SOURCE-LINKED INTELLIGENCE

Three Steps at a Time: Learning Representations from Action Sequences in Contrastive RL

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

While self-supervised approaches to reinforcement learning have achieved strong results by learning representations of states and actions, a key open question is the time scale over which actions should be modeled. Departing from the standard formulation relying on single-step actions, we extend contrastive reinforcement learning (CRL), a prototypical self-supervised method, to operate over action chunks, and find that this results in large, pervasive gains across established offline and online benchmarks: +31.7% and +93.1% across 18 and 11 environments respectively. While action-chunking-driv

Read original source ↗ Open in workspace

recordType

paper

region

Global