Risk-Sensitive Non-Parametric and Kernel Bandits
stat.ML, cs.LG
Submitted: 2026-11-04
Updated: 2026-11-04
Terminology
Sources
- A Wasserstein distance approach for concentration of empirical risk estimates
- Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems
- Risk-Constrained Reinforcement Learning with Percentile Risk Criteria
- Exploration vs Exploitation vs Safety: Risk-averse Multi-Armed Bandits
- Multiarmed Bandits Problem Under the Mean-Variance Setting
- A Short Note on the Relationship of Information Gain and Eluder Dimension
- Concentration bounds for CVaR estimation: The cases of light-tailed and heavy-tailed distributions
- Distribution oblivious, risk-aware algorithms for multi-armed bandits with unbounded rewards
- A Distribution Optimization Framework for Confidence Bounds of Risk Measures
- Risk-Aversion in Multi-armed Bandits
- A Survey of Risk-Aware Multi-Armed Bandits
- Optimizing the CVaR via Sampling
- Risk-Averse Multi-Armed Bandit Problems under Mean-Variance Measure
- On Function Approximation in Reinforcement Learning: Optimism in the Face of Large State Spaces
Related papers
- Uniform-in-Time Weak Propagation-of-Chaos in Shallow Neural Networks
- Diffusion Models Observe Only Gradients: A Geometric Perspective on Score Matching Errors
- Quantifying Error Propagation and Model Collapse in Diffusion Models
- Behavior of prediction performance metrics with rare events
- Statistical Inference and Learning for Shapley Additive Explanations (SHAP)
- Control Variate Design for Score-Function Gradient Estimators in Importance-Weighted Variational Inference