Generalized Policy Iteration using Tensor Approximation for Hybrid Control.
Suhan ShettyTeng XueSylvain CalinonPublished in: ICLR (2024)
Keyphrases
- policy iteration
- linear approximation
- markov decision processes
- optimal control
- control system
- model free
- reinforcement learning
- optimal policy
- fixed point
- least squares
- higher order
- finite state
- sample path
- temporal difference
- control problems
- average reward
- search algorithm
- control strategy
- dynamic programming
- bayesian networks