Dealing with Non-Stationarity in Multi-Agent Reinforcement Learning via Trust Region Decomposition.
Wenhao LiXiangfeng WangBo JinJunjie ShengHongyuan ZhaPublished in: CoRR (2021)
Keyphrases
- multi agent reinforcement learning
- trust region
- global optimum
- optimization methods
- column generation
- multi agent
- stochastic games
- hessian matrix
- log likelihood
- levenberg marquardt
- reinforcement learning
- learning agents
- newton method
- multi agent systems
- artificial neural networks
- line search
- multi agent learning
- least squares
- machine learning
- expert systems
- optimization method
- back propagation