Bad Qubits — Learn Quantum by Doing

Multiple choice

In a quantum GAN's minimax value function, which player optimizes in which direction, and what holds at the Nash equilibrium?

The discriminator minimizes and the generator is fixed; at equilibrium the generator outputs a single constant sample
The generator minimizes and the discriminator maximizes; at equilibrium the generator's distribution matches the data and the discriminator can do no better than guessing
The generator maximizes and the discriminator minimizes; at equilibrium the discriminator perfectly separates real from fake forever
Both the generator and discriminator minimize the same objective; at equilibrium both reach zero loss simultaneously