Work

A Survey of In-Context Reinforcement Learning

Year: 2025

Type: preprint

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.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2502.07978

Authors: Moeini, Amir, Wang, Jiuqi, Beck, Jacob, Blaser, Ethan, Whiteson, Shimon, Chandra, Rohan, Zhang, Shangtong

Institutions: University of Virginia, University of Oxford

Language: English

Topic: Reinforcement Learning in Robotics

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: National Science Foundation

Awards: SLES: CRASH - Challenging Reinforcement-learning based Adversarial scenarios for Safety Hardening, Graduate Research Fellowship Program (GRFP), III: Small: Moving offline learning to rank online, from theory to practice

OpenAlex ID: W4407569677

Cites:

Cited by: 7

Related to: 10