TY - GEN
T1 - An average-reward reinforcement learning algorithm based on Schweitzer's Transformation
AU - Li, Jianjun
AU - Ren, Jiangong
AU - Li, Yanjie
PY - 2012
Y1 - 2012
N2 - In this paper, we propose a relative value iteration reinforcement learning (RVI-RL) algorithm based on Schweitzer's Transformation for Markov decision processes (MDP) with average reward. An equivalent average reward optimality equation and a new form of action-value function are presented via Schweitzer's Transformation. Then, combined with the theory of relative value iteration, this RVI-RL algorithm doesn't only omit the estimation of the average reward in the learning, but also improves the convergence rate. Finally, a simulation experiment for the navigation of autonomous mobile robot is considered, which illustrates the effectiveness and applicability of the algorithm.
AB - In this paper, we propose a relative value iteration reinforcement learning (RVI-RL) algorithm based on Schweitzer's Transformation for Markov decision processes (MDP) with average reward. An equivalent average reward optimality equation and a new form of action-value function are presented via Schweitzer's Transformation. Then, combined with the theory of relative value iteration, this RVI-RL algorithm doesn't only omit the estimation of the average reward in the learning, but also improves the convergence rate. Finally, a simulation experiment for the navigation of autonomous mobile robot is considered, which illustrates the effectiveness and applicability of the algorithm.
KW - Average reward
KW - Reinforcement Learning
KW - Relative value iteration
KW - Robotic navigation
UR - https://www.scopus.com/pages/publications/84873563097
M3 - 会议稿件
AN - SCOPUS:84873563097
SN - 9789881563811
T3 - Chinese Control Conference, CCC
SP - 2966
EP - 2970
BT - Proceedings of the 31st Chinese Control Conference, CCC 2012
T2 - 31st Chinese Control Conference, CCC 2012
Y2 - 25 July 2012 through 27 July 2012
ER -