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.
CITATION STYLE
Rückstieb, T., Sehnke, F., Schaul, T., Wierstra, D., Sun, Y., & Schmidhuber, J. (2010). Exploring Parameter Space in Reinforcement Learning. Paladyn, 1(1), 14–24. https://doi.org/10.2478/s13230-010-0002-4
Mendeley helps you to discover research relevant for your work.