Value-Decomposition Networks For Cooperative Multi-Agent Learning Based On Team Reward.
Peter SunehagGuy LeverAudrunas GruslysWojciech Marian CzarneckiVinícius Flores ZambaldiMax JaderbergMarc LanctotNicolas SonneratJoel Z. LeiboKarl TuylsThore GraepelPublished in: AAMAS (2018)
Keyphrases
- multi agent learning
- cooperative
- game theory
- multi agent reinforcement learning
- agents and multi agent systems
- multi agent
- cooperating agents
- reinforcement learning
- replicator dynamics
- multi agent systems
- long run
- artificial intelligence
- neural network
- decision trees
- complex domains
- nash equilibria
- machine learning