A Survey of In-Context Reinforcement Learning

Amir Moeini, Jiuqi Wang, Jacob Beck, Ethan Blaser, Shimon Whiteson +2 more
2/11/2025
cs.LG

No confident code implementation found for this paper.

Abstract

Reinforcement learning (RL) agents typically optimize their policies by performing expensive backward passes to update their network parameters. However, some agents can solve new tasks without updating any parameters by simply conditioning on additional context such as their action-observation histories. This paper surveys work on such behavior, known as in-context reinforcement learning.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Towards Provable Emergence of In-Context Reinforcement Learning

89% match2025

Safe In-Context Reinforcement Learning

87% match2025

In-Context Reinforcement Learning via Communicative World Models

86% match2025

Transformers Can Learn Temporal Difference Methods for In-Context Reinforcement Learning

86% match2024

Towards Monotonic Improvement in In-Context Reinforcement Learning

86% match2025

Online Reinforcement Learning in Non-Stationary Context-Driven Environments

84% match1 repo102023

Cite this paper

@article{moeini2025survey,
  title  = {A Survey of In-Context Reinforcement Learning},
  author = {Amir Moeini and Jiuqi Wang and Jacob Beck and Ethan Blaser and Shimon Whiteson and Rohan Chandra and Shangtong Zhang},
  year   = {2025},
  eprint = {2502.07978},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2502.07978v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2502.07978.svg)](https://codeofpaper.com/paper/2502.07978)

Discussion