A Hybrid Stochastic Policy Gradient Algorithm for Reinforcement Learning.
Nhan H. PhamLam M. NguyenDzung T. PhanPhuong Ha NguyenMarten van DijkQuoc Tran-DinhPublished in: AISTATS (2020)
Keyphrases
- reinforcement learning
- policy gradient
- learning algorithm
- optimal solution
- computational complexity
- dynamic programming
- actor critic
- np hard
- monte carlo
- function approximation
- convergence rate
- simulated annealing
- cost function
- search space
- natural gradient
- path planning
- markov decision processes
- state space
- reinforcement learning algorithms
- model free reinforcement learning