2 papers
cs.RO2026
LLM-Guided Task- and Affordance-Level Exploration in Reinforcement Learning
Jelle Luijkx, Runyu Ma, Zlatan AjanoviÄ +1
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…
cs.RO2025
ExploRLLM: Guiding Exploration in Reinforcement Learning with Large Language Models
Runyu Ma, Jelle Luijkx, Zlatan Ajanovic +1
In robot manipulation, Reinforcement Learning (RL) often suffers from low sample efficiency and uncertain convergence, especially in large observation and action spaces. Foundation…