Preservation and Application of Acquired Knowledge Using Instance-Based Reinforcement Learning for Multi-Robot Systems
Junki Sakanoue, Toshiyuki Yasuda, Kazuhiro Ohkura · Journal of Advanced Computational Intelligence and Intelligent Informatics · 2011
We have been developing a reinforcement learning technique called BRL as an approach to autonomous specialization, which is a new concept in cooperative multi-robot systems. BRL has a mechanism for autonomously segmenting the continuous state and action space. However, as in other machine learning approaches, overfitting is occasionally observed after successful learning. This paper proposes a technique to sophisticatedly utilize messy knowledge acquired using BRL. The proposed technique is expected to show better robustness against environmental changes. We investigate the proposed technique by conducting computer simulations of a cooperative carrying task.