DeLF: Designing Learning Environments with Foundation Models
This addresses the problem of making RL more accessible for practitioners by automating environment design, though it appears incremental as it builds on existing foundation models.
The paper tackles the difficulty of applying reinforcement learning (RL) in practice by introducing DeLF, a method that uses large language models to design RL environment components like observation and action spaces, and demonstrates it can generate executable environment codes for four different learning scenarios.
Reinforcement learning (RL) offers a capable and intuitive structure for the fundamental sequential decision-making problem. Despite impressive breakthroughs, it can still be difficult to employ RL in practice in many simple applications. In this paper, we try to address this issue by introducing a method for designing the components of the RL environment for a given, user-intended application. We provide an initial formalization for the problem of RL component design, that concentrates on designing a good representation for observation and action space. We propose a method named DeLF: Designing Learning Environments with Foundation Models, that employs large language models to design and codify the user's intended learning scenario. By testing our method on four different learning environments, we demonstrate that DeLF can obtain executable environment codes for the corresponding RL problems.