Discovering hidden structure in factored MDPs

AbstractMarkov Decision Processes (MDPs) describe a wide variety of planning scenarios ranging from military operations planning to controlling a Mars rover. However, todayʼs solution techniques scale poorly, limiting MDPsʼ practical applicability. In this work, we propose algorithms that automatically discover and exploit the hidden structure of factored MDPs. Doing so helps solve MDPs faster and with less memory than state-of-the-art techniques.Our algorithms discover two complementary state abstractions — basis functions and nogoods. A basis function is a conjunction of literals; if the conjunction holds true in a state, this guarantees the existence of at least one trajectory to the goal. Conversely, a nogood is a conjunction whose presence implies the non-existence of any such trajectory, meaning the state is a dead end. We compute basis functions by regressing goal descriptions through a determinized version of the MDP. Nogoods are constructed with a novel machine learning algorithm that uses basis functions as training data.Our state abstractions can be leveraged in several ways. We describe three diverse approaches — GOTH, a heuristic function for use in heuristic search algorithms such as RTDP; ReTrASE, an MDP solver that performs modified Bellman backups on basis functions instead of states; and SixthSense, a method to quickly detect dead-end states. In essence, our work integrates ideas from deterministic planning and basis function-based approximation, leading to methods that outperform existing approaches by a wide margin