Policy Evaluation in Distributional LQR.
Zifan WangYulong GaoSiyi WangMichael M. ZavlanosAlessandro AbateKarl Henrik JohanssonPublished in: CoRR (2023)
Keyphrases
- policy evaluation
- least squares
- monte carlo
- reinforcement learning
- temporal difference
- policy iteration
- markov decision processes
- model free
- optimal control
- variance reduction
- matrix inversion
- function approximation
- semi parametric
- optimal policy
- linear regression
- evaluation function
- gaussian process
- partially observable markov decision processes
- statistical inference
- importance sampling
- action selection
- cost function
- state space
- partially observable
- supervised learning
- linear programming
- infinite horizon
- learning algorithm
- control strategy
- markov chain