Runyu Ma — accepted AI-conference papers

2026

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

Jelle Douwe Luijkx, Runyu Ma, Zlatan Ajanovic, Jens Kober

ICRA 2026poster

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 gui…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2025

ExploRLLM: Guiding Exploration in Reinforcement Learning with Large Language Models

Runyu Ma, Jelle Luijkx, Zlatan Ajanovic, Jens Kober

ICRA 2025

In robot manipulation, Reinforcement Learning (RL) often suffers from low sample efficiency and uncertain convergence, especially in large observation and action spaces. Foundation Models (FMs) offer an alternative, demonstrating promise in zero-shot and few-shot settings. However, they can be unrel

Cited by 25 Source ↗code ↗Scholar ↗