Login / Signup
Verifiably safe exploration for end-to-end reinforcement learning.
Nathan Hunt
Nathan Fulton
Sara Magliacane
Trong Nghia Hoang
Subhro Das
Armando Solar-Lezama
Published in:
HSCC (2021)
Keyphrases
</>
end to end
reinforcement learning
active exploration
action selection
ad hoc networks
optimal policy
multipath
admission control
wireless ad hoc networks
high bandwidth
markov decision processes
content delivery
congestion control
application layer
multi hop
rate allocation
response time