@inproceedings{6d5d95925b504121ac8a8158572797f9,
title = "IBPO: Solving 3D Strategy Game with the Intrinsic Reward",
abstract = "In recent years, deep reinforcement learning achieves great success in many fields, especially in the field of games, such as AlphaGo, AlphaZero and AlphaStar. However, reward sparsity is still a problem in the 3D strategy games with a higher dimension of state space and more complex game scenarios. To solve this problem, in this paper, we propose an intrinsic-based policy optimization algorithm (IBPO) for reward sparsity. The IBPO incorporates the intrinsic reward into the traditional policy, which composed by the differential fusion mechanism and the modified value network. The experimental results show our method can obtain better performance than the previous methods on the VizDoom.",
keywords = "Deep reinforcement learning, Game, Intrinsic reward, Reward sparsity",
author = "Huale Li and Rui Cao and Xiaohan Hou and Xuan Wang and Linlin Tang and Jiajia Zhang and Shuhan Qi",
note = "Publisher Copyright: {\textcopyright} 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.; 4th International Conference on Smart Vehicular Technology, Transportation, Communication and Applications, VTCA 2021 ; Conference date: 22-05-2021 Through 24-05-2021",
year = "2022",
doi = "10.1007/978-981-16-4039-1\_25",
language = "英语",
isbn = "9789811640384",
series = "Smart Innovation, Systems and Technologies",
publisher = "Springer Science and Business Media Deutschland GmbH",
pages = "257--264",
editor = "Tsu-Yang Wu and Shaoquan Ni and Shu-Chuan Chu and Chi-Hua Chen and Margarita Favorskaya",
booktitle = "Advances in Smart Vehicular Technology, Transportation, Communication and Applications - Proceedings of VTCA 2021",
address = "德国",
}