An End-to-End Automatic Cache Replacement Policy Using Deep Reinforcement Learning.

Yang Zhou Fang Wang Zhan Shi Dan Feng

Published in: ICAPS (2022)

Keyphrases

end to end
replacement policy
reinforcement learning
web caching
hit rate
buffer management
prefetching
hit ratio
access patterns
proxy cache
wireless ad hoc networks
ad hoc networks
poisson process
admission control
congestion control
content delivery
dynamic programming
application layer
miss ratio
machine learning
optimal control
markov decision processes
optimal policy
state space
query processing