Saturation-Insensitive Dueling Bandits with General Function Approximation
cs.LG
Submitted: 2026-09-26
Updated: 2026-09-26
Terminology
Sources
- Reinforcement Learning from Human Feedback with Active Queries
- Provable Benefits of Policy Learning from Human Preferences in Contextual Bandit Problems
- A Unified Confidence Sequence for Generalized Linear Models, with Applications to Bandits
- Feel-Good Thompson Sampling for Contextual Dueling Bandits
- Learning What to Recommend: Minimax Optimal Simple Regret in Logistic Bandits
- Active Preference Learning for Large Language Models
- PAC Reinforcement Learning for Predictive State Representations
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: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks