In-Distribution Imagination for Model-Based Offline Reinforcement Learning

arXiv:2609.38673 · cs.LG · Submitted 2026-09-29 · Read on arXiv

cs.LG

Submitted: 2026-09-29

Updated: 2026-09-29

Terminology

• Reinforcement Learning — 1× in this paper · explained in 4 episodes

Sources

• D4RL: Datasets for Deep Data-Driven Reinforcement Learning
• Finite Memory Belief Approximation for Optimal Control in Partially Observable Markov Decision Processes
• Robust Adversarial Policy Optimization Under Dynamics Uncertainty
• Trajectory-Regularized Stochastic Optimal Control via KL Divergence
• RoVerFly: Robust and Versatile Implicit Hybrid Control of Quadrotor-Payload Systems
• InfoNCE: Identifying the Gap Between Theory and Practice
• Representation Learning with Contrastive Predictive Coding
• Is Model Ensemble Necessary? Model-based RL via a Single Model with Lipschitz Regularized Value Function

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