Semicentralized Deep Deterministic Policy Gradient in Cooperative StarCraft Games.
Dong XieXiangnan ZhongPublished in: IEEE Trans. Neural Networks Learn. Syst. (2022)
Keyphrases
- policy gradient
- cooperative
- game theory
- video games
- game play
- reinforcement learning
- actor critic
- function approximation
- optimal control
- multi agent
- computer games
- gradient method
- nash equilibria
- nash equilibrium
- multi agent systems
- variance reduction
- game playing
- game theoretic
- single agent
- approximation methods
- reinforcement learning algorithms
- average reward
- real valued
- convergence rate
- imperfect information
- stochastic games
- machine learning
- markov chain