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

15citations
arXiv:2405.13861
15
citations
#1129
in ICLR 2025
of 3827 papers
4
Top Authors
6
Data Points

Abstract

Traditionally, reinforcement learning (RL) agents learn to solve new tasks by updating their neural network parameters through interactions with the task environment. However, recent works demonstrate that some RL agents, after certain pretraining procedures, can learn to solve unseen new tasks without parameter updates, a phenomenon known as in-context reinforcement learning (ICRL). The empirical success of ICRL is widely attributed to the hypothesis that the forward pass of the pretrained agent neural network implements an RL algorithm. In this paper, we support this hypothesis by showing, both empirically and theoretically, that when a transformer is trained for policy evaluation tasks, it can discover and learn to implement temporal difference learning in its forward pass.

Citation History

Jan 26, 2026
14
Feb 1, 2026
14
Feb 6, 2026
15+1
Feb 13, 2026
15
Feb 13, 2026
15
Feb 13, 2026
15