Open Course Space

Topics in Multiagent Learning

Massachusetts Institute of TechnologyUnited States6.S890
Free, no sign-up neededFall 2024English
Go to course on MIT OpenCourseWare

While machine learning techniques have had significant success in single-agent settings, an increasingly large body of literature has been studying settings involving several learning agents with different objectives. In these settings, standard training methods such as gradient descent are less successful and the simultaneous learning of the agents commonly leads to non-stationary and even chaotic system dynamics.

Description from MIT OpenCourseWare.

Where to take this course