王达 - 2138CC太阳集团（大数据学院）

王达，博士，讲师，2025年博士毕业于2138CC太阳集团，研究方向为强化学习与具身智能，重点围绕强化学习数据效率、泛化性能提升、Sim2real等问题开展研究。近年来，在《Machine Learning》、《Neural Networks》、ICML、NeurIPS、AAAI等国内外期刊和会议发表论文多篇，授权国家发明专利2项。曾获第四届CCF优秀大学生学术秀博士组二等奖、2138cn太阳集团古天乐优秀博士论文奖、2138cn太阳集团古天乐首届“登崇杯”研究生创新作品大赛博士组一等奖等荣誉。担任ICML、NeurIPS、AAAI等各类国际会议和期刊审稿人。

[1] Da Wang, Lin Li, Wei Wei*, Qixian Yu, Jianye Hao, Jiye Liang. Improving Generalization in Offline Reinforcement Learning via Adversarial Data Splitting. Proceedings of the Forty-first International Conference on Machine Learning, 2024: 50822-50839. (CCF A类会议, 人工智能领域顶级会议)

[2] Da Wang, Lin Li, Wei Wei*, Qixian Yu, Jianye Hao, Jiye Liang. Improving Generalization in Offline Reinforcement Learning via Latent Distribution Representation Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 2025: 21053-21061. (CCF A类会议, 人工智能领域顶级会议, Oral: 前5%)

[3] Ting Guo, Da Wang, Jiye Liang*, Kaihan Zhang, Jianchao Zeng. SpeAr: A Spectral Approach for Zero-Shot Node Classification. Advances in Neural Information Processing Systems, 2024: 69000-69021. (CCF A类会议, 人工智能领域顶级会议)

[4] Da Wang, Wei Wei*, Lin Li, Xin Wang, Jiye Liang. Rethinking Exploration-Exploitation Trade-off in Reinforcement Learning via Cognitive Consistency. Neural Networks, 2025, 187: 107342. (CCF B类期刊)

[5] Wei Wei, Da Wang, Lin Li, Jiye Liang*. Re-attentive Experience Replay in Off-policy Reinforcement Learning. Machine Learning, 2024, 113(5): 2327-2349. (CCF B类期刊)

[6] Wei Wei, Da Wang, Jiye Liang*. Accelerating ReliefF using information granulation. International Journal of Machine Learning and Cybernetics, 2022, 13(1): 29-38. (CCF C类期刊)

[1] 山西省研究生创新项目: 深度强化学习的稳健经验回放方法研究, 2021.09-2022.09, 主持(已结项)

[2] 科技创新2030-“新一代人工智能”重大项目: 认知计算基础理论与方法研究, 项目总预算452万元, 2021.01-2024.12, 参与(项目编号: 2020AAA0106100)

[3] 国家重点研发计划: 基于自组网无人机群的污染气体激光监测平台, 项目总预算465万元, 2020.12-2023.11, 参与(项目编号: SQ2019YFE011866)