A Multiplicative Value Function for Safe and Efficient Reinforcement Learning.

Nick Bührer Zhejun Zhang Alexander Liniger Fisher Yu Luc Van Gool

Published in: IROS (2023)

Keyphrases

reinforcement learning
machine learning
real time
neural network
genetic algorithm
state space
computationally efficient
markov decision processes
database
case study
similarity measure
lightweight
computationally expensive
function approximation