2019-2020 2nd term, IERG 6130

Reinforcement Learning and Beyond
[Home | Schedule | Final Project ]

Project Topics

Course project is an opportunity for you to apply what you have learned in class to a problem of your interest in reinforcement learning. Two students form a group. The course projects of 2020 Spring term are now released as follows:


Author(s) Project Title Link
Jie Chen & Shouhang Hu Pair Trading with Reinforcement Learning link
Minghao Guo & Haodong Duan Improve the Training Efficiency for Multi-Agent RL using Master-Slave Framework link
Xiaoyang Guo & Yi Zhang Learning to Navigate with Environment Map Memory link
Yuze He & Xiang Pan A Reinforcement-learning based Energy Plan Selection Approach for Energy Markets with Retail Choice link
Jinwei Liu & Jiaqi Xu Learn to Generate Rectilinear Steiner Minimum Tree link
Ka Lok Ng & Xiao Yi Exploration of Adversarial Inputs to Reinforcement Learning Agents link
Anyi Rao & Xudong Xu Reinforcement Learning for Video Summarization link
Siyu Shen Understanding Behaviors Learnt by Multi-agent RL for Massively Multiplayer Online Games link
Shuyao Shi & Zirui Song Learning to Evade Jamming Attacks in the Wireless Networks Using Reinforcement Learning link
Tai Wang & Yuanbo Xiangli Learn to Solve Rubik’s Cubes More Efficiently and Effectively link
Zikai Wei & Jiankai Sun Vision-Dialog Navigation and Beyond link
Wenjie Xu & Gongpu Chen Reinforcement Learning for Delay-Constrained Network Optimization link
Ceyuan Yan & Yinghao Xu From Rule-based to Learning-based Network Pruning link
Wenyong Zhang & Liangliang Hao Learn to Charge Electric Vehicles in Large Scale link
Zheyuan Yang & Yuming Zhang Reinforcement Learning for UAV Trajectory Control link
Jinan Zhou Exploring Natural Language Emergence from Multi-Agent Collaboration link
Yutong Zhou & Zhehao Jiang Agent-based Obstacle Bypassing System link
Jingyan Zhou & Jinchao Li Policy Learning for Task-oriented Dialogue Systems link
Siyue Xie & Yiming Li A Graph-based Model for Ride-sharing Order Dispatching via Decentralized Multi-agent Deep Reinforcement Learning link