Login / Signup
Verifiably Safe Exploration for End-to-End Reinforcement Learning.
Nathan Hunt
Nathan Fulton
Sara Magliacane
Nghia Hoang
Subhro Das
Armando Solar-Lezama
Published in:
CoRR (2020)
Keyphrases
</>
end to end
reinforcement learning
active exploration
action selection
congestion control
multipath
high bandwidth
wireless ad hoc networks
ad hoc networks
markov decision processes
application layer
rate allocation
multimedia
optimal policy
content delivery