V on Neumann's celebrated minimax theorem establishes the existence of Nash equilibrium in all two-player zero-sum games where the players' utilities are continuous as well as concave in their

This feedback can be system generated or elicited from a human observing the training process. Previous approaches have not been able to scale to complex environments and are constrained to receiving feedback at the state level which can be expensive to collect. To this end, we introduce an approach that scales to more complex domains and extends beyond state-level feedback, thus, reducing the burden on the evaluator.

This paper proceeds as follows.

Due to their inherent complexity, these tasks pose significant challenges for current machine learning systems.

A challenging problem in seeking to bring multi-agent reinforcement learning (MARL) techniques into real-world applications, such as autonomous driving and drone swarms, is how to control multiple agents safely and cooperatively to accomplish tasks.

As such, we prevent policies from merely exploiting heuristic rewards without improving the task reward.

Our experimental results demonstrate that the ranking algorithm-based classifiers provide plans that enhance infection rate control, especially with increased action budgets for small networks.

Real-world multi-agent scenarios often involve mixed motives, demanding altruistic agents capable of self-protection against potential exploitation.