RTP-Q: A Reinforcement Learning System with Time Constraints Exploration Planning for Accelerating the Learning Rate

スポンサーリンク

概要

• 論文の詳細を見る

• Reinforcement learning is an efficient method for solving Markov Decision Processes that an agent improves its performance by using scalar reward values with higher capability of reactive and adaptive behaviors. Q-learning is a representative reinforcement learning method which is guaranteed to obtain an optimal policy but needs numerous trials to achieve it. k-Certainty Exploration Learning System realizes active exploration to an environment, but, the learning process is separated into two phases and estimate values are not derived during the process of identifying the environment. Dyna-Q architecture makes fuller use of a limited amount of experiences and achieves a better policy with fewer environment interactions during identifying an environment by learning and planning with constrained time, however, the exploration is not active. This paper proposes a RTP-Q reinforcement learning system which varies an efficient method for exploring an environment into time constraints exploration planning and compounds it into an integrated system of learning, planning and reacting for aiming for the best of both methods. Based on improving the performance of exploring an environment, refining the model of the environment, the RTP-Q learning system accelerates the learning rate for obtaining an optimal policy. The results of experiment on navigation tasks demonstrate that the RTP-Q learning system is efficient.

• 社団法人電子情報通信学会の論文
• 1999-10-25

著者

• TATSUMI Shoji

  Faculty of Engineering, Osaka City University

• Tatsumi Shoji

  Faculty Of Engineering Osaka City University

• Tatsumi S

  Osaka City Univ. Osaka‐shi Jpn

• Zhao Gang

  Fujitsu Kansai-chubu Net-tech Limited

• Zhao Gang

  National Astronomical Observatories Chinese Acad. Of Sci. Beijing Chn

• SUN Ruoying

  Faculty of Engineering, Osaka City University

• ZHAO Gang

  Faculty of Engineering, Osaka City University

• SUN Ruoying

  College of Industry and Commerce Management, Liaoning University

• Sun Ruoying

  Faculty Of Engineering Osaka City University

関連論文

• Parallel Genetic Algorithm for Constrained Clustering
• Parallel Genetic Algorithms Based on a Multiprocessor System FIN and Its Application
• Boltzmann Machine and Parallel Genetic Algorithms Based on the Fin
• A PARALLEL IMPLEMENTATION OF THE LEARNING CLASSIFIER SYSTEMS ON THE FIN-1
• Substellar Companions to Evolved Intermediate-Mass Stars : HD 145457 and HD 180314
• Detection of Small-Amplitude Oscillations in the G-Giant HD 76294 (ζ Hydrae)
• Calculation of Photoionized Plasmas with a Detailed-Configuration-Accounting Atomic Model
• Multiagent Cooperating Learning Methods by Indirect Media Communication(Neural Netoworks and Bioengineering)
• On the Spectroscopic Determination of Atmospheric Parameters and O/Fe Abundances of RR Lyrae Stars
• Multiagent Cooperating Learning Methods by Indirect Media Communication
• Na I D Lines in the SN 2002ap Spectrum
• On the Abundance of Potassium in Metal-Poor Stars
• α Element Abundances in Mildly Metal-Poor Stars
• Convergence of the Q-ae Learning on Deterministic MDPs and Its Efficiency on the Stochastic Environment
• RTP-Q: A Reinforcement Learning System with Time Constraints Exploration Planning for Accelerating the Learning Rate
• Q-ee Learning : A Novel Q-Learning Method with Exploitation and Exploration
• An Accelerated k-Certainty Exploration Method
• Electron Impact Excitation of Ti XVIII
• Applying Genetic Algorithm to Conceptual Clustering
• Algorithms for Matrix Multiplication and the FFT on a Processor Array with Separable Buses(Regular Section)
• Solving an All-Pairs Shortest Paths Problem on a Processor Array with Separable Buses
• A Pattern Defect Inspection Method by Grayscale Image Comparison without Precise Image Alignment
• Electron Impact Excitation of N-like Ca XIV

もっと見る 閉じる

スポンサーリンク