Policy Gradient Optimization of Thompson Sampling Policies.
Seungki MinCiamac C. MoallemiDaniel J. RussoPublished in: CoRR (2020)
Keyphrases
- parametric optimization
- policy gradient
- policy gradient methods
- policy search
- optimization algorithm
- reinforcement learning
- optimal policy
- function approximation
- partially observable markov decision processes
- model free reinforcement learning
- natural actor critic
- actor critic
- reinforcement learning methods
- gradient method
- average reward
- optimal control
- optimization method
- markov decision processes
- optimization problems
- state space
- dynamic programming