Combining Tree-Search, Generative Models, and Nash Bargaining Concepts in Game-Theoretic Reinforcement Learning.
Zun LiMarc LanctotKevin R. McKeeLuke MarrisIan GempDaniel HennesPaul MullerKate LarsonYoram BachrachMichael P. WellmanPublished in: CoRR (2023)
Keyphrases
- game theoretic
- generative model
- tree search
- game theory
- reinforcement learning
- nash equilibrium
- decision problems
- state space
- probabilistic model
- nash equilibria
- discriminative learning
- search algorithm
- branch and bound
- mathematical programming
- discriminative models
- prior knowledge
- constraint propagation
- search tree
- trust model
- solution concepts
- equilibrium strategies
- optimal policy
- imperfect information
- em algorithm
- game tree
- utility function
- resource allocation
- background knowledge
- machine learning
- learning tasks
- multiagent systems
- combinatorial auctions
- path finding
- dynamic programming
- lower bound
- multi agent systems
- learning algorithm