Adaptive Trust Region Policy Optimization: Global Convergence and Faster Rates for Regularized MDPs.
Lior ShaniYonathan EfroniShie MannorPublished in: CoRR (2019)
Keyphrases
- global convergence
- trust region
- global optimum
- line search
- optimization methods
- newton method
- optimization method
- unconstrained optimization
- convergence analysis
- objective function
- faster convergence
- markov decision processes
- simulated annealing
- convergence speed
- risk minimization
- convergence rate
- optimization problems
- optimal solution
- search space
- step size
- particle swarm
- regularized least squares
- reinforcement learning
- lower bound
- conjugate gradient
- support vector machine
- fuzzy logic
- optimization procedure
- swarm intelligence