ICLR 2023 accepted papers on Bandits and online learning
21 of the 1,575 papers accepted at ICLR 2023 (1.3%) are on Bandits and online learning, compared with 0.9% at ICLR 2022. They fall into 4 topics.
See ICLR 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 · 8 papers
- Adversarial Attacks on Adversarial Bandits (3 citations)
- Asymptotic Instance-Optimal Algorithms for Interactive Decision Making (1 citation)
- Neural Design for Genetic Perturbation Experiments (1 citation)
- Collaborative Pure Exploration in Kernel Bandit
- Combinatorial Pure Exploration of Causal Bandits
- Distributed Differential Privacy in Multi-Armed Bandits
- Replicable Bandits
- Achieving Near-Optimal Individual Regret & Low Communications in Multi-Agent Bandits
Contextual bandits and Thompson sampling · 5 papers
Online convex optimization and games · 4 papers
RL theory and MDPs · 4 papers
- Near-Optimal Adversarial Reinforcement Learning with Switching Costs
- Achieving Sub-linear Regret in Infinite Horizon Average Reward Constrained MDP with Linear Function Approximation
- Learning Adversarial Linear Mixture Markov Decision Processes with Bandit Feedback and Unknown Transition
- Provably Efficient Lifelong Reinforcement Learning with Linear Representation