Useful Algorithm/Proof Tricks for Combinatorial Multi-Armed Bandits (CMAB)

less than 1 minute read

Published:

Some notes about ALgorithm/Proof Tricks for CMAB. Keep updating…

Must-read CMAB papers

These are some must-read papers for CMAB, including different models (semi-bandit, full-bandit, cascading bandit, CMAB with triggering arms/CMAB-T, contextual CMAB), different methods (ucb, ucb-variance, ucb-distribution, Thompson sampling, policy-randomization, optimzation-based), and tutorials (for CMAB before 2017).