DYSTIL: Dynamic Strategy Induction With Large Language Models For Reinforcement Learning

Abstract

Reinforcement learning from expert demonstrations has long remained a challenging research problem, and existing state-of-the-art methods using behavioral cloning plus further RL training often suffer from poor generalization, low sample efficiency, and poor model interpretability. Inspired by the strong reasoning abilities of large language models (LLMs), we propose a novel strategy-based reinforcement learning framework integrated with LLMs called DYnamic STrategy Induction with Llms for reinforcement learning (DYSTIL) to overcome these limitations. DYSTIL dynamically queries a strategy-generating LLM to induce textual strategies based on advantage estimations and expert demonstrations, and gradually internalizes induced strategies into the RL agent through policy optimization to improve its performance through boosting policy generalization and enhancing sample efficiency. It also provides a direct textual channel to observe and interpret the evolution of the policy's underlying str

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keywang2025dystil

Related papers

• Guiding Reinforcement Learning Using Uncertainty-aware Large Language Models (2024)0.00
• Zero-shot Model-based Reinforcement Learning Using Large Language Models (2024)0.00
• Think In Games: Learning To Reason In Games Via Reinforcement Learning With Large Language Models (2025)0.00
• Language Agents With Reinforcement Learning For Strategic Play In The Werewolf Game (2023)0.00
• Llm-explorer: A Plug-in Reinforcement Learning Policy Exploration Enhancement Driven By Large Language Models (2025)0.00
• Reinforcement Learning Environment With Llm-controlled Adversary In D&D 5th Edition Combat (2025)0.00
• From Laws To Motivation: Guiding Exploration Through Law-based Reasoning And Rewards (2024)0.00
• Mental Modeling Of Reinforcement Learning Agents By Language Models (2024)0.00