The Last Update Time: 2020.9.17
2015/09-present: Associate Professor, Nanjing University of Information, Science and Technology, Nanjing, China;
2011/09-2015/06: Ph.D., University of Wollongong, Wollongong, Australia;
PROFESSIONAL ACTIVITIES:
1. Guest Editor of “Journal of Computers”.
2. Paper reviewer for the 8th International Workshop of AAMAS-2015 on Agent-based Complex Automated Negotiations.
3. Invited presentation on the 6th International Workshop of AAMAS-2015 on Collaborative Agents Research & Development (CARE), 4th May 2015, Istanbul, Turkey.
Agent-based Task/Resource Allocation;
Grid/Cloud Computing;
Artificial Intelligence.
FUND (Leader)
1. Research about Resource Allocation in Open and Dynamic Cloud Environments (Fund No: 61602254). Chinese National Natural Science Foundation, China, 2016-2019.
2. Research about the Multi-agent-based Resource Allocation Algorithms in Social Networks (Fund No: BK20160968). Jiangsu Province Natural Science Foundation, China, 2016-2019.
FUND (Participation)
1. The Selection and Improvement of the P2P Center Node in Streaming Media (Fund No: 2008A520024), Henan Province Natural Science Foundation, China, 2007-2008.
PUBLICATION:
Peer-reviewed Journal Paper:
1. Yan Kong, Minjie Zhang and Dayong Ye, “A Belief Propagation-based Method for Task Allocation in Open and Dynamic Cloud Environments”, Knowledge-based Systems, Vol. 115, pp. 123-132, 2016.
2. Yan Kong, Minjie Zhang and Dayong Ye, “An Auction-based Approach for Group Task Allocation in An Open Network Environment”. The Computer Journal, 59 (3), pp.403-422, 2015.
3. Yan Kong, Minjie Zhang and Dayong Ye, “A Negotiation-based Method for Task Allocation with Time Constraints in Open Grid Environments”. Concurrency and Computation: Practice and Experience. Vol. 27, No.3, pp. 735-761, 2015.
Scholarly Book Chapters:
1. Yan Kong, Minjie Zhang and Dayong Ye, “A Group Task Allocation Strategy in Open and Dynamic Grid Environments”. Chapter in Recent Advances in Agent-based Complex Automated Negotiation, Studies in Computational Intelligence, Fujita et al. (Eds.), Springer. (in press)
2. Yan Kong, Minjie Zhang and Dayong Ye, “A Negotiation Method for Task Allocation with Time Constraints in Open Grid Environments”. In Next Frontier in Agent-Based Complex Automated Negotiation, Studies in Computational Intelligence, Fukuta et al. (Eds.), Springer, Vol. 596, pp. 19-36, 2014.
郑州大学 计算机软件与理论 With Certificate of Graduation for Study as Master's Candidates 工学硕士
University of Wollongong 计算机 With Certificate of Graduation for Doctorate Study 工学博士
Telephone : 15850620486
Email : kongyan4282@163.com
深度强化学习是深度学习和强化学习的结合,利用了深度学习的感知能力,来解决策略和值函数的建模问题,然后使用误差反向传播算法来优化目标函数;同时利用了强化学习的决策能力,来定义问题和优化目标。深度强化学习在一定程度上具备了解决复杂问题的通用智能,并在一些领域取得了成功。