Login / Signup
TTOpt: A Maximum Volume Quantized Tensor Train-based Optimization and its Application to Reinforcement Learning.
Konstantin Sozykin
Andrei Chertkov
Roman Schutski
Anh-Huy Phan
Andrzej S. Cichocki
Ivan V. Oseledets
Published in:
NeurIPS (2022)
Keyphrases
</>
reinforcement learning
optimization algorithm
markov decision processes
high order
global optimization
function approximation
optimization process
maximum number
neural network
state space
higher order
learning problems
machine learning
evolutionary algorithm
least squares
transfer learning