 September 2014 by Ifilippi (Talk | contribs)

Jump to: navigation, search

Roy Fox is a 4th year PhD student in the Computer Science working with Prof. Naftali Tishby on Information Theoretic methods for Reinforcement Learning. He will be visiting Caltech on 2 Oct (Thu). If you would like to meet with him, please sign up for a slot below (use your IMSS credentials to log in).

Schedule

  • 11:30 am - Richard Murray
  • 12:00 pm - Group meeting talk, 106 ANB
  • 1:30 pm - Ioannis Filippidis
  • 2:15 pm - Open
  • 3:00 pm - Yilin Mo
  • 3:45 pm - Open
  • 4:30 pm - Depart

Abstract

Optimal Selective Attention and Action in Reactive Agents
Roy Fox, Hebrew University

2 Oct (Thu), 12 pm
106 Annenberg

Intelligent agents, interacting with their environment, operate under constraints on what they can observe and how they can act. Unbounded agents can use standard Reinforcement Learning to optimize their inference and control under purely external constraints. Bounded agents, on the other hand, are subject to internal constraints as well. This only allows them to partially notice their observations, and to partially intend their actions, requiring rational selection of attention and action.

In this talk we will see how to find the optimal information-constrained policy in reactive (memoryless) agents. We will discuss a number of reasons why internal constraints are often best modeled as bounds on information-theoretic quantities, and why we can focus on reactive agents with hardly any loss of generality. We will link the solution of the constrained problem to that of soft clustering, and present some of its nice properties, such as principled dimensionality reduction.