Supported Trust Region Optimization for Offline Reinforcement Learning.
Yixiu MaoHongchang ZhangChen ChenYi XuXiangyang JiPublished in: CoRR (2023)
Keyphrases
- trust region
- reinforcement learning
- optimization methods
- unconstrained optimization
- line search
- optimization problems
- global optimum
- optimization method
- optimization algorithm
- global convergence
- learning algorithm
- column generation
- hessian matrix
- newton method
- multi view
- state space
- function approximation
- levenberg marquardt
- convergence rate
- optimization procedure
- integer programming
- neural network
- fixed point
- information theoretic
- graph cuts
- simulated annealing
- machine learning