Robotic action acquisition with cognitive biases in coarse-grained state space. (July 2016)

• Record Type: Journal Article
• Authors: Uragami, Daisuke; Kohno, Yu; Takahashi, Tatsuji
• Is Part Of: Bio systems. Volume 145(2016:Jul.)
• Page Start: 41
• Page End: 52
• Publication Date: 2016-07
• Subjects: Loosely symmetric model -- Q-learning -- Acrobot -- Giant-swing robot -- Partially observable markov decision process -- Biologically inspired cognitive architecture; Biological systems -- Periodicals; Biology -- Periodicals; Biology -- Periodicals; Evolution -- Periodicals; Biologie -- Périodiques; Évolution -- Périodiques; 570
• DOI: 10.1016/j.biosystems.2016.05.007
• Languages: English
• ISSNs: 0303-2647

Abstract

Abstract: Some of the authors have previously proposed a cognitively inspired reinforcement learning architecture (LS-Q) that mimics cognitive biases in humans. LS-Q adaptively learns under uniform, coarse-grained state division and performs well without parameter tuning in a giant-swing robot task. However, these results were shown only in simulations. In this study, we test the validity of the LS-Q implemented in a robot in a real environment. In addition, we analyze the learning process to elucidate the mechanism by which the LS-Q adaptively learns under the partially observable environment. We argue that the LS-Q may be a versatile reinforcement learning architecture, which is, despite its simplicity, easily applicable and does not require well-prepared settings.