Papers
arxiv:2509.16615

LLM-Guided Task- and Affordance-Level Exploration in Reinforcement Learning

Published on Sep 20
Authors:
,
,

Abstract

LLM-TALE integrates LLM planning into RL to enhance sample efficiency and success rates in robotic manipulation tasks by correcting suboptimal plans and exploring multimodal affordances.

AI-generated summary

Reinforcement learning (RL) is a promising approach for robotic manipulation, but it can suffer from low sample efficiency and requires extensive exploration of large state-action spaces. Recent methods leverage the commonsense knowledge and reasoning abilities of large language models (LLMs) to guide exploration toward more meaningful states. However, LLMs can produce plans that are semantically plausible yet physically infeasible, yielding unreliable behavior. We introduce LLM-TALE, a framework that uses LLMs' planning to directly steer RL exploration. LLM-TALE integrates planning at both the task level and the affordance level, improving learning efficiency by directing agents toward semantically meaningful actions. Unlike prior approaches that assume optimal LLM-generated plans or rewards, LLM-TALE corrects suboptimality online and explores multimodal affordance-level plans without human supervision. We evaluate LLM-TALE on pick-and-place tasks in standard RL benchmarks, observing improvements in both sample efficiency and success rates over strong baselines. Real-robot experiments indicate promising zero-shot sim-to-real transfer. Code and supplementary material are available at https://llm-tale.github.io.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2509.16615 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2509.16615 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2509.16615 in a Space README.md to link it from this page.

Collections including this paper 1