|Cyclic Error Correction based Q-learning for Mobile Robots Navigation
Rongkuan Tang, Hongliang Yuan*
International Journal of Control, Automation, and Systems, vol. 15, no. 4, pp.1790-1798, 2017
Abstract : "Similar to control systems, reinforcement learning can capture notions of optimal behavior using natural
interaction experience. In the context of reinforcement learning, the temporal difference error of the generated
experience measures how well the learner responds to the system. Specially sequential difference of accumulated
temporal difference error can indicate the learning performance. In this paper, we fully utilize the error correction in
closed-loop peculiarity by mapping a representation error to the step-size component. The proposed cyclic step-size
could better control how new estimates are iteratively blended together over time, and the new estimates guide the
action selection process which in turn influence the value distribution. To guide more promising action decision, an
ensemble action selector is proposed which incorporates the idea of ensemble wisdom of the weak. Experimental
results conducted under gridworld mobile robot navigation task demonstrate the validity, capacity of fast learning
and easy-plugged implementation of the derived algorithm, leading to increasing applicability to real-life problems."
Cyclic step-size, ensemble wisdom, mobile robots navigation, reinforcement learning.