AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

CoDrift: Compositional Drifting for Offline Reinforcement Learning

arXiv · AI, language, vision and robotics · article · Aug 25, 2026 · UTC

Offline reinforcement learning is intrinsically multi-objective: a policy must remain compatible with the behavioral support of a fixed dataset while preferentially selecting high-value actions. We recast these objectives in a common form by viewing each as an action-space motion field that specifies how generated actions should move. This perspective enables heterogeneous learning objectives to be combined directly through field composition. Inspired by drifting models, we propose CoDrift, a compositional framework for one-step generative policy learning. CoDrift combines three objective-leve

Read original source ↗ Open in workspace

recordType
paper
region
Global

Evidence & attribution

First collected: 2026-09-21T10:22:00.206Z. This is not the publication date.