Convex-Hull-Neighborhood Smooth Dual Generalization: Controlling Local Correction Propagation in Offline RL

arXiv:2608.03108 · cs.LG, cs.CL · Submitted 2026-08-04 · Read on arXiv

Yi Yang, Zhennan Chen, Mingfeng Lv, Hanlei Li, Zhengsen Ruan, Lvqing Yang

cs.LG, cs.CL

Submitted: 2026-08-04

Code: https://github.com/YOUNG-fnxm/CSDG

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Reinforcement Learning — 41× in this paper · explained in 4 episodes
• Generalization — 29× in this paper · explained in 14 episodes
• Actor — 15× in this paper · explained in 3 episodes
• Fixed Point — 13× in this paper · explained in 2 episodes
• Benchmark — 8× in this paper · explained in 2 episodes
• Regularization — 7× in this paper · explained in 3 episodes
• Ablation — 6× in this paper · explained in 1 episode
• Deep Reinforcement Learning — 5× in this paper · explained in 3 episodes
• Q-learning — 5× in this paper · explained in 3 episodes
• Accuracy — 3× in this paper · explained in 1 episode
• Distribution Shift — 3× in this paper · explained in 12 episodes
• Ablation Studies — 2× in this paper · explained in 1 episode
• Adam — 2× in this paper · explained in 3 episodes
• EMMA — 2× in this paper · explained in 2 episodes
• Equivariance — 2× in this paper · explained in 3 episodes
• Generative Model — 2× in this paper · explained in 2 episodes
• Monotonicity — 2× in this paper · explained in 2 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Ablation Study — 1× in this paper · explained in 3 episodes
• Calibration — 1× in this paper · explained in 9 episodes
• Convex Hull Neighborhood Smooth Dual Generalization — 1× in this paper
• Covariate Shift — 1× in this paper · explained in 3 episodes
• Evaluation Protocol — 1× in this paper · explained in 2 episodes
• Hyperparameters — 1× in this paper · explained in 2 episodes
• Latent Space — 1× in this paper · explained in 7 episodes
• Markov Decision Process (MDP) — 1× in this paper · explained in 16 episodes
• Offline Optimization — 1× in this paper · explained in 2 episodes
• Reinforcement Learning (RL) — 1× in this paper · explained in 26 episodes
• Representation Learning — 1× in this paper · explained in 3 episodes
• Reward Function — 1× in this paper · explained in 4 episodes
• Robustness — 1× in this paper · explained in 6 episodes

Sources

• OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning
• Pessimistic Bootstrapping for Uncertainty-Driven Offline Reinforcement Learning
• Flow Actor-Critic for Offline Reinforcement Learning
• UMBRELLA: Uncertainty-Aware Model-Based Offline Reinforcement Learning Leveraging Planning
• D4RL: Datasets for Deep Data-Driven Reinforcement Learning
• Extreme Q-Learning: MaxEnt RL without Entropy
• Improving Offline RL by Blending Heuristics
• Offline Reinforcement Learning with Implicit Q-Learning
• Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems
• When Data Geometry Meets Deep Function: Generalizing Offline Reinforcement Learning
• Off-Policy Policy Gradient with State Distribution Correction
• Deployment-Efficient Reinforcement Learning via Model-Based Offline Optimization
• AWAC: Accelerating Online Reinforcement Learning with Offline Datasets
• Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning
• Less is More: Clustered Cross-Covariance Control for Offline RL
• UNIQ: Conformal Calibration for Adaptive Conservatism in Offline Reinforcement Learning
• Behavior Regularized Offline Reinforcement Learning
• Uncertainty Weighted Actor-Critic for Offline Reinforcement Learning
• The In-Sample Softmax for Offline Reinforcement Learning
• Offline RL with No OOD Actions: In-Sample Learning via Implicit Value Regularization

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