Adversarial dynamic games for Markov jump systems: A policy iteration Q-learning method

2025/09/19 by Hao Shen, Jiacheng Wu, Jing Wang +2
Computer Science · Engineering · #Adaptive Dynamic Programming Control #Reinforcement Learning in Robotics #Mechanical Circulatory Support Devices

paper · doi:10.1016/j.automatica.2025.112591

Citations

• Reinforcement learning-based optimal control for Markov jump systems with completely unknown dynamics