Login / Signup
A Multifidelity Sim-to-Real Pipeline for Verifiable and Compositional Reinforcement Learning.
Cyrus Neary
Christian Ellis
Aryaman Singh Samyal
Craig Lennon
Ufuk Topcu
Published in:
CoRR (2023)
Keyphrases
</>
reinforcement learning
function approximation
sufficient conditions
neural network
real world
learning algorithm
action selection
data sets
search engine
computer vision
decision trees
multi agent
learning process
dynamic environments
markov decision processes
processing pipeline