Login / Signup
On Regret-Optimal Learning in Decentralized Multiplayer Multiarmed Bandits.
Naumaan Nayyar
Dileep M. Kalathil
Rahul Jain
Published in:
IEEE Trans. Control. Netw. Syst. (2018)
Keyphrases
</>
learning process
online learning
worst case
learning algorithm
learning systems
prior knowledge
reinforcement learning
multi armed bandits
distributed systems
mobile robot
active learning
loss function
learning tasks
learning problems
inductive inference
multi armed bandit
cooperative