Reinforcement Learning and Control
Reinforcement learning to learn high performance intelligent decision and control policies automatically from interacting with the environments. Control theory provides a principled way to design and analyze the safety and stability of closed loop controlled dynamic systems. I'm interested in borrowing ideas from both areas, and develop the theories and algorithms for learning control policies for agents that satisfy important properties including: (1) Safety: The agent should not violate the safety constraints; (2) Stability: The learning process and the final controlled system should be stable; (3) Efficiency: The learning process should be efficient.
- B. Peng, Y. Mu, Y. Guan, SE. Li, Y. Yin, J. Chen, "Model-Based Actor-Critic with Chance Constraint for Stochastic System", IEEE Conference on Decision and Control (CDC), 2021.
- H. Ma, J. Chen, SE. Li, X. Zhang, S. Zheng, J. Chen, "Model-based Constrained Reinforcement Learning using Generalized Control Barrier Function", IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2021.
- B. Peng, Y. Mu, J. Duan, Y. Guan, SE. Li, J. Chen, "Separated Proportional-Integral Lagrangian for Chance Constrained Reinforcement Learning", IEEE Intelligent Vehicle Symposium (IV), 2021.
- J. Li, L. Sun, J. Chen, M. Tomizuka, W. Zhan, "A Safe Hierarchical Planning Framework for Complex Driving Scenarios based on Reinforcement Learning", International Conference on Robotics and Automation (ICRA), 2021.
- J. Chen, B. Yuan, and M. Tomizuka, “Model-free Deep Reinforcement Learning for Urban Autonomous Driving”, IEEE Intelligent Transportation Systems Conference (ITSC), 2019.
- J. Chen, B. Yuan, and M. Tomizuka, “Deep Imitation Learning for Autonomous Driving in Generic Urban Scenarios with Enhanced Safety”, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2019.
- J. Chen, W. Zhan, and M. Tomizuka, “Autonomous Driving Motion Planning with Constrained Iterative LQR”, IEEE Transactions on Intelligent Vehicles (T-IV), 2019.
- J. Chen, Z. Wang, and M. Tomizuka, “Deep Hierarchical Reinforcement Learning for Autonomous Driving with Distinct Behaviors”, IEEE Intelligent Vehicle Symposium (IV), 2018.
- J. Chen, W. Zhan, and M. Tomizuka, “Constrained Iterative LQR for On-Road Autonomous Driving Motion Planning”, IEEE Intelligent Transportation Systems Conference (ITSC), 2017.
- C. Liu, J. Chen, T-D. Nguyen and M. Tomizuka, “The Robustly-Safe Automated Driving System for Enhanced Active Safety”, SAE World Congress, SAE Technical Paper 2017-01-1406, 2017.