No article text was recorded for this version.
finite-time regret analysis
Version 2 of 2112 papers129 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Stochastic Online Learning with Feedback Graphs: Finite-Time and Asymptotic Optimality
- Blog: Instance-Optimality in Interactive Decision Making: Toward a Non-Asymptotic Theory
- Blog: Crush Optimism with Pessimism: Structured Bandits Beyond Asymptotic Optimality
- Blog: Bandit Algorithms Based on Thompson Sampling for Bounded Reward Distributions
- Blog: Explore First, Exploit Next: The True Shape of Regret in Bandit Problems
- Blog: Stochastic Online Learning with Feedback Graphs: Finite-Time and Asymptotic Optimality
- Blog: Explore First, Exploit Next: The True Shape of Regret in Bandit Problems
- Blog: Explore First, Exploit Next: The True Shape of Regret in Bandit Problems
- Blog: Online Learning with Gaussian Payoffs and Side Observations
- Blog: From 6235149080811616882909238708 to 29: Vanilla Thompson Sampling Revisited
- Blog: Near Minimax Optimal Players for the Finite-Time 3-Expert Prediction Problem
- Blog: Adaptive Exploration in Linear Contextual Bandit
- Blog: From Restless to Contextual: A Thresholding Bandit Reformulation for Finite-horizon Improvement
- Blog: Asymptotically-Optimal Gaussian Bandits with Side Observations
- Blog: Online Passive-Aggressive Algorithms
- Blog: Reinforcement Learning in a Birth and Death Process: Breaking the Dependence on the State Space
- Blog: Single-Trajectory Distributionally Robust Reinforcement Learning
- Blog: Finite-Time Analysis of Round-Robin Kullback-Leibler Upper Confidence Bounds for Optimal Adaptive Allocation with Multiple Plays and Markovian Rewards
- Blog: Optimal Regret of Bandits under Differential Privacy
- Blog: Stochastic contextual bandits with graph feedback: from independence number to MAS number
- Blog: Asymptotically-Optimal Gaussian Bandits with Side Observations
- Blog: Stochastic contextual bandits with graph feedback: from independence number to MAS number
- Blog: Stochastic Linear Optimization under Bandit Feedback
- Blog: Multi-dueling Bandits with Dependent Arms
- Blog: Best Arm Identification with Minimal Regret
- Blog: Conservative Exploration for Semi-Bandits with Linear Generalization: A Product Selection Problem for Urban Warehouses
- Blog: Asymptotically Optimal Strategies For Combinatorial Semi-Bandits in Polynomial Time
- Blog: Optimality of Thompson Sampling with Noninformative Priors for Pareto Bandits
- Blog: Asymptotic Instance-Optimal Algorithms for Interactive Decision Making
- Blog: Minimax Regret for Partial Monitoring: Infinite Outcomes and Rustichini's Regret
- Blog: Reinforcement Learning in a Birth and Death Process: Breaking the Dependence on the State Space
- Blog: Optimistic posterior sampling for reinforcement learning: worst-case regret bounds
- Blog: Regret-optimal Strategies for Playing Repeated Games with Discounted Losses
- Blog: Regret Lower Bound and Optimal Algorithm in Dueling Bandit Problem
- Blog: Worst-Case Bounds for the Logarithmic Loss of Predictors
- Blog: On the Finite-Time Performance of the Knowledge Gradient Algorithm
- Blog: Improved Regret Bounds for Online Kernel Selection under Bandit Feedback
- Blog: The KL-UCB Algorithm for Bounded Stochastic Bandits and Beyond
- Blog: Online Learning in Contextual Bandits using Gated Linear Networks
- Blog: Dueling Posterior Sampling for Preference-Based Reinforcement Learning
- Blog: Non-Asymptotic Gap-Dependent Regret Bounds for Tabular MDPs
- Blog: Experimental Design for Regret Minimization in Linear Bandits
- Blog: Learning to Cache and Caching to Learn: Regret Analysis of Caching Algorithms
- Blog: Influential Bandits: Pulling an Arm May Change the Environment
- Blog: On the Necessity of Collaboration for Online Model Selection with Decentralized Data
- Blog: Optimality of Thompson Sampling with Noninformative Priors for Pareto Bandits
- Blog: Nearly Minimax Optimal Reinforcement Learning for Linear Markov Decision Processes
- Blog: Bayesian decision-making under misspecified priors with applications to meta-learning
- Blog: Is Q-Learning Provably Efficient?
- Blog: Stochastic Online Learning with Probabilistic Graph Feedback
- Blog: Almost Optimal Anytime Algorithm for Batched Multi-Armed Bandits
- Blog: From Restless to Contextual: A Thresholding Bandit Approach to Improve Finite-horizon Performance
- Blog: Kullback-Leibler Maillard Sampling for Multi-armed Bandits with Bounded Rewards
- Blog: Understanding the Training and Generalization of Pretrained Transformer for Sequential Decision Making
- Blog: Optimizing Adaptive Experiments: A Unified Approach to Regret Minimization and Best-Arm Identification
- Blog: Optimal Batched Linear Bandits
- Blog: Structure Adaptive Algorithms for Stochastic Bandits
- Blog: Bandits with Switching Costs: T^{2/3} Regret
- Blog: Thompson Sampling for 1-Dimensional Exponential Family Bandits
- Blog: Asymptotically Optimal Information-Directed Sampling
Showing 60 of 112 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_finite_time_regret_analysis_efddfb52,
title = {finite-time regret analysis},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/finite-time-regret-analysis/rdr_efddfb528bf64b988dee32d564c4fb34},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 2, frozen text):
@misc{lacuna_finite_time_regret_analysis_efddfb52_v2,
title = {finite-time regret analysis},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/finite-time-regret-analysis/rdr_efddfb528bf64b988dee32d564c4fb34/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-21},
}