RLBench

RLBench is a benchmark dataset that contains a variety of robotic manipulation tasks used to evaluate the performance of reinforcement learning and imitation learning algorithms in robotics.

Papers using RLBench (6)

ViReSkill: Vision-Grounded Replanning with Skill Memory for LLM-Based Planning in Lifelong Robot Learning2025Actor-Critic for Continuous Action Chunks: A Reinforcement Learning Framework for Long-Horizon Robotic Manipulation with Sparse Reward2025Learning from Suboptimal Data in Continuous Control via Auto-Regressive Soft Q-Network2025Coarse-to-fine Q-Network with Action Sequence for Data-Efficient Reinforcement Learning2024RLingua: Improving Reinforcement Learning Sample Efficiency in Robotic Manipulations With Large Language Models2024Continuous Control with Coarse-to-fine Reinforcement Learning2024