cs.LGNov 15, 2026

RIFT: Reward Improvement Field Transfer for Cross-Domain Offline RL

Authors: Jinhee Won, Mardavij Roozbehani, Munther Dahleh

Organizations: Massachusetts Institute of Technology, Cambridge, MA, USA

Abstract

Learning from limited target data is a central challenge in cross-domain offline reinforcement learning. Abundant source data can help, but dynamics differences can make direct transition reuse unreliable. We propose Reward Improvement Field Transfer (RIFT), which instead learns how low- and high-reward source transitions differ. RIFT encodes source and target transitions in a shared latent space, pairs low- and high-reward source transitions using optimal transport, and fits an affine field to their displacements. It applies this field to low-reward target anchors and decodes the results to augment the target dataset. The approach builds on the hypothesis that related domains can share useful low-to-high reward structure despite different dynamics. We bound synthesis error under shared class geometry, identify conditions favoring target anchoring over source-high transplant, and derive a conditional connection to downstream return. Experiments on dense-reward locomotion tasks under gravity, morphology, and friction shifts show improved aggregate performance over existing baselines.

Figures & tables

Appendix figures & tables13 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Target-Aligned Bellman Backup for Cross-domain Offline Reinforcement Learning

    May 21, 2026Wei Liu, Ting LongOffline RLCross-Domain Transfer Learning

  2. Bridging Dynamics Gaps via Diffusion Schrödinger Bridge for Cross-Domain Reinforcement Learning

    Feb 27, 2026Hanping Zhang, Yuhong GuoReinforcement LearningCross-Domain Transfer Learning

  3. Generative Support Realignment for Cross-Domain Offline Reinforcement Learning

    May 13, 2026Minung Kim, Jeongmo Kim, Gwanwoo Choi +1Offline RLCross-Domain Transfer Learning