AAAI 2026 accepted papers on Bandits and online learning
31 of the 4,417 papers accepted at AAAI 2026 (0.7%) are on Bandits and online learning, compared with 0.9% at AAAI 2025. They fall into 4 topics.
See AAAI 2026 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
Online convex optimization and games · 15 papers
- SACO: Sequence-Aware Constrained Optimization Framework for Coupon Distribution in E-commerce (1 citation)
- Bandit Learning in Housing Markets
- Budgeted Online Active Learning with Expert Advice and Episodic Priors
- Constrained Online Convex Optimization with Memory and Predictions
- Decentralized Online Convex Optimization with Unknown Feedback Delays
- Deep (Predictive) Discounted Counterfactual Regret Minimization
- Faster Game Solving via Asymmetry of Step Sizes
- Learning-Augmented Ski Rental with Discrete Distribution: A Bayesian Approach
- Minimum-Cost Network Flow with Dual Predictions
- Online Linear Regression with Paid Stochastic Features
- Ordinal Secretaries with Advice
- A Switching Framework for Online Interval Scheduling with Predictions
and 3 more in the interactive map.
Multi-armed bandits · 10 papers
- Provably Efficient Multi-Objective Bandit Algorithms Under Preference-Centric Customization (1 citation)
- Robust Decentralized Multi-armed Bandits: From Corruption-Resilience to Byzantine-Resilience (1 citation)
- Best Arm Identification with Biased Contexts
- Beyond the Lower Bound: Bridging Regret Minimization and Best Arm Identification in Lexicographic Bandits
- Constrained Best Arm Identification with Tests for Feasibility
- Fair Algorithms with Probing for Multi-Agent Multi-Armed Bandits
- GINO-Q: Learning an Asymptotically Optimal Index Policy for Restless Multi-armed Bandits
- Multiple-play Stochastic Bandits with Prioritized Arm Capacity Sharing
- On the Robustness of Bandit Multiple Testing
- Quantum Lipschitz Bandits