Regret Bounds for Decentralized Learning in Cooperative Multi-Agent Dynamical Systems.

Seyed Mohammad Asghari Yi Ouyang Ashutosh Nayyar

Published in: UAI (2020)

Keyphrases

dynamical systems
learning process
predictive state representations
learning algorithm
reinforcement learning
hidden markov models
supervised learning
objective function
multi class
mutual information
online learning
learning problems
learning theory
nonlinear dynamical systems