Explore opponent-shaping and interference in general-sum games through this lecture delivered at the 2023 Cooperative AI Summer School. Delve into the foundational work of Jakob Foerster, an Associate Professor at the University of Oxford's department of engineering science. Gain insights from Foerster's extensive experience in deep multi-agent reinforcement learning, including his contributions at Google Brain, OpenAI, and DeepMind. Learn about his role in organizing the first Emergent Communication workshop at NeurIPS and his recognition as a CIFAR AI chair. Discover the implications of these concepts for cooperative AI and multi-agent systems in this hour-long presentation.
Overview
Syllabus
Opponent-Shaping and Interference in General-Sum Games
Taught by
Cooperative AI Foundation
Related Courses
-
RLHF: How to Learn from Human Feedback with Reinforcement Learning
-
Learning to Cooperate and Compete via Self Play
-
Building Adaptive Multi-Agent AI Systems: From Theory to Implementation
-
Multi-Agent AI Coordination and Pathfinding Using Cooperative Reward Shaping
-
Aligning AI to Everyone via Reinforcement Learning
-
Independent Learning Dynamics for Stochastic Games - Where Game Theory Meets
