Aleksandrs Slivkins

6

Papers

0

Total Citations

Papers (6)

Robust Performance Incentivizing Algorithms for Multi-Armed Bandits with Strategic Agents

Efficient Contextual Bandits with Continuous Actions

Constrained episodic reinforcement learning in concave-convex and knapsack settings

Bandits with Knapsacks beyond the Worst Case

Incentivizing Combinatorial Bandit Exploration

Bandit Social Learning under Myopic Behavior