Junchi Liang
I received my PhD degree from the Department of Computer Science at Rutgers University. My advisor is Professor Abdeslam Boularias. Before I came to Rutgers, I obtained a Master degree in computer science at University of Chicago, a Bachelors Degree in computer science at South China University of Technology.
My research interest includes reinforcement learning, imitation learning, deep learning and robotics.
Email: jl2068 [at] cs [dot] rutgers [dot] edu
Publication
Junchi Liang and Abdeslam Boularias. ”Learning Category-Level Manipulation Tasks from Point Clouds with Dynamic Graph CNNs”. In Proceedings of the 2023 International Conference on Robotics and Automation (ICRA), London, UK, 2023.
Junchi Liang, Bowen Wen, Kostas E. Bekris and Abdeslam Boularias. ”Learning Sensorimotor Primitives of Sequential Manipulation Tasks from Visual Demonstrations”. In Proceedings of the 2022 International Conference on Robotics and Automation (ICRA), Philadelphia, USA, 2022.
Junchi Liang, Abdeslam Boularias. "Inferring Time-delayed Causal Relations in POMDPs from the Principle of Independence of Cause and Mechanism". In Proceedings of the 30th International Joint Conference on Artificial Intelligence (IJCAI),Montreal, Canada, 2021.
Junchi Liang, Abdeslam Boularias. "Self-Supervised Learning of Long-Horizon Manipulation Tasks with Finite-State Task Machines." Learning for Dynamics and Control. PMLR, 2021.
Junchi Liang, Abdeslam Boularias. "Learning Transition Models with Time-delayed Causal Relations." 2020 IEEE/RSJ International Conference on Intelligent Robotsand Systems (IROS). IEEE, 2020.
Junchi Liang, Abdeslam Boularias, "Task-Relevant Object Discovery and Categorization for Playing First-person Shooter Games", arXiv:1806.06392
Andrew S Morgan, Bowen Wen,Junchi Liang, Abdeslam Boularias, Aaron Dollar and Kostas Bekris. "Vision-driven Compliant Manipulation for Reliable, High-Precision Assembly Tasks". In Proceedings of Robotics: Science and Systems (R:SS),virtual, 2021.
Repository
Reinforcement Learning Benchmark
https://github.com/Junchi-Liang/rl_benchmark
In this repo, I implement several modern reinforcement learning algorithms. A demo video for my implementation of PPO in playing Vizdoom can be found below:
Education
PhD in Computer Science, Rutgers University, Sep. 2016 - Sep. 2022
M. S. in Computer Science, University of Chicago, Sep. 2014 - Dec. 2015
B. Eng. in Computer Science and Technology, South China University of Technology, Sep. 2009 - Jul. 2013
Experience
Machine Learning Intern, Nuro, Jun 2021 - Sep 2021
Software Engineer Intern, Facebook, Jun 2015 - Sep 2015
Research Assistant, Sep 2019 - Jul 2022
Teaching Assistant, Sep 2016 - Jul 2019
Teaching
Teaching Assistant, CS214-Systems Programming, Spring 2019
Teaching Assistant, CS314-Principal of Programming Languages, Fall 2018
Teaching Assistant, CS440-Introduction to Artificial Intelligence, Spring 2018
Teaching Assistant, CS344-Design and Analysis of Computer Algorithms, Fall 2017
Teaching Assistant, CS419-Computer Security, Spring 2017
Teaching Assistant, CS344-Design and Analysis of Computer Algorithms, Fall 2016