5 papers
Exact Model-Free Policy Iteration for Co-safe LTL Planning
Zetong Xuan, Yu Wang
This work studies model-free reinforcement learning for co-safe linear temporal logic (sc-LTL) objectives in finite Markov decision processes, which can be reduced to maximal reach…
Optimal Constrained sc-LTL Planning in MDPs via Switching Policies
Zetong Xuan, Yu Wang
We study the synthesis of optimal policies for planning problems on Markov decision processes with both objectives and safety constraints specified in co-safe linear temporal logic…
Control Synthesis in Partially Observable Environments for Complex Perception-Related Objectives
Zetong Xuan, Yu Wang
Perception-related tasks often arise in autonomous systems operating under partial observability. This work studies the problem of synthesizing optimal policies for complex percept…
Convergence Guarantee of Dynamic Programming for LTL Surrogate Reward
Zetong Xuan, Yu Wang
Linear Temporal Logic (LTL) is a formal way of specifying complex objectives for planning problems modeled as Markov Decision Processes (MDPs). The planning problem aims to find th…
On the Uniqueness of Solution for the Bellman Equation of LTL Objectives
Zetong Xuan, Alper Kamil Bozkurt, Miroslav Pajic +1
Surrogate rewards for linear temporal logic (LTL) objectives are commonly utilized in planning problems for LTL objectives. In a widely-adopted surrogate reward approach, two disco…