Premium Content

Multi-Agent Reinforcement Learning

Cooperation, competition, and self-play

This chapter requires a subscription to access.

What you'll unlock:

  • 1. Game-Theoretic Foundations
  • 2. Independent Learners and Non-Stationarity
  • 3. VDN and QMIX: Value Decomposition
  • 4. MADDPG and COMA
  • 5. MAPPO: PPO for Cooperative MARL
  • 6. Self-Play and PSRO: AlphaStar and OpenAI Five
Subscribe to Unlock

Already have an account? Sign in