Online Regret Bounds for a New Reinforcement Learning Algorithm
Peter Auer and Ronald Ortner
In: 1st Austrian Cognitive Vision Workshop, 31 Jan 2005, Zell an der Pram, Austria.

There is a more recent version of this eprint available. Click here to view it.

Abstract

We present a new learning algorithm for undiscounted finite-step reinforcement learning with restarts. Our algorithm is based on upper confidence bounds and achieves logarithmic online regret in respect to an optimal policy.

Available Versions of this Item

• Online Regret Bounds for a New Reinforcement Learning Algorithm (deposited 28 November 2005) [Currently Displayed]
  • Online Regret Bounds for a New Reinforcement Learning Algorithm (deposited 29 December 2005)
  • Online Regret Bounds for a New Reinforcement Learning Algorithm (deposited 29 December 2005)

[Edit]