SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning

ICRA 2024

Featured on Hugging Face Daily Paper
*Equal Contribution; 1Department of EECS, University of California, Berkeley; 2Department of Computer Science, University of Washington; 3Department of Computer Science, Stanford University; 4Intrinsic Innovation LLC
SERL is a ready-to-use software suite for robotic RL, featuring sample efficient off-policy algorithms, various reward specification methods, and advanced controller for popular robots. It includes example tasks such as PCB assembly, cable routing, and reset-freeobject relocation. Remarkably, it trains policies in just 25 to 50 minutes, outperforming previous benchmarks with high success rates and robustness.

Uncut Training Process

Zero-shot Robustness to Perturbations and Distractors

PCB Component Insertion

Cable Routing

Object Relocation


                title={SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning},
                author={Jianlan Luo and Zheyuan Hu and Charles Xu and You Liang Tan and Jacob Berg and Archit Sharma and Stefan Schaal and Chelsea Finn and Abhishek Gupta and Sergey Levine},