Generative Support Realignment for Cross-Domain Offline Reinforcement Learning

arXiv:2605.13054 · cs.LG, cs.AI · Submitted 2026-05-13 · Read on arXiv

cs.LG, cs.AI

Submitted: 2026-05-13

Updated: 2026-09-29

Code: https://github.com/ikostrikov/implicit_q_learning

Terminology

• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Target-aligned Coverage Expansion — 1× in this paper

Sources

• D4RL: Datasets for Deep Data-Driven Reinforcement Learning
• Evaluating Reinforcement Learning Algorithms in Observational Health Settings
• Auto-Encoding Variational Bayes
• Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems
• DiffStitch: Boosting Offline Reinforcement Learning with Diffusion-based Trajectory Stitching
• Generative Trajectory Stitching through Diffusion Composition
• Cross-Domain Policy Adaptation by Capturing Representation Mismatch
• Dual-Robust Cross-Domain Offline Reinforcement Learning Against Dynamics Shifts
• Score-Based Generative Modeling through Stochastic Differential Equations
• Contrastive Representation for Data Filtering in Cross-Domain Offline Reinforcement Learning
• Behavior Regularized Offline Reinforcement Learning

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks