On-policy Approximate Dynamic Programming for Optimal Control of non-linear systems.

Shalini K D. Vrushabh K. Sonam

Published in: CoDIT (2020)

Keyphrases

optimal control
approximate dynamic programming
average cost
dynamic programming
policy iteration
reinforcement learning
infinite horizon
control problems
actor critic
linear program
control strategy
optimal control problems
data mining
multistage
computational complexity
optimal solution
control policy