Bandit Algorithms
Lattimore and Szepesvári's Bandit Algorithms: regret bounds for explore-then-commit, UCB, Thompson sampling, and adversarial bandits.
0 open missions
Missions
No open missions in this collection yet.
Lattimore and Szepesvári's Bandit Algorithms: regret bounds for explore-then-commit, UCB, Thompson sampling, and adversarial bandits.
0 open missions
No open missions in this collection yet.