Our analysis highlights sufficient properties for a regret minimization algorithm to be used as leader.

Step 2. The deduction in Step 1 can be iterated repeatedly due to the symmetry of

We study the problem of exploration in Reinforcement Learning and present a novel model-free solution. We adopt an information-theoretical viewpoint and start from the instance-specific lower bound of the number of samples that have to be collected to identify a nearly-optimal policy.

Optimal auction design is a fundamental problem in algorithmic game theory.

However, simply pooling everyone's data and sharing with each other can lead to free-riding [