On the Convergence Rate of Off-Policy Policy Optimization Methods with Density-Ratio Correction.
Jiawei HuangNan JiangPublished in: AISTATS (2022)
Keyphrases
- optimization methods
- convergence rate
- density ratio
- global convergence
- gradient method
- convergence speed
- density ratio estimation
- least squares
- step size
- optimization method
- gravitational search algorithm
- learning rate
- optimization problems
- simulated annealing
- outlier detection
- stochastic methods
- primal dual
- particle swarm
- optimal policy
- semi parametric
- particle swarm optimization algorithm
- information retrieval
- semi supervised learning
- line search
- numerical stability
- support vector
- genetic algorithm