We study the problem of policy optimization (PO) with linear temporal logic (LTL) constraints. The language of LTL allows flexible description of tasks that may be unnatural to encode as a scalar cost function. We consider LTL-constrained PO as a systematic framework, decoupling task specification from policy selection, and as an alternative to the standard of cost shaping. With access to a generative model, we develop a model-based approach that enjoys a sample complexity analysis for guaranteeing both task satisfaction and cost optimality (through a reduction to a reachability problem). Empirically, our algorithm can achieve strong performance even in low-sample regimes.
@article{arxiv.2206.09546,
title = {Policy Optimization with Linear Temporal Logic Constraints},
author = {Cameron Voloshin and Hoang M. Le and Swarat Chaudhuri and Yisong Yue},
journal= {arXiv preprint arXiv:2206.09546},
year = {2022}
}