SDV: Simple Double Validation Model-Based Offline Reinforcement Learning.

Xun Wang Haonan Chen Junming Yang Zhuzhong Qian Bolei Zhang

Published in: ECAI (2023)

Keyphrases

reinforcement learning
model free
function approximation
real time
databases
machine learning
objective function
neural network
genetic algorithm
learning algorithm
knowledge base
data sets
optimal solution
support vector
expert systems
artificial neural networks
active learning