conftrace_

bayesian regret

33 papers

Explore in graph

Co-occurring keywords

thompson sampling (237) multi-armed bandit (1098) posterior sampling (152) regret bound (1926) online learning (1777) reinforcement learning (4352) bayesian regret bound (6) markov decision process (790) sequential decision making (215) rate-distortion theory (20)

Papers

On the Performance of Thompson Sampling on Logistic Bandits COLT 2019
Regret Bounds for Thompson Sampling in Episodic Restless Bandit Problems NIPS 2019
An Information-Theoretic Analysis for Thompson Sampling with Many Actions NIPS 2018
Scalar Posterior Sampling with Applications NIPS 2018
The Externalities of Exploration and How Data Diversity Helps Exploitation COLT 2018
Why is Posterior Sampling Better than Optimism for Reinforcement Learning? ICML 2017
Optimistic Gittins Indices NIPS 2016
Prior-free and prior-dependent regret bounds for Thompson Sampling NIPS 2013