Google, IBM & Meta Certificates – 40% Off
One plan covers every Professional Certificate on Coursera.
Unlock All Certificates
Explore policy revision dynamics and algorithm design in stochastic and mean-field games through this 56-minute seminar from GERAD Research Center. Delve into game theoretic models for analyzing strategic interactions in multi-agent systems, focusing on stochastic games and N-player mean-field games. Examine common learning paradigms for policy selection, with emphasis on simple decentralized algorithms. Discover structural results on policy dynamics and their application to algorithm design. Learn about a decentralized learning algorithm and its convergence to near-equilibrium policies in various game classes. Cover topics including single-agent reinforcement learning, multi-agent system applications, stochastic game play description, policy treatments, objective functions, policy update rules, e-satisficing, two-player games, policy set quantization, learning and adaptation decoupling, and symmetric game algorithms. Gain insights from simulations presented by Bora Yongacoglu from Queen's University.
