Lane-change Behavior Learning of Self-driving Cars
Published:
Applying SOTA imitation learning and meta-learning algorithms for driving bahavior learning of autonomous vehicles.
Posts by Collection
portfolio
Pedestrian Interaction Learning for Autonomous Vehicles
Published:
Applying SOTA imitation learning and reinforcement algorithms for V2X with simulation on CARLA.
DeepFreight
Published:
An intelligent freight delivery scheduling system built with the SOTA MARL algorithms and an optimization solver.
DeepBridge
Published:
A Poker AI for Bridge based on self-playing with SOTA MARL algorithms and heuristic search.
A Simple Tutorial of AI
Published:
Tutorials on commonly-used basic AI techniques.
Two-Phase Simplex Method
Published:
An implementation of the two-phase simplex method as an LP solver.
Common Numeric Optimization Algorithms
Published:
Justified MATLAB implementations of common numeric optimization algorithms for nonlinear and convex optmization.
Scalable Option Discovery based on Spectral Clustering
Published:
An option discovery algorithm based on spectral clustering which can be used for continuous control tasks.
Scalable Multi-agent Covering Option Discovery based on Kronecker Graphs
Published:
An option discovery algorithm for multi-agent reinforcement learning, including the tabular version and scalable NN-based version.
ODPP
Published:
A novel Unsupervised Option Discovery algorithm based on Determinant Point Process.
Hierarchical AIRL
Published:
A novel Hierarchical Imitation Learning algorithm based on AIRL.
Multi-task Hierarchical AIRL
Published:
A SOTA Multi-task Hierarchical Imitation Learning algorithm with broad applications, such as robotics.
Hierarchical Deep CFR
Published:
A skill-based Poker AI && A hierarchical strategy learner for Imperfect Information Games.
publications
Supervised Learning for Semantic Segmentation of 3D LiDAR Data
Published in IEEE Intelligent Vehicles Symposium (IV), 2019
Jilin Mei, Jiayu Chen, Wen Yao, Xijun Zhao, and Huijing Zhao
Download here
DeepFreight: A Model-free Deepreinforcement-learning-based Algorithm for Multi-transfer Freight Delivery
Published in Proceedings of the International Conference on Automated Planning and Scheduling (ICAPS), 2021
Jiayu Chen, Abhishek K. Umrawal, Tian Lan, and Vaneet Aggarwal
Download here
Decision Making for Autonomous Driving via Augmented Adversarial Inverse Reinforcement Learning
Published in IEEE International Conference on Robotics and Automation (ICRA), 2021
Pin Wang, Dapeng Liu, Jiayu Chen, Hanhan Li, and Ching-Yao Chan
Download here
Multi-agent Deep Covering Option Discovery
Published in ICML Reinforcement Learning for Real Life Workshop, 2021
Jiayu Chen, Marina Wagdy Wadea Haliem, Tian Lan, and Vaneet Aggarwal
Download here
Multi-Agent Covering Option Discovery Based on Kronecker Product of Factor Graphs
Published in IEEE Transactions on Artificial Intelligence, 2022
Jiayu Chen, Jingdi Chen, Tian Lan, Vaneet Aggarwal
Download here
Scalable Multi-agent Option Discovery based on Kronecker Graphs
Published in Proceedings of the 36th Conference on Neural Information Processing Systems (NeurIPS), 2022
Jiayu Chen, Jingdi Chen, Tian Lan, Aggarwal Vaneet
Download here
Hierarchical Deep Counterfactual Regret Minimization
Published in arXiv preprint arXiv:2305.17327, 2023
Jiayu Chen, Tian Lan, and Vaneet Aggarwal
Download here
Option-Aware Adversarial Inverse Reinforcement Learning for Robotic Control
Published in IEEE International Conference on Robotics and Automation (ICRA), 2023
Jiayu Chen, Tian Lan, and Vaneet Aggarwal
Download here
Learning-based Two-tiered Online Optimization of Region-wide Datacenter Resource Allocation
Published in arXiv preprint arXiv:2306.17054, 2023
Chang-Lin Chen, Hanhan Zhou, Jiayu Chen, Mohammad Pedramfar, Vaneet Aggarwal, Tian Lan, Zheqing Zhu, Chi Zhou, Tim Gasser, Pol Mauri Ruiz, Vijay Menon, Neeraj Kumar, and Hongbo Dong
Download here
Multi-task Hierarchical Adversarial Inverse Reinforcement Learning
Published in Proceedings of the 40th International Conference on Machine Learning (ICML), 2023
Jiayu Chen, Dipesh Tamboli, Tian Lan, and Vaneet Aggarwal
Download here
Hierarchical Adversarial Inverse Reinforcement Learning
Published in IEEE Transactions on Neural Networks and Learning Systems, 2023
Jiayu Chen, Tian Lan, and Vaneet Aggarwal
Download here
A Unified Algorithm Framework for Unsupervised Discovery of Skills based on Determinantal Point Process
Published in Proceedings of the 37th Conference on Neural Information Processing Systems (NeurIPS), 2023
Jiayu Chen, Vaneet Aggarwal, and Tian Lan
Download here
talks
Multi-agent Deep Covering Option Discovery
Published:
This is a presentation of my accepted paper – Multi-agent Deep Covering Option Discovery, on the ICML Reinforcement Learning for Real Life Workshop, which is a great opportunity for meeting outstanding researchers from the same comunity. The conference is held online due to the COVID-19.
DeepFreight: A Model-free Deepreinforcement- learning-based Algorithm for Multi-transfer Freight Delivery
Published:
This is a presentation of my accepted paper – DeepFreight: A Model-free Deepreinforcement-learning-based Algorithm for Multi-transfer Freight Delivery, on ICAPS, which is a top conference on learning and automated planning. The conference is held online due to the COVID-19.
Multi-agent Covering Option Discovery through Kronecker Product of Factor Graphs
Published:
This is a presentation of my accepted paper – Multi-agent Covering Option Discovery through Kronecker Product of Factor Graphs, on AAMAS, which is a top conference on multi-agent learning system. The conference is held online due to the COVID-19.
Scalable Multi-agent Option Discovery based on Kronecker Graphs
Published:
This is a presentation of my accepted paper – Scalable Multi-agent Option Discovery based on Kronecker Graphs, on NeurIPS, which is one of the best conferences on machine learning and artifical intelligence. This is also my first in-person conference. It’s a great honor and pleasure for me to meet with great ML/AI researchers from all over the world.
Option-Aware Adversarial Inverse Reinforcement Learning for Robotic Control
Published:
This is a presentation of my accepted paper – Option-Aware Adversarial Inverse Reinforcement Learning for Robotic Control, on ICRA, which is one of the best conferences on automatic robotics.
teaching
Research experience at Peking University
Research, School of EECS, Peking University, 2018
I have worked as a research assistant on autonomous driving techniques (e.g., semantic perception, interactive behavior learning) from 2018/09 to 2020/07, under the supervision of Prof. Huijing Zhao, and completed my Bachelor thesis there.
Research experience at University of California, Berkeley
Research, School of EECS, University of California, Berkeley, 2019
I have worked as a research assistant on driving behavior learning of autonomous vehicles from 2019/09 to 2020/01, under the supervision of Prof. Ching-Yao Chan.
Research experience at Purdue University
Research, School of Industrial Engineering, Purdue University, 2020
I have worked with Prof. Vaneet Aggarwal and Prof. Tian Lan as a Ph.D. student/candidate from 2022/07 till now. My research focuses on Reinforcement Learning algorithm design and applications.
Teaching experience at Purdue University
Undergraduate/Graduate course, School of Industrial Engineering, Purdue University, 2021
I have been the teaching assistant for IE 23000 - Probability And Statistics In Engineering for five straight semesters from 2021 Fall to 2023 Fall. I also worked as the teaching assistant for IE 53800 - Nonlinear Optimization Algorithms And Models in 2023 Spring.