Tsallis Entropy Regularization for Linearly Solvable MDP and Linear Quadratic Regulator.

Yota Hashizume Koshi Oishi Kenji Kashima

Published in: CoRR (2024)

Keyphrases

linear quadratic
optimal control
closed loop
dynamical systems
vector valued
markov decision processes
gaussian model
special case
state space
reinforcement learning
dynamic programming
reproducing kernel hilbert space
computational complexity
control system
feature vectors
maximum likelihood