Conservative and Adaptive Penalty for Model-Based Safe Reinforcement Learning.

Yecheng Jason Ma Andrew Shen Osbert Bastani Dinesh Jayaraman

Published in: AAAI (2022)

Keyphrases

reinforcement learning
model free
function approximation
machine learning
learning capabilities
reinforcement learning algorithms
adaptive control
data sets
genetic algorithm
multi agent
data driven
penalty function
database
optimal control
dynamic programming
control system
learning algorithm
neural network