Create and explore imaginative 3D worlds with our new product Dreamfield (opens in a new tab)
Papers
Topics
Authors
Recent
Search
2000 character limit reached

DYSTIL: Dynamic Strategy Induction with Large Language Models for Reinforcement Learning

Published 6 May 2025 in cs.LG | (2505.03209v1)

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 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 strategies during training. We test DYSTIL over challenging RL environments from Minigrid and BabyAI, and empirically demonstrate that DYSTIL significantly outperforms state-of-the-art baseline methods by 17.75% in average success rate while also enjoying higher sample efficiency during the learning process.

Summary

No one has generated a summary of this paper yet.

Paper to Video (Beta)

No one has generated a video about this paper yet.

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Continue Learning

We haven't generated follow-up questions for this paper yet.

Tweets

Sign up for free to view the 1 tweet with 2 likes about this paper.