@inproceedings{5bdb72acbcf9475ba33b6b1d8c8c4798,
title = "Opposition-based Q(λ) algorithm",
abstract = "The problem of delayed reward in reinforcement learning is usually tackled by implementing the mechanism of eligibility traces. In this paper we introduce an extension of eligibility traces to solve one of the challenging problems in reinforcement learning. The concept of opposition traces is proposed in this work to deal with large state space problems in reinforcement learning applications. We combine the idea of opposition and eligibility traces to construct the oppositionbased Q(λ). The results are compared with the conventional Watkins' Q(λ) and reflect a remarkable performance increase.",
author = "Maryam Shokri and Tizhoosh, {Hamid R.} and Mohamed Kamel",
year = "2006",
language = "English (US)",
isbn = "0780394909",
series = "IEEE International Conference on Neural Networks - Conference Proceedings",
pages = "254--261",
booktitle = "International Joint Conference on Neural Networks 2006, IJCNN '06",
note = "International Joint Conference on Neural Networks 2006, IJCNN '06 ; Conference date: 16-07-2006 Through 21-07-2006",
}