Adaptive Reward Design in Reinforcement Learning: A Taxonomy and Survey

摘要

Adaptive Reward Design (ARD) is becoming a fundamental component for Reinforcement Learning (RL) agents, as they are deployed in increasingly complex settings where a single static reward across all phases of learning is rarely sufficient. Yet, ARD is rarely studied as a coherent topic: Relevant ideas are dispersed across reward shaping, curriculum learning, intrinsic motivation, non-stationary objectives, and preference- or feedback-based learning, which obscures conceptual connections and complicates method selection. This survey provides a unified view of ARD in RL by introducing a taxonomy, organized by the primary driver of the reward variation. The taxonomy distinguishes external-feedback-driven reward updates from reward adaptations driven by endogenous within-run signals and those conditioned on exogenous context signals. Using explicit assignment rules, we place work published between 2010 and 2025 within this taxonomy. By synthesizing typical RL settings and domains at the driver level, we simplify the method selection in ARD. Further, we describe the evolution and current trends of ARD and conclude by outlining promising future research directions.