No article text was recorded for this version.
logarithmic update scheduling
Version 1 of 1118 papers156 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Batched Multi-armed Bandits Problem
- Blog: Batched Thompson Sampling for Multi-Armed Bandits
- Blog: Near-optimal Optimistic Reinforcement Learning using Empirical Bernstein Inequalities
- Blog: Provably Efficient Reinforcement Learning via Surprise Bound
- Blog: Dynamic Batch Learning in High-Dimensional Sparse Linear Contextual Bandits
- Blog: Batched Multi-armed Bandits Problem
- Blog: Parallelizing Thompson Sampling
- Blog: Lazy OCO: Online Convex Optimization on a Switching Budget
- Blog: Online Learning for Function Placement in Serverless Computing
- Blog: Provably Efficient Reinforcement Learning with Linear Function Approximation under Adaptivity Constraints
- Blog: Contextual Multi-Armed Bandits with Minimum Aggregated Revenue Constraints
- Blog: Batched Bandit Problems
- Blog: Lipschitz Bandits With Batched Feedback
- Blog: An Asymptotically Optimal Batched Algorithm for the Dueling Bandit Problem
- Blog: Batched Nonparametric Contextual Bandits
- Blog: Multinomial Logit Contextual Bandits: Provable Optimality and Practicality
- Blog: Optimal Batched Linear Bandits
- Blog: Langevin Thompson Sampling with Logarithmic Communication: Bandits and Reinforcement Learning
- Blog: Online Reinforcement Learning in Markov Decision Process Using Linear Programming
- Blog: Efficient Batched Algorithm for Contextual Linear Bandits with Large Action Space via Soft Elimination
- Blog: The Batch Complexity of Bandit Pure Exploration
- Blog: Provably Efficient Q-Learning with Low Switching Cost
- Blog: Sample and Computationally Efficient Continuous-Time Reinforcement Learning with General Function Approximation
- Blog: Almost Optimal Anytime Algorithm for Batched Multi-Armed Bandits
- Blog: Batched Stochastic Matching Bandits
- Blog: Batched Dueling Bandits
- Blog: Provably Efficient Reinforcement Learning via Surprise Bound
- Blog: Optimal and Practical Batched Linear Bandit Algorithm
- Blog: Asymptotic Performance of Thompson Sampling in the Batched Multi-Armed Bandits
- Blog: Practical and Optimal Algorithm for Linear Contextual Bandits with Rare Parameter Updates
- Blog: Efficient Function Placement in Virtual Networks: An Online Learning Approach
- Blog: Posterior Sampling for Large Scale Reinforcement Learning
- Blog: Provably Efficient High-Dimensional Bandit Learning with Batched Feedbacks
- Blog: Scalar Posterior Sampling with Applications
- Blog: Near-optimal Regret Bounds for Reinforcement Learning
- Blog: Optimal Learning for Structured Bandits
- Blog: Achieving Limited Adaptivity for Multinomial Logistic Bandits
- Blog: Sample-Efficient Reinforcement Learning with loglog(T) Switching Cost
- Blog: Optimal and Practical Batched Linear Bandit Algorithm
- Blog: Finite-Time Analysis of Round-Robin Kullback-Leibler Upper Confidence Bounds for Optimal Adaptive Allocation with Multiple Plays and Markovian Rewards
- Blog: Near-optimal Reinforcement Learning using Bayesian Quantiles
- Blog: Regret-Optimal Q-Learning with Low Cost for Single-Agent and Federated Reinforcement Learning
- Blog: Settling the Sample Complexity of Online Reinforcement Learning
- Blog: Batched Thompson Sampling
- Blog: Input perturbations for adaptive control and learning
- Blog: Online Experimental Design for Network Tomography
- Blog: A General Framework for Sequential Decision-Making under Adaptivity Constraints
- Blog: Double Explore-then-Commit: Asymptotic Optimality and Beyond
- Blog: Batched Thompson Sampling
- Blog: Sequential Batch Learning in Finite-Action Linear Contextual Bandits
- Blog: Regret Bounds for Batched Bandits
- Blog: Optimistic posterior sampling for reinforcement learning: worst-case regret bounds
- Blog: Contextual Slate GLM Bandits with Limited Adaptivity
- Blog: Provably Efficient Reinforcement Learning with Linear Function Approximation Under Adaptivity Constraints
- Blog: Online Policy Gradient for Model Free Learning of Linear Quadratic Regulators with √T Regret
- Blog: Learning Unknown Markov Decision Processes: A Thompson Sampling Approach
- Blog: Nearly Minimax Optimal Regret for Multinomial Logistic Bandit
- Blog: Multinomial Logit Bandit with Low Switching Cost
- Blog: Bypassing the Monster: A Faster and Simpler Optimal Algorithm for Contextual Bandits under Realizability
- Blog: Optimal Best-arm Identification in Linear Bandits
Showing 60 of 118 papers.
History & citation
Current · Permanent link
- Reinforcement Learning with Low Switching Cost merged into this direction (52% overlap)
- The Efficiency of Rare Policy Updates in Batched Bandits merged into this direction (76% overlap)
- Logarithmic Switching Costs for Efficient Reinforcement Learning merged into this direction (58% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_logarithmic_update_scheduling_a27fddee,
title = {logarithmic update scheduling},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/logarithmic-update-scheduling/rdr_a27fddee38ae4ae0936419bf259b951a},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 1, frozen text):
@misc{lacuna_logarithmic_update_scheduling_a27fddee_v1,
title = {logarithmic update scheduling},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/logarithmic-update-scheduling/rdr_a27fddee38ae4ae0936419bf259b951a/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-21},
}