Hindsight Trust Region Policy Optimization.
Hanbo ZhangSite BaiXuguang LanNanning ZhengPublished in: CoRR (2019)
Keyphrases
- trust region
- optimization methods
- unconstrained optimization
- line search
- global optimum
- optimization method
- optimization problems
- constrained optimization
- optimization algorithm
- global convergence
- newton method
- genetic algorithm
- levenberg marquardt
- hessian matrix
- linear program
- maximum likelihood
- quadratic programming
- log likelihood
- risk minimization
- least squares
- support vector machine
- multi objective