elsciRL: Integrating Language Solutions into Reinforcement Learning Problem Settings

2025/07/11 by Osborne, Philip, Carvalho, Danilo S., Freitas, André
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #I.2.1 #I.2.11 #I.2.5 #I.2.7

paper · doi:10.48550/arxiv.2507.08705

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 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.

Citations

• The Llama 3 Herd of Models
• Self-Refine: Iterative Refinement with Self-Feedback
• A Survey of Text Games for Reinforcement Learning informed by Natural Language
• Deep Reinforcement Learning at the Edge of the Statistical Precipice
• MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers
• MushroomRL: Simplifying Reinforcement Learning Research
• Hierarchical Decision Making by Generating and Following Natural Language Instructions
• Hierarchical and Interpretable Skill Acquisition in Multi-task Reinforcement Learning
• A Deep Hierarchical Approach to Lifelong Learning in Minecraft
• Playing Atari with Deep Reinforcement Learning
• Gymnasium: A Standard Interface for Reinforcement Learning Environments

Related

• Words as Beacons: Guiding RL Agents with High-Level Language Prompts
• PARL: Prompt-based Agents for Reinforcement Learning
• A Survey of Reinforcement Learning Informed by Natural Language
• Using Large Language Models to Automate and Expedite Reinforcement Learning with Reward Machine
• Synthesizing Programmatic Reinforcement Learning Policies with Large Language Model Guided Search