Recent Selected Publications / Research Proposal (*Corresponding Author)
[1] Yunlong Liu, “Graphical Model-Based Deep Reinforcement Learning in Partially Observable Domains” ，Research Proposal (If you are interested in this topic, please contact me)
[2] Yunlong Liu*, Jianyang Zheng, " Online Learning and Planning in Partially Observable Domains without Prior Knowledge", submitted.
[3] Yunlong Liu*, Jianyang Zheng, " Combining Offline Models and Online Monte-Carlo Tree Search for Planning from Scratch", submitted.
[4] Danning Yu, Kun Ni, Yunlong Liu*, “Deep Q-network with Predictive State Models in Partially Observable Domains”, submitted.
[5] Yunlong Liu*, Yifeng Zeng, Hexing Zhu, Yun Tang, "Making and Improving Predictions of Interest Using an MDP Model”, AAMAS 2017 (CCF B)
[6] Yunlong Liu*, Hexing Zhu, Yifeng Zeng, Zongxiong Dai, "Learning Predictive State Representations via Monte-Carlo Tree Search", IJCAI 2016 （CCF A）
[7] Yunlong Liu*, Yun Tang, and Yifeng Zeng, "Predictive State Representations with State Space Partitioning", AAMAS 2015 (Full/oral paper (CCF A).
[8] Chunqing Huang, Yisheng An, Sun Zhou, Zhezheng Hong and Yunlong Liu*, "Basis selection in spectral learning of predictive state representations", Neurocomputing, vol.310 2018, 183–189. （SCI 2区）
[10] Yunlong Liu, Zijiang Yang, and Guoli Ji*, "Solving Partially Observable Problems with Inaccurate PSR Models", Information Sciences,vol.283:142-152, 2014(SCI 2区).
[11] Yunlong Liu*, and Guoli Ji, "An Algorithm for Resetting PSR Models", Chinese Journal of Computers, vol.35(5):1046-105, 2012, in Chinese.
[12] Yunlong Liu*, Guoli Ji, and Zijiang Yang, "Using Learned PSR models for Planning under Uncertainty", the 23th Canadian Conference on Artificial Intelligence, volume 6085 of Lecture Notes in Computer Science: 309-314, 2010.
[13] C.Q. Huang, L.F. Xie, and Y.L. Liu*, "PD plus Error-dependent Integral Nonlinear Controllers for Robot Manipulators with an Uncertain Jacobian Matrix", ISA Transactions, vol.51(6):792-800, 2012.
[14] Yunlong Liu*, and Guoli Ji, "CMAC-based Sarsa(
)Learning Algorithms for RoboCup-soccer Goalkeeper", Journal of Beijing University of Technology, vol. 38(9):1348-1352, 2012, in Chinese.
[15] Guoli Ji, Yong Zeng, Jinting Guan, Qingshun Quinn, and Yunlong Liu*, "Recent Advances in Mathematical Modeling and Simulation of DNA Replication Process"， Current Bioinformatics, Vol. 8:524-529, 2013.
Research Interest
● （Deep）Reinforcement Learning with focus on reinforcement learning in partially observable domains, planning with model uncertainty, spectral learning, Predictive State Representations(PSRs) and POMDPs.
Service
● Program committee member: AAAI 2019, IJCAI 2017
● Reviewer: NIPS 2016，ACM Transactions on Intelligent Systems and Technology, IEEE Transactions on Neural Networks and Learning Systems, etc. .
