RESEARCH PAPERYear 2024

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

Jianlan Luo; Zheyuan Hu; Charles Xu; You Liang Tan; Jacob Berg; Archit Sharma; Stefan Schaal; Chelsea Finn; Abhishek Gupta; Sergey Levine

Read paper PDF DOI Code Project page

Classification

View four quadrants

Major category: Foundational work
Quadrant: Not applicable
Architecture: Not applicable
Prediction paradigm: Not applicable
Subcategories: Action policy foundations Surveys & technical resources
Source review status: Verified from primary sources

Category review. SERL is a pre-2026 integrated foundation for practical model-free robot reinforcement learning: demonstration replay, rewards, resets and compliant control. The manuscript places it in RL post-training context; it does not supply a learned future-world backbone. Reading evidence

AT A GLANCE

Contribution

A contribution summary has not been added yet.

Abstract

An abstract has not been added yet.

Affiliations

Not listed in the collection.

BibTeX

@inproceedings{serl,
  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},
  title        = {{SERL:} {A} Software Suite for Sample-Efficient Robotic Reinforcement
                  Learning},
  booktitle    = {ICRA},
  pages        = {16961--16969},
  year         = {2024},
}

Classification

Contribution

Abstract

Affiliations

BibTeX

More in this category

Critique of World Model

Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning

Mean Flows for One-step Generative Modeling