Inverse Concave-Utility Reinforcement Learning is Inverse Game Theory.
Mustafa Mert ÇelikokFrans A. OliehoekJan-Willem van de MeentPublished in: CoRR (2024)
Keyphrases
- game theory
- reinforcement learning
- game theoretic
- cooperative
- multi agent systems
- nash equilibrium
- multi agent learning
- fictitious play
- resource allocation
- mechanism design
- learning algorithm
- financial crisis
- statistical physics
- decision theory
- multi agent
- function approximation
- utility function
- multiagent learning
- multi agent reinforcement learning
- dynamic programming
- machine learning