{"slug": "codrift-compositional-drifting-for-offline-reinforcement-learning", "title": "CoDrift: Compositional Drifting for Offline Reinforcement Learning", "summary": "Researchers propose CoDrift, a compositional framework for offline reinforcement learning that combines three objective-level fields into a unified policy field, achieving the best average rank across 73 tasks from OGBench and D4RL in both offline and offline-to-online settings.", "body_md": "arXiv:2608.23939v1 Announce Type: new\nAbstract: 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-level fields into a unified policy field. The conditional field preserves state-dependent behavioral structure, while the marginal field pools actions across states to provide a more stable generative signal in the single-positive-sample regime of continuous-control offline RL. The value field moves generated actions toward higher-value regions. The composed field is absorbed into a stochastic generator that produces an action with a single forward pass at deployment. We evaluate CoDrift on 73 tasks from OGBench and D4RL in both offline and offline-to-online settings. CoDrift compares favorably with state-of-the-art methods and achieves the best average rank in both settings.", "url": "https://wpnews.pro/news/codrift-compositional-drifting-for-offline-reinforcement-learning", "canonical_source": "https://www.machinebrief.com/news/codrift-compositional-drifting-for-offline-reinforcement-lea-ha63", "published_at": "2026-08-26 04:00:00+00:00", "updated_at": "2026-08-26 04:44:08.688075+00:00", "lang": "en", "topics": ["machine-learning", "artificial-intelligence"], "entities": ["CoDrift", "OGBench", "D4RL"], "alternates": {"html": "https://wpnews.pro/news/codrift-compositional-drifting-for-offline-reinforcement-learning", "markdown": "https://wpnews.pro/news/codrift-compositional-drifting-for-offline-reinforcement-learning.md", "text": "https://wpnews.pro/news/codrift-compositional-drifting-for-offline-reinforcement-learning.txt", "jsonld": "https://wpnews.pro/news/codrift-compositional-drifting-for-offline-reinforcement-learning.jsonld"}}