Discussion of selected applications and future challenges will conclude the talk. Both single and multiple population scenarios will be covered. This plenary talk will provide an overview of recent developments in the landscape described above, focusing on some foundational results for both model-based and model-free settings, with the latter involving data-driven policy design, requiring reinforcement learning, zero-order stochastic optimization, and finite-sample analysis. This latter challenge actually turns out to be a blessing in itself, under some (realistic) structural specifications, as in the high population setting the agents become infinitesimal entities, making the underlying dynamic game asymptotically belonging to the class of mean field games (MFGs), a topic that has attracted intense research activity in recent years.
Another challenge presents itself in scalability of the decision process, as the size of the population of the agents grows.
The inherent asymmetry in information across the agents, with them not operating under the same (and consistent) modeling assumptions, and with strategic interactions taking place in neighborhoods and propagating across the network create major challenges in the decision-making process, necessitating each agent to operate in a non-stationary environment and develop beliefs on others, with the belief generation process leading to what is known as second-guessing phenomenon. and whether they are fully cooperating or fully non-cooperating, or a mix of the two, as well as whether the mode of cooperation (or non-cooperation) during the evolution of the game dynamics is not fixed and changes depending on external as well as internal factors (driven by events that may be generated partially by the strategies adopted by the agents operating under asymmetric, decentralized information). A natural framework, and a comprehensive one, for modeling, optimization, and analysis in such systems is that provided by stochastic dynamic games, which accommodates different solution concepts depending on how the interactions among the agents are modeled, such as whether there is a hierarchy among them, or they all operate symmetrically as far as the decision-making process goes. Abstract: Decision making in dynamic uncertain environments with multiple agents having possibly misaligned objectives arises in many disciplines and application domains, including control (particularly, networked control, such as control and operation of multiple robots, unmanned vehicles, mobile sensor networks, and the smart grid), communications (particularly in transmission of information to multiple destinations under privacy constraints), distributed optimization (particularly, with topological and informational constraints), social networks (such as problems of consensus and dissensus), and economics.
0 kommentar(er)
