The Feasibility of Constrained Reinforcement Learning Algorithms: A Tutorial Study

no code implementations • 15 Apr 2024 • Yujie Yang, Zhilong Zheng, Shengbo Eben Li, Masayoshi Tomizuka, Changliu Liu

We demonstrate our feasibility theory by visualizing different feasible regions under both MPC and RL policies in an emergency braking control task.

Model Predictive Control reinforcement-learning +1

On the Stability of Datatic Control Systems

no code implementations • 30 Jan 2024 • Yujie Yang, Zhilong Zheng, Shengbo Eben Li

This information restricts the time derivative of any unknown state to the intersection of a set of closed balls.

Feasible Policy Iteration

no code implementations • 18 Apr 2023 • Yujie Yang, Zhilong Zheng, Shengbo Eben Li, Jingliang Duan, Jingjing Liu, Xianyuan Zhan, Ya-Qin Zhang

To address this challenge, we propose an indirect safe RL framework called feasible policy iteration, which guarantees that the feasible region monotonically expands and converges to the maximum one, and the state-value function monotonically improves and converges to the optimal one.

Reinforcement Learning (RL) Safe Reinforcement Learning