elsciRL: Integrating Language Solutions into Reinforcement Learning Problem Settings

TL;DR

elsciRL is an open-source Python library that integrates language solutions into reinforcement learning, using LLMs to generate instructions that can enhance agent performance and facilitate rapid evaluation of language-based methods.

Contribution

The paper introduces elsciRL, a novel library that combines language models with reinforcement learning, including a GUI for instruction generation and self-completion, enabling easier application and testing.

Findings

Instructions generated by LLMs can improve RL agent performance

The library simplifies applying language solutions to RL environments

Empirical results support the effectiveness of the approach

Abstract

We present elsciRL, an open-source Python library to facilitate the application of language solutions on reinforcement learning problems. We demonstrate the potential of our software by extending the Language Adapter with Self-Completing Instruction framework defined in (Osborne, 2024) with the use of LLMs. Our approach can be re-applied to new applications with minimal setup requirements. We provide a novel GUI that allows a user to provide text input for an LLM to generate instructions which it can then self-complete. Empirical results indicate that these instructions \textit{can} improve a reinforcement learning agent's performance. Therefore, we present this work to accelerate the evaluation of language solutions on reward based environments to enable new opportunities for scientific discovery.