Exploring Parameter Space in Reinforcement Learning

Autor:	Rückstieß Thomas, Sehnke Frank, Schaul Tom, Wierstra Daan, Sun Yi, Schmidhuber Jürgen
Jazyk:	angličtina
Rok vydání:	2010
Předmět:	reinforcement learning optimization exploration policy gradients Technology
Zdroj:	Paladyn, Vol 1, Iss 1, Pp 14-24 (2010)
Druh dokumentu:	article
ISSN:	2081-4836
DOI:	10.2478/s13230-010-0002-4
Popis:	This paper discusses parameter-based exploration methods for reinforcement learning. Parameter-based methods perturb parameters of a general function approximator directly, rather than adding noise to the resulting actions. Parameter-based exploration unifies reinforcement learning and black-box optimization, and has several advantages over action perturbation. We review two recent parameter-exploring algorithms: Natural Evolution Strategies and Policy Gradients with Parameter-Based Exploration. Both outperform state-of-the-art algorithms in several complex high-dimensional tasks commonly found in robot control. Furthermore, we describe how a novel exploration method, State-Dependent Exploration, can modify existing algorithms to mimic exploration in parameter space.
Databáze:	Directory of Open Access Journals
Externí odkaz:	https://doaj.org/article/1d7d7f4ee4c14115b57878db43f50fab Zobrazit plný text záznamu Full text from SpringerLink View record in DOAJ