Research map / Reinforcement learning / RL from feedback
Preference Is More than Comparisons: Rethinking Dueling Bandits with Augmented Human Feedback
Shengbo Wang, Hong Sun, Ke Li
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add augmented feedback (related observations) to confidence bounds | RUCB / DTS · Sushi and Car Preference recommendation | cumulative regret | Improved |
| add augmented feedback to DTS/RUCB with LLM-annotated dependencies | RUCB / DTS · LLM response optimization (Anthropic H-H) | cumulative regret | Improved |
| use context-free DB instead of parametric BT-based DB | dueling bandits · Sushi and Car Preference | cumulative regret | Improved |
| use deterministic IPEA-RUCB instead of stochastic IPEA-DTS | IPEA-HF · DTLZ7 multi-objective optimization (sparse feedback) | cumulative regret | Improved |
| use stochastic strategy (DTS-based) instead of deterministic RUCB-based | IPEA-HF · LLM response optimization | cumulative regret | Improved |
Closest papers by meaning
- Neural Dueling Bandits: Preference-Based Optimization with Human Feedback (ICLR 2025 · similarity 0.90)
- Enhancing Preference-based Linear Bandits via Human Response Time (NeurIPS 2024 · similarity 0.90)
- Capturing Individual Human Preferences with Reward Features (NeurIPS 2025 · similarity 0.88)
- Variance-aware Regret Bounds for Stochastic Contextual Dueling Bandits (ICLR 2024 · similarity 0.88)
- Direct Preference-Based Evolutionary Multi-Objective Optimization with Dueling Bandits (NeurIPS 2024 · similarity 0.88)
- Bandits with Preference Feedback: A Stackelberg Game Perspective (NeurIPS 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
