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

SERL Successful Deployments

Have you used SERL successfully? Send us your videos to jianlanluo@berkeley.edu!

Zero-shot Robustness to Perturbations and Distractors

PCB Component Insertion

Cable Routing

Object Relocation

BibTeX

          
            @misc{luo2024serl,
                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},
                year={2024},
                eprint={2401.16013},
                archivePrefix={arXiv},
                primaryClass={cs.RO}
            }