On the Global Convergence Rates of Decentralized Softmax Gradient Play in Markov Potential Games.
Runyu ZhangJincheng MeiBo DaiDale SchuurmansNa LiPublished in: NeurIPS (2022)
Keyphrases
- global convergence
- global optimum
- convergence analysis
- game playing
- convergence speed
- convergence rate
- optimization methods
- convex minimization
- constrained optimization problems
- games played
- online game
- line search
- video games
- computer games
- optimization method
- markov chain
- board game
- coordinate ascent
- neural network
- swarm intelligence
- nash equilibrium
- particle swarm
- multi agent
- multiscale
- game players
- newton method
- genetic algorithm