Robotic action acquisition with cognitive biases in coarse-grained state space

详细信息    查看全文

• 作者：Daisuke Uragami^a ; ^{dduragami@gmail.com" class="auth_mail" title="E-mail the corresponding author} ; Yu Kohno^b ; ^{yu.kohno02@gmail.com" class="auth_mail" title="E-mail the corresponding author} ; Tatsuji Takahashi^c ; ^{tatsuji.takahashi@gmail.com" class="auth_mail" title="E-mail the corresponding author}
• 关键词：Loosely symmetric model ; Q-learning ; Acrobot ; Giant-swing robot ; Partially observable markov decision process ; Biologically inspired cognitive architecture
• 刊名：Biosystems
• 出版年：2016
• 出版时间：July 2016
• 年：2016
• 卷：145
• 期：Complete
• 页码：41-52
• 全文大小：3344 K

文摘

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.