Lexicographic Multi-Objective Reinforcement Learning
This work addresses the problem of handling prioritized objectives in reinforcement learning for researchers and practitioners, offering a novel approach but with incremental contributions to existing multi-objective methods.
The paper tackles lexicographic multi-objective reinforcement learning problems, where policies must optimize multiple reward signals in a prioritized order, and introduces a family of algorithms that converge to lexicographically optimal policies, demonstrating practical applicability with empirical evaluations.
In this work we introduce reinforcement learning techniques for solving lexicographic multi-objective problems. These are problems that involve multiple reward signals, and where the goal is to learn a policy that maximises the first reward signal, and subject to this constraint also maximises the second reward signal, and so on. We present a family of both action-value and policy gradient algorithms that can be used to solve such problems, and prove that they converge to policies that are lexicographically optimal. We evaluate the scalability and performance of these algorithms empirically, demonstrating their practical applicability. As a more specific application, we show how our algorithms can be used to impose safety constraints on the behaviour of an agent, and compare their performance in this context with that of other constrained reinforcement learning algorithms.