Tractable Reinforcement Learning of Signal Temporal Logic Objectives
This addresses a bottleneck in applying reinforcement learning to real-world robotic tasks with time-bound specifications, offering a more tractable approach.
The paper tackled the computational intractability of reinforcement learning for signal temporal logic specifications due to exponential state-space growth from history requirements, and proposed a compact augmented state-space representation with an approximate solution, showing performance bounds and comparisons via simulations.
Signal temporal logic (STL) is an expressive language to specify time-bound real-world robotic tasks and safety specifications. Recently, there has been an interest in learning optimal policies to satisfy STL specifications via reinforcement learning (RL). Learning to satisfy STL specifications often needs a sufficient length of state history to compute reward and the next action. The need for history results in exponential state-space growth for the learning problem. Thus the learning problem becomes computationally intractable for most real-world applications. In this paper, we propose a compact means to capture state history in a new augmented state-space representation. An approximation to the objective (maximizing probability of satisfaction) is proposed and solved for in the new augmented state-space. We show the performance bound of the approximate solution and compare it with the solution of an existing technique via simulations.