Trust Region Policy Optimization.
John SchulmanSergey LevinePieter AbbeelMichael I. JordanPhilipp MoritzPublished in: ICML (2015)
Keyphrases
- trust region
- optimization methods
- unconstrained optimization
- global optimum
- line search
- optimization method
- optimization algorithm
- global convergence
- column generation
- optimization problems
- newton method
- levenberg marquardt
- constrained optimization
- quadratic programming
- objective function
- branch and bound
- simulated annealing
- log likelihood
- maximum likelihood