To Switch or Not to Switch? Balanced Policy Switching in Offline Reinforcement Learning.

Tao Ma Xuzhi Yang Zoltan Szabo

Published in: CoRR (2024)

Keyphrases

reinforcement learning
optimal policy
high speed
action selection
policy search
function approximation
switched networks
machine learning
multi agent
dynamic programming
policy making
robotic control
partially observable environments
state space