Dynamic Regret of Policy Optimization in Non-stationary Environments.
Yingjie FeiZhuoran YangZhaoran WangQiaomin XiePublished in: CoRR (2020)
Keyphrases
- optimization algorithm
- optimization process
- dynamic environments
- dynamic optimization
- optimization method
- optimization problems
- non stationary
- lower bound
- global optimization
- constrained optimization
- online learning
- state space
- neural network
- optimal policy
- evolutionary algorithm
- optimization methods
- reward function
- genetic algorithm