Research on Path Planning Algorithm for Mobile Robot Based on Improved Reinforcement Learning.

This paper proposes an improved Q-learning algorithm to solve the problem that the traditional Q-learning algorithm is applied to the path planning of mobile robot in complex environment, the convergence speed is slow due to large number of iterations, and even the actual reward signal is sparse so that the agent cannot get the optimal path. The improved algorithm reduces the number of iterative runs of the agent in the path planning process to improve the convergence speed by further updating the iterative formula of the Q-value. At the same time, adding sparse reward algorithm leads to finding the optimal path successfully. In order to verify the effectiveness of the algorithm, simulation experiments are carried out in two groups of environments: the simple and the complex. The final simulation results show that the improved algorithm can avoid obstacles effectively and find the optimal path to the target position after less iterations, which proves that the performance of the improved algorithm is better than the traditional Q-learning in the path planning.