Near-Optimal Adversarial Reinforcement Learning with Switching Costs.

Ming Shi Yingbin Liang Ness B. Shroff

Published in: ICLR (2023)

Keyphrases

reinforcement learning
switching costs
multi agent
prior studies
state space
individual level
learning process
markov decision processes
online services
network effects
dynamic programming
wireless networks
end to end
optimal control