Reinforcement Learning Based Temporal Logic Control with Maximum Probabilistic Satisfaction

1 code implementation • 14 Oct 2020 • Mingyu Cai, Shaoping Xiao, Baoluo Li, Zhiliang Li, Zhen Kan

This paper presents a model-free reinforcement learning (RL) algorithm to synthesize a control policy that maximizes the satisfaction probability of linear temporal logic (LTL) specifications.

Motion Planning reinforcement-learning +1