Policy Evaluation in Distributional LQR.
Zifan WangYulong GaoSiyi WangMichael M. ZavlanosAlessandro AbateKarl Henrik JohanssonPublished in: L4DC (2023)
Keyphrases
- policy evaluation
- least squares
- reinforcement learning
- temporal difference
- monte carlo
- policy iteration
- model free
- optimal control
- markov decision processes
- matrix inversion
- semi parametric
- function approximation
- variance reduction
- optimal policy
- statistical inference
- partially observable markov decision processes
- state space
- reinforcement learning algorithms
- action selection
- finite state
- fixed point
- regression model
- support vector machine