Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Dynamic Balancing for Model Selection in Bandits and RL
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Dynamic balancing used to select among OFUL confidence-scaling instances (basic version, no biases/scales) instead of Stochastic Corral | OFUL confidence parameter tuning · Synthetic linear bandits, noise sigma 1, 0.3, 0.05 | cumulative regret / sqrt(T) | Mixed |
| Replace importance-weighted Corral with dynamic balancing for model selection | OFUL confidence parameter tuning · Synthetic linear bandits, noise sigma 1, 0.3, 0.05 | cumulative regret / sqrt(T) | Helped |
| Use the dynamic balancing algorithm with theory-derived biases and scaling factors vs. basic version | Dynamic Balancing · Synthetic linear bandits | regret | No clear effect |
Closest papers by meaning
- Model Selection in Contextual Stochastic Bandit Problems (NeurIPS 2020 · similarity 0.93)
- Best of Both Worlds Model Selection (NeurIPS 2022 · similarity 0.92)
- Sparsity-Agnostic Linear Bandits with Adaptive Adversaries (NeurIPS 2024 · similarity 0.90)
- Beyond Primal-Dual Methods in Bandits with Stochastic and Adversarial Constraints (NeurIPS 2024 · similarity 0.88)
- Small steps no more: Global convergence of stochastic gradient bandits for arbitrary learning rates (NeurIPS 2024 · similarity 0.88)
- Generalized Linear Bandits: Almost Optimal Regret with One-Pass Update (NeurIPS 2025 · similarity 0.88)
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.