No article text was recorded for this version.
heavy-tailed reward distributions
Version 2 of 2227 papers303 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Bandits Corrupted by Nature: Lower Bounds on Regret and Robust Optimistic Algorithms
- Blog: No-Regret Reinforcement Learning with Heavy-Tailed Rewards
- Blog: Low-rank Matrix Bandits with Heavy-tailed Rewards
- Blog: Improved Regret Bounds for Linear Bandits with Heavy-Tailed Rewards
- Blog: Minimax Policy for Heavy-Tailed Bandits
- Blog: Thompson Sampling on Symmetric α-Stable Bandits
- Blog: Minimax Policy for Heavy-tailed Bandits
- Blog: Thompson Sampling on Symmetric Alpha-Stable Bandits
- Blog: Decentralized Randomly Distributed Multi-agent Multi-armed Bandit with Heterogeneous Rewards
- Blog: Contextual Bandits for Unbounded Context Distributions
- Blog: Cooperative Multi-Agent Bandits with Heavy Tails
- Blog: Tackling Heavy-Tailed Rewards in Reinforcement Learning with Function Approximation: Minimax Optimal and Instance-Dependent Regret Bounds
- Blog: Optimal Algorithms for Stochastic Multi-Armed Bandits with Heavy Tailed Rewards
- Blog: Bootstrapping Upper Confidence Bound
- Blog: On the Optimality of Perturbations in Stochastic and Adversarial Multi-armed Bandit Problems
- Blog: Thompson Exploration with Best Challenger Rule in Best Arm Identification
- Blog: Thompson Sampling on Asymmetric α-Stable Bandits
- Blog: Tackling Heavy-Tailed Rewards in Reinforcement Learning with Function Approximation: Minimax Optimal and Instance-Dependent Regret Bounds
- Blog: Minimax Policy for Heavy-tailed Bandits
- Blog: The KL-UCB Algorithm for Bounded Stochastic Bandits and Beyond
- Blog: Regret Minimization in Heavy-Tailed Bandits
- Blog: Stochastic Graphical Bandits with Heavy-Tailed Rewards
- Blog: Censored Exploration and the Dark Pool Problem
- Blog: UCB algorithms for multi-armed bandits: Precise regret and adaptive inference
- Blog: Exact Policy Recovery in Offline RL with Both Heavy-Tailed Rewards and Data Corruption
- Blog: Minimax Optimal Bandits for Heavy Tail Rewards
- Blog: Improving PAC Exploration Using the Median Of Means
- Blog: Minimax Policy for Heavy-tailed Multi-armed Bandits
- Blog: Quantum Heavy-tailed Bandits
- Blog: A General Framework for Bandit Problems Beyond Cumulative Objectives
- Blog: Optimal best arm selection for general distributions
- Blog: Bandits with Stochastic Corruption: Lower Bounds on Regret and Robust Optimistic Algorithms
- Blog: Inference with the Upper Confidence Bound Algorithm
- Blog: Extended UCB Policy for Multi-Armed Bandit with Light-Tailed Reward Distributions
- Blog: Log-Sum-Exponential Estimator for Off-Policy Evaluation and Learning
- Blog: Information Theoretic Guarantees For Policy Alignment In Large Language Models
- Blog: Modeling Attrition in Recommender Systems with Departing Bandits
- Blog: Linearizing contextual bandits with latent state dynamics
- Blog: Bandits Corrupted by Nature: Lower Bounds on Regret and Robust Optimistic Algorithm
- Blog: Implicitly normalized forecaster with clipping for linear and non-linear heavy-tailed multi-armed bandits
- Blog: Bootstrapping Upper Confidence Bound
- Blog: Strategic Choices in Optimization
- Blog: On Thompson Sampling for Smoother-than-Lipschitz Bandits
- Blog: Bounded regret in stochastic multi-armed bandits
- Blog: Online Learning and Pricing with Reusable Resources: Linear Bandits with Sub-Exponential Rewards
- Blog: Breaking the Moments Condition Barrier: No-Regret Algorithm for Bandits with Super Heavy-Tailed Payoffs
- Blog: Breaking the Moments Condition Barrier: No-Regret Algorithm for Bandits with Super Heavy-Tailed Payoffs
- Blog: Robust Offline Reinforcement Learning with Heavy-Tailed Rewards
- Blog: (ε, u)-Adaptive Regret Minimization in Heavy-Tailed Bandits
- Blog: Catastrophic Goodhart: regularizing RLHF with KL divergence does not mitigate heavy-tailed reward misspecification
- Blog: Heavy-tailed Linear Bandits: Adversarial Robustness, Best-of-both-worlds, and Beyond
- Blog: Improved Regret Bounds for Linear Bandits with Heavy-Tailed Rewards
- Blog: Variance-aware decision making with linear function approximation under heavy-tailed rewards
- Blog: No-Regret Algorithms for Heavy-Tailed Linear Bandits
- Blog: Bandit algorithms: Letting go of logarithmic regret for statistical robustness
- Blog: Self-Concordant Perturbations for Linear Bandits
- Blog: Catoni Contextual Bandits are Robust to Heavy-tailed Rewards
- Blog: Deterministic Sequencing of Exploration and Exploitation for Multi-Armed Bandit Problems
- Blog: On exact sampling of stochastic perpetuities
- Blog: Bandit algorithms: Letting go of logarithmic regret for statistical robustness
Showing 60 of 227 papers.
History & citation
Current · Permanent link
- parameter-dependent robust estimation split from this direction (50% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_heavy_tailed_reward_distributions_905866ea,
title = {heavy-tailed reward distributions},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/heavy-tailed-reward-distributions/rdr_905866ea97a34ac796156ea1d2a84bff},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 2, frozen text):
@misc{lacuna_heavy_tailed_reward_distributions_905866ea_v2,
title = {heavy-tailed reward distributions},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/heavy-tailed-reward-distributions/rdr_905866ea97a34ac796156ea1d2a84bff/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-20},
}