Controller synthesis for linear temporal logic and steady-state specifications

Abstract

The problem of deriving decision-making policies, subject to some formal specification of behavior, has been well-studied in the control synthesis, reinforcement learning, and planning communities. Such problems are typically framed in the context of a non-deterministic decision process, the non-determinism of which is optimally resolved by the computed policy. In this paper, we explore the derivation of such policies in Markov decision processes (MDPs) subject to two types of formal specifications. First, we consider steady-state specifications that reason about the infinite-frequency behavior of the resulting agent. This behavior corresponds to the frequency with which an agent visits each state as it follows its decision-making policy indefinitely. Second, we examine the infinite-trace behavior of the agent by imposing Linear Temporal Logic (LTL) constraints on the behavior induced by the resulting policy. We present an algorithm to find a deterministic policy satisfying LTL and steady-state constraints by characterizing the solutions as an integer linear program (ILP) and experimentally evaluate our approach. In our experimental results section, we evaluate the proposed ILP using MDPs with stochastic and deterministic transitions.