From Optimization to Control: Quasi Policy Iteration.
Mohamad Amin Sharifi KolarijaniPeyman Mohajerin EsfahaniPublished in: CoRR (2023)
Keyphrases
- policy iteration
- markov decision processes
- optimal control
- reinforcement learning
- model free
- control system
- sample path
- least squares
- optimization algorithm
- control problems
- optimal policy
- fixed point
- dynamic programming
- evolutionary algorithm
- state space
- finite state
- temporal difference
- markov decision process
- policy evaluation
- machine learning