Asynchronous Gradient Play in Zero-Sum Multi-agent Games.
Ruicheng AoShicong CenYuejie ChiPublished in: ICLR (2023)
Keyphrases
- multi agent
- stochastic games
- game theory
- nash equilibria
- game playing
- boolean games
- american football
- repeated games
- multi agent systems
- nash equilibrium
- imperfect information
- single agent
- games played
- multiagent reinforcement learning
- leader follower
- game theoretic
- multi player
- cooperative
- online game
- multi agent decision making
- learning agents
- intelligent agents
- perfect information
- incomplete information
- multiagent systems
- game players
- reinforcement learning
- autonomous agents
- board game
- reinforcement learning agents
- game design
- game tree search
- multiple agents
- coalition formation
- heterogeneous agents
- playing games
- extensive form games
- card game
- asynchronous communication
- human players
- average reward
- image gradient
- online discussion
- game play
- markov decision processes