AAAI 2023 accepted papers on Bandits and online learning
35 of the 2,023 papers accepted at AAAI 2023 (1.7%) are on Bandits and online learning, compared with 2.1% at AAAI 2022. They fall into 4 topics.
See AAAI 2023 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest accepted papers by meaning and how crowded the spot has become.
Topics and papers
Multi-armed bandits · 13 papers
- Optimistic Whittle Index Policy: Online Learning for Restless Bandits (14 citations)
- Quantum Multi-Armed Bandits and Stochastic Linear Bandits Enjoy Logarithmic Regrets (10 citations)
- Scalable Decision-Focused Learning in Restless Multi-Armed Bandits with Application to Maternal and Child Health (5 citations)
- Fairness and Welfare Quantification for Regret in Multi-Armed Bandits (4 citations)
- An Efficient Algorithm for Fair Multi-Agent Multi-Armed Bandit with Low Regret (3 citations)
- Flexible Budgets in Restless Bandits: A Primal-Dual Algorithm for Efficient Budget Allocation (3 citations)
- AC-Band: A Combinatorial Bandit-Based Approach to Algorithm Configuration (2 citations)
- Decentralized Stochastic Multi-Player Multi-Armed Walking Bandits (2 citations)
- Networked Restless Bandits with Positive Externalities (2 citations)
- Robust Planning over Restless Groups: Engagement Interventions for a Large-Scale Maternal Telehealth Program (2 citations)
- On the Sample Complexity of Representation Learning in Multi-Task Bandits with Global and Local Structure
- Optimal Execution via Multi-Objective Multi-Armed Bandits (Student Abstract)
and 1 more in the interactive map.
Online convex optimization and games · 12 papers
- Learning-Augmented Algorithms for Online TSP on the Line (12 citations)
- Distributed Projection-Free Online Learning for Smooth and Convex Losses (6 citations)
- Efficient Algorithms for Regret Minimization in Billboard Advertisement (Student Abstract) (5 citations)
- An Improved Algorithm for Online Min-Sum Set Cover (4 citations)
- Improved Kernel Alignment Regret Bound for Online Kernel Learning (3 citations)
- Smoothed Online Combinatorial Optimization Using Imperfect Predictions (2 citations)
- Fully Online Matching with Stochastic Arrivals and Departures (1 citation)
- Gradient-Variation Bound for Online Convex Optimization with Constraints (1 citation)
- Learning-Assisted Algorithm Unrolling for Online Optimization with Budget Constraints (1 citation)
- Fully Dynamic Online Selection through Online Contention Resolution Schemes
- Learning Revenue Maximization Using Posted Prices for Stochastic Strategic Patient Buyers
- Tighter Robust Upper Bounds for Options via No-Regret Learning
Contextual bandits and Thompson sampling · 6 papers
- Efficient Explorative Key-Term Selection Strategies for Conversational Contextual Bandits (10 citations)
- Combinatorial Causal Bandits (5 citations)
- Double Doubly Robust Thompson Sampling for Generalized Linear Contextual Bandits (4 citations)
- Stochastic Contextual Bandits with Long Horizon Rewards (4 citations)
- Meta-Learning for Simple Regret Minimization (3 citations)
- Reward-Biased Maximum Likelihood Estimation for Neural Contextual Bandits: A Distributional Learning Perspective
RL theory and MDPs · 4 papers
- Non-stationary Risk-Sensitive Reinforcement Learning: Near-Optimal Dynamic Regret, Adaptive Detection, and Separation Design (2 citations)
- Online Reinforcement Learning with Uncertain Episode Lengths (2 citations)
- Bilinear Exponential Family of MDPs: Frequentist Regret Bound with Tractable Exploration & Planning (1 citation)
- Optimism in Face of a Context:Regret Guarantees for Stochastic Contextual MDP (1 citation)