When is Mean-Field Reinforcement Learning Tractable and Relevant?

Batuhan Yardim Artur Goldman Niao He

Published in: AAMAS (2024)

Keyphrases

reinforcement learning
function approximation
markov decision processes
np hard
learning algorithm
lower bound
np complete
optimal policy
closely related
robotic control
optimal solution
computational complexity
supervised learning
model free
temporal difference
statistical mechanics