Safe Exploration in Markov Decision Processes

TL;DR

This paper introduces a safe exploration framework for Markov decision processes that avoids the impractical ergodicity assumption, providing an efficient algorithm for safe, yet exploratory, policies with demonstrated effectiveness on complex tasks.

Contribution

It formulates safety via ergodicity constraints, proves NP-hardness of safe policy restriction, and proposes an efficient exploration algorithm compatible with existing methods.

Findings

Our method outperforms classical exploration techniques in experiments.

The proposed approach ensures safety while maintaining effective exploration.

Application to Martian terrain exploration demonstrates practical utility.

Abstract

In environments with uncertain dynamics exploration is necessary to learn how to perform well. Existing reinforcement learning algorithms provide strong exploration guarantees, but they tend to rely on an ergodicity assumption. The essence of ergodicity is that any state is eventually reachable from any other state by following a suitable policy. This assumption allows for exploration algorithms that operate by simply favoring states that have rarely been visited before. For most physical systems this assumption is impractical as the systems would break before any reasonable exploration has taken place, i.e., most physical systems don't satisfy the ergodicity assumption. In this paper we address the need for safe exploration methods in Markov decision processes. We first propose a general formulation of safety through ergodicity. We show that imposing safety by restricting attention to the resulting set of guaranteed safe policies is NP-hard. We then present an efficient algorithm for guaranteed safe, but potentially suboptimal, exploration. At the core is an optimization formulation in which the constraints restrict attention to a subset of the guaranteed safe policies and the objective favors exploration policies. Our framework is compatible with the majority of previously proposed exploration methods, which rely on an exploration bonus. Our experiments, which include a Martian terrain exploration problem, show that our method is able to explore better than classical exploration methods.