Fuzzy Sarsa with Focussed Replacing Eligibility Traces for Robust and Accurate Control

スポンサーリンク

概要

• 論文の詳細を見る

• Several methods of reinforcement learning in continuous state and action spaces that utilize fuzzy logic have been proposed in recent years. This paper introduces Fuzzy Sarsa(λ), an on-policy algorithm for fuzzy learning that relies on a novel way of computing replacing eligibility traces to accelerate the policy evaluation. It is tested against several temporal difference learning algorithms: Sarsa(λ), Fuzzy Q(λ), an earlier fuzzy version of Sarsa and an actor-critic algorithm. We perform detailed evaluations on two benchmark problems : a maze domain and the cart pole. Results of various tests highlight the strengths and weaknesses of these algorithms and show that Fuzzy Sarsa(λ) outperforms all other algorithms tested for a larger granularity of design and under noisy conditions. It is a highly competitive method of learning in realistic noisy domains where a denser fuzzy design over the state space is needed for a more precise control.

• 2010-06-01

著者

• Kamdem Sylvain

  Oita University

• Ohki Hidehiro

  Oita University

• Sueda Naomichi

  Oita University

関連論文

• Fuzzy Sarsa with Focussed Replacing Eligibility Traces for Robust and Accurate Control
• Fuzzy Sarsa with Focussed Replacing Eligibility Traces for Robust and Accurate Control

スポンサーリンク