Human-Behavior Learning for Infinite-Horizon Optimal Tracking Problems of Robot Manipulators.

Adolfo Perrusquía Wen Yu

Published in: CDC (2021)

Keyphrases

human behavior
infinite horizon
robot manipulators
reinforcement learning
optimal solution
dynamic programming
optimal control
finite horizon
single item
real time
learning algorithm
partially observable
markov decision process
stochastic demand