Policy iteration for the deterministic control problems - a viscosity approach.
Wenpin TangHung Vinh TranYuming Paul ZhangPublished in: CoRR (2023)
Keyphrases
- control problems
- policy iteration
- reinforcement learning
- optimal control
- markov decision processes
- model free
- sample path
- infinite horizon
- optimal policy
- temporal difference
- average reward
- approximate dynamic programming
- fixed point
- queueing systems
- function approximation
- state space
- markov decision process
- dynamic programming
- least squares
- markov decision problems
- finite state
- adaptive control
- control strategy
- learning algorithm
- action selection
- differential equations
- supervised learning
- reinforcement learning algorithms
- partially observable