A Coach-Based Bayesian Reinforcement Learning Method for Snake Robot Control

Abstract

Reinforcement Learning (RL) usually needs thousands of episodes, leading its applications on physical robots expensive and challenging. Little research has been reported about snake robot control using RL due to additional difficulty of high redundancy of freedom. We propose a coach-based deep learning method for snake robot control, which can effectively save convergence time with much less episodes. The main contributions include: 1) a unified graph-based Bayesian framework integrating a coach module to guide the RL agent; 2) an explicit stochastic formulation of robot-environment interaction with uncertainty; 3) an efficient and robust training process for snake robot control to achieve both path planning and obstacle avoidance simultaneously. The performance has been demonstrated on both simulation and real-world data in comparison with state-of-the-art, showing promising results.