Dynamic Colocation Policies with Reinforcement Learning.

Yuhao Li Dan Sun Benjamin C. Lee

Published in: ACM Trans. Archit. Code Optim. (2020)

Keyphrases

reinforcement learning
optimal policy
function approximation
machine learning
robotic control
policy search
markov decision processes
data structure
case study
real time
dynamic environments
dynamic programming
model free
temporal difference
reward function
control policies
fitted q iteration