An Extremely Simple Reinforcement Learning Rule for Neural Networks

Authors:
Xiaolong Ma
Affiliations:
Stony Brook University, Stony Brook, NY 11794-3800, USA
Venue:
ISNN '07 Proceedings of the 4th international symposium on Neural Networks: Advances in Neural Networks
Year:
2007

Citing 6
Cited 0

Introduction to the theory of neural computation

Introduction to the theory of neural computation
Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning

Machine Learning
Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
Neuromorphic architectures for nanoelectronic circuits: Research Articles

International Journal of Circuit Theory and Applications - Nanoelectric Circuits
Infinite-horizon policy-gradient estimation

Journal of Artificial Intelligence Research
Global Reinforcement Learning in Neural Networks

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we derive a simple reinforcement learning rule based on a more general form of REINFORCE formulation. We test our new rule on both classification and reinforcement problems. The results have shown that although this simple learning rule has a high probability of being stuck in local optimum for the case of classification tasks, it is able to solve some global reinforcement problems (e.g. the cart-pole balancing problem) directly in the continuous space.