Safe Reinforcement Learning by Imagining the Near Future.

Garrett Thomas Yuping Luo Tengyu Ma

Published in: CoRR (2022)

Keyphrases

reinforcement learning
policy search
reinforcement learning algorithms
temporal difference
model free
machine learning
bayesian networks
function approximation
long term
dynamic programming
state space
learning process
action selection
databases
multi agent
decision trees
e learning
learning algorithm
real world