TY - GEN
T1 - Play games using Reinforcement Learning and Artificial Neural Networks with Experience Replay
AU - Xu, Meng
AU - Shi, Haobin
AU - Wang, Yao
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/9/14
Y1 - 2018/9/14
N2 - Reinforcement learning is a self-learning algorithm in which an agent acquires experience through continuous interaction with the environment, which is more like the process of human or animal learning. Reinforcement learning is widely used in the field of playing games, and the classical reinforcement learning algorithm can easily produce Curse of Dimensionality when the state dimension is too large. In order to improve the convergence rate of reinforcement learning, a method of training Non Player Character (NPC) in games using Sarsa learning algorithm is proposed. The artificial neural network is used to approximate the value function. In order to make better use of experience, this paper sets up double neural networks, and uses experience memory to store experience, and uses experience replay to speed up the convergence of sarsa learning. Using the method presented in this paper to train NPC, we can find the NPC which is trained by the method has more learning ability than the classical reinforcement learning.
AB - Reinforcement learning is a self-learning algorithm in which an agent acquires experience through continuous interaction with the environment, which is more like the process of human or animal learning. Reinforcement learning is widely used in the field of playing games, and the classical reinforcement learning algorithm can easily produce Curse of Dimensionality when the state dimension is too large. In order to improve the convergence rate of reinforcement learning, a method of training Non Player Character (NPC) in games using Sarsa learning algorithm is proposed. The artificial neural network is used to approximate the value function. In order to make better use of experience, this paper sets up double neural networks, and uses experience memory to store experience, and uses experience replay to speed up the convergence of sarsa learning. Using the method presented in this paper to train NPC, we can find the NPC which is trained by the method has more learning ability than the classical reinforcement learning.
KW - artificial neural network
KW - experience replay
KW - Non Player Character
KW - reinforcement learning
UR - http://www.scopus.com/inward/record.url?scp=85055673585&partnerID=8YFLogxK
U2 - 10.1109/ICIS.2018.8466428
DO - 10.1109/ICIS.2018.8466428
M3 - 会议稿件
AN - SCOPUS:85055673585
T3 - Proceedings - 17th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2018
SP - 855
EP - 859
BT - Proceedings - 17th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2018
A2 - Xiong, Wei
A2 - Shang, Wenqiang
A2 - Xu, Simon
A2 - Lee, Hwee-Kuan
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 17th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2018
Y2 - 6 June 2018 through 8 June 2018
ER -