OCALM: Object-Centric Assessment with Language Models
This addresses the problem of reward specification for non-experts in complex RL environments, though it appears incremental by building on existing LLM and object-centric methods.
The paper tackles the challenge of designing interpretable reward functions for reinforcement learning agents by proposing OCALM, which derives such functions from natural language task descriptions using object-centric concepts, enabling agents to learn policies directly from descriptions.
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.