conftrace_

upper confidence bound

197 papers

Explore in graph

Also known as

UCB

Co-occurring keywords

regret bound (1926) multi-armed bandit (1098) online learning (1777) contextual bandit (381) bayesian optimization (624) gaussian process (1200) thompson sampling (237) reinforcement learning (4352) stochastic optimization (1060) ucb algorithm (44)

Papers

No-regret approximate inference via Bayesian optimisation UAI 2021
Contextual Blocking Bandits AISTATS 2021
No-regret Algorithms for Multi-task Bayesian Optimization AISTATS 2021
Stochastic Bandits with Linear Constraints AISTATS 2021
Federated Multi-armed Bandits with Personalization AISTATS 2021
Multi-Armed Bandits with Cost Subsidy AISTATS 2021
Multitask Bandit Learning Through Heterogeneous Feedback Aggregation AISTATS 2021
Reinforcement Learning in Parametric MDPs with Exponential Families AISTATS 2021
Regulating Greed Over Time in Multi-Armed Bandits JMLR 2021
Provably Efficient Fictitious Play Policy Optimization for Zero-Sum Markov Games with Structured Transitions ICML 2021
Near-Optimal Model-Free Reinforcement Learning in Non-Stationary Episodic MDPs ICML 2021
Decentralized Multi-Agent Linear Bandits with Safety Constraints AAAI 2021
Multinomial Logit Contextual Bandits: Provable Optimality and Practicality AAAI 2021
Regime Switching Bandits NIPS 2021
A Closer Look at the Worst-case Behavior of Multi-armed Bandit Algorithms NIPS 2021
Exploiting Opponents Under Utility Constraints in Sequential Games NIPS 2021
Stochastic Multi-Armed Bandits with Control Variates NIPS 2021
MADE: Exploration via Maximizing Deviation from Explored Regions NIPS 2021
Dynamic Bottleneck for Robust Self-Supervised Exploration NIPS 2021
Federated Multi-Armed Bandits AAAI 2021
Robust Contextual Bandits via Bootstrapping AAAI 2021
Bandits with many optimal arms NIPS 2021
Efficient Algorithms for Stochastic Repeated Second-price Auctions ALT 2021
Double Explore-then-Commit: Asymptotic Optimality and Beyond COLT 2021
Adaptive Sampling for Estimating Distributions: A Bayesian Upper Confidence Bound Approach L4DC 2021