OCALM: Object-Centric Assessment with Language Models

Kaufmann, Timo ; Blüml, Jannis; Wüst, Antonia; Delfosse, Quentin; Kersting, Kristian und Hüllermeier, Eyke (August 2024): OCALM: Object-Centric Assessment with Language Models. Reinforcement Learning Conference (RLC 2024) Workshop on Reinforcement Learning Beyond Rewards (RLBRew), Amherst, MA, USA, 9. August 2024.

Abstract

Properly defining a reward signal to efficiently train a reinforcement learning (RL) agent is a challenging task. Designing balanced objective functions from which a desired behavior can emerge requires expert knowledge, especially for complex environments. Learning rewards from human feedback or using large language models (LLMs) to directly provide rewards are promising alternatives, allowing non-experts to specify goals for the agent. However, black-box reward models make it difficult to debug the reward. In this work, we propose Object-Centric Assessment with Language Models (OCALM) to derive inherently interpretable reward functions for RL agents from natural language task descriptions. OCALM uses the extensive world-knowledge of LLMs while leveraging the object-centric nature common to many environments to derive reward functions focused on relational concepts, providing RL agents with the ability to derive policies from task descriptions.

• Dokumententyp: Konferenzbeitrag (Paper)
• Fakultät: Mathematik, Informatik und Statistik > Informatik > Künstliche Intelligenz und Maschinelles Lernen
• Themengebiete: 000 Informatik, Informationswissenschaft, allgemeine Werke > 004 Informatik
• Sprache: Englisch
• DFG: Gefördert durch die Deutsche Forschungsgemeinschaft (DFG) - SPP 2422