RLChina 2023 Poster

Poster




1
论文题目： On the Effectiveness of Large Language Models as Interactive Modeling Tools for Operations Research
讲者单位：中国科学院自动化研究所
期刊或会议：
全部作者：Zeyu Ba, Jiwen Jiang, Luoyang Sun, Ning Yang, Xuanfa Jin, Runji Lin, Xihan Li, Haifeng Zhang, Jun Wang


2
论文题目： Low Rank Matrix Differential Equations as Deep Kernel Principal Component Analysis
讲者单位：中北大学
期刊或会议：
全部作者：Shimin Shan, Yanbo Wang, Wenyu Chen, Fangshu Cui


3
论文题目： AlignDiff: Aligning Diverse Human Preferences via Behavior-Customisable Diffusion Model
讲者单位：天津大学
期刊或会议：NeurIPS 2023
全部作者：Zibin Dong, Yifu Yuan, Jianye Hao, Fei Ni, Yao Mu, Yan Zheng, Yujing Hu, Tangjie Lv, Changjie Fan, Zhipeng Hu


4
论文题目： METAGPT: Meta Programming For A Multi-agent Collaborative Framework
讲者单位：DeepWisdom深度赋智
期刊或会议：
全部作者：Sirui Hong, Mingchen Zhuge, Jonathan Chen, Xiawu Zheng, Yuheng Cheng, Ceyao Zhang, Jinlin Wang, Zili Wang, Steven Ka Shing Yau,
                        Zijuan Lin, Liyang Zhou, Chenyu Ran, Lingfeng Xiao, Chenglin Wu, Jürgen Schmidhuber


5
论文题目： OpenRL: A Unified Reinforcement Learning Framework
讲者单位：第四范式
期刊或会议：
全部作者： Shiyu Huang, Wenze Chen, Yiwen Sun, Fuqing Bie, Wei-Wei Tu


6
论文题目： Hybrid-DeepCord: Towards Scalable, Efficient, and Robust Coordination of Ride-Pooling and Public Transit via Hybrid Multiagent Reinforcement Learning
讲者单位：香港科技大学
期刊或会议：
全部作者：Yulong Hu, Sen Li


7
论文题目： RACE: Improve Multi-Agent Reinforcement Learning with Representation Asymmetry and Collaborative Evolution
讲者单位：天津大学
期刊或会议：ICML 2023
全部作者： Pengyi Li, Jianye Hao, Hongyao Tang, Yan Zheng, Xian Fu


8
论文题目： ERL—Re²: Efficient Evolutionary Reinforcement Learning with Shared State Representation and Individual Policy Representation
讲者单位：天津大学
期刊或会议：ICLR 2023
全部作者：Jianye Hao, Pengyi Li, Hongyao Tang, Yan Zheng, Xian Fu, Zhaopeng Meng


9
论文题目： ReMax: A simple, Efficient,Effective Reinforcement Learning Method for Aligning Large Language Models
讲者单位：香港中文大学（深圳）
期刊或会议：
全部作者：Ziniu Li, Tian Xu, Yushun Zhang, Zhihang Lin, Yang Yu, Ruoyu Sun, Zhi-Quan Luo


10
论文题目： RiskQ: Risk-sensitive Multi-Agent Reinforcement Learning Value Factorization
讲者单位：厦门大学
期刊或会议：NeurIPS 2023
全部作者：Siqi Shen, Chennan Ma, Chao Li, Weiquan Liu, Yongquan Fu, Songzhu Mei, Xinwang Liu, Cheng Wang


11
论文题目： ResQ: A Residual Q Function-based Approach for Multi-Agent Reinforcement Learning Value Factorization
讲者单位：厦门大学
期刊或会议：NeurIPS 2022
全部作者：Siqi Shen, Mengwei Qiu, Jun Liu, Weiquan Liu, Yongquan Fu, Xinwang Liu, Cheng Wang


12
论文题目： Leveraging Large Language Models for StarCraft Ⅱ: A Text Environment and Chain of Summarization Approach
讲者单位：中国科学院自动化研究所
期刊或会议：
全部作者：Weiyu Ma, Qirui Mi, Xue Yan, Yuqiao Wu, Haifeng Zhang, Jun Wang


13
论文题目： Adaptive Control Strategy for Quadruped Robots in Actuator Degradation Scenarios
讲者单位：上海交通大学
期刊或会议：
全部作者：Xinyuan Wu, Wentao Dong, Hang Lai, Yong Yu, Ying Wen


14
论文题目： Imitation Learning from Imperfection: Theoretical Justifications and Algorithms
讲者单位：南京大学
期刊或会议：NeurIPS 2023
全部作者：Ziniu Li, Tian Xu, Zeyu Qin, Yang Yu, Zhi-Quan Luo


15
论文题目： Lending Interaction Wings to Recommender Systems with Conversational Agents
讲者单位：伦敦大学学院
期刊或会议：NeurIPS 2023
全部作者：Jiarui Jin, Xianyu Chen, Fanghua Ye, Mengyue Yang, Yue Feng, Weinan Zhang, Yong Yu, Jun Wang


16
论文题目： EUCLID: Towards Efficient Unsupervised Reinforcement Learning with Multi-choice Dynamics Model
讲者单位：天津大学
期刊或会议：ICLR 2023
全部作者：Yifu Yuan, Jianye Hao, Fei Ni, Yao Mu, Yan Zheng, Yujing Hu, Jinyi Liu, Yingfeng Chen, Changjie Fan


17
论文题目： 基于图形学程序噪声渲染的通用对抗样本生成方法
讲者单位：同济大学
期刊或会议：Displays
全部作者：严峻, 尹慧琳, 葛万成, 刘丽


18
论文题目： Agent as Cerebrum, Controller as Cerebellum: Implementing an Embodied LMM-based Agent on Drones
讲者单位：北京航空航天大学
期刊或会议：
全部作者：Haoran Zhao, Fengxing Pan, Huqiuyue Ping, Yaoming Zhou


19
论文题目： ProAgent: Building Proactive Cooperative AI with Large Language Models
讲者单位：香港中文大学（深圳）
期刊或会议：
全部作者：Ceyao Zhang, Kaijie Yang, Siyi Hu, Zihao Wang, XIaojun Chang, Feng Yin, Yitao Liang, Yaodong Yang


20
论文题目： Is Risk-Sensitive Reinforcement Learning Properly Resolved?
讲者单位：上海交通大学
期刊或会议：
全部作者：Ruiwen Zhou, Minghuan Liu, Kan Ren, XUfang Luo, Weinan Zhang, Dongsheng Li


21
论文题目： Optimal Market Making Agents Under Model Uncertainty: A Robust Reinforcement Learning Approach
讲者单位：新加坡国立大学重庆研究院
期刊或会议：
全部作者：Ying Chen, JuLian Sester, Hoang Hai Tran, Yijiong Zhang


22
论文题目： Efficient Symbolic Policy Learning with Differentiable Symbolic Expression
讲者单位：中国科学院计算技术研究所
期刊或会议：NeurIPS 2023
全部作者：Jiaming Guo, Rui Zhang, Shaohui Peng, Qi Yi, Xing Hu, Ruizhi Chen, Zidong Du, Xishan Zhang, Ling Li, Qi Guo, Yunji Chen


23
论文题目： Context Shift Reduction for Offline Meta-Reinforcement Learning
讲者单位：中国科学院计算技术研究所
期刊或会议：NeurIPS 2023
全部作者：Yunkai Gao, Rui Zhang, Jiaming Guo, Fan Wu, Qi Yi, Shaohui Peng, Siming Lan, Ruizhi Chen, Zidong Du, Xing Hu, Qi Guo, Ling Li, Yunji Chen


24
论文题目： Contrastive Modules with Temporal Attention for Multi-Task Reinforcement Learning
讲者单位：中国科学院计算技术研究所
期刊或会议：NeurIPS 2023
全部作者：Siming Lan, Rui Zhang, Qi Yi, Jiaming Guo, Shaohui Peng, Yunkai Gao, Fan Wu, Ruizhi Chen, Zidong Du, Xing Hu, Xishan Zhang, Ling Li, Yunji Chen


25
论文题目： Online Prototype Alignment for Few-shot Policy Transfer
讲者单位：中国科学院计算技术研究所
期刊或会议：ICML 2023
全部作者：Qi Yi, Rui Zhang, Shaohui Peng, Jiaming Guo, Yunkai Gao, Kaizhao Yuan, Ruizhi Chen, Siming Lan, Xing Hu, Zidong Du, Xishan Zhang, Qi Guo, Yunji Chen


26
论文题目： Conceptual Reinforcement Learning for Language-Conditioned Tasks
讲者单位：中国科学院计算技术研究所
期刊或会议：AAAI 2023
全部作者： Shaohui Peng, Xing Hu, Rui Zhang, Jiaming Guo, Qi Yi, Ruizhi Chen, Zidong Du, Ling Li, Qi Guo, Yunji Chen