Adaptive Reward Design in Reinforcement Learning: A Taxonomy and Survey

Creators: Baybas, Raphaela and D'Eramo, Carlo and Brune, Philipp
Title: Adaptive Reward Design in Reinforcement Learning: A Taxonomy and Survey
Item Type: Conference or Workshop Item
Event Title: (Proceedings of the) 35th International Joint Conference on Artificial Intelligence
Event Location: Bremen, Germany
Event Dates: August, 15-21, 2026
Projects: TTZ-GZ
Page Range: pp. 7768-7776
Additional Information: Open Access
Date: 15 August 2026
Divisions: Informationsmanagement
Abstract (ENG): 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.
Forthcoming: No
Main areas or research: Transformationmanagement
Language: English
Uncontrolled Keywords: Machine Learning ; Reinforcement learning
Link eMedia: Download
Citation:

Baybas, Raphaela and D'Eramo, Carlo and Brune, Philipp (2026) Adaptive Reward Design in Reinforcement Learning: A Taxonomy and Survey. In: (Proceedings of the) 35th International Joint Conference on Artificial Intelligence, August, 15-21, 2026, Bremen, Germany, pp. 7768-7776. (IJCAI). ISBN 9781956792096

Actions for admins (login required)

View Item in edit mode (academic staff only) View Item in edit mode (academic staff only)