Learning in Non-Cooperative Configurable Markov Decision Processes.

Giorgia Ramponi Alberto Maria Metelli Alessandro Concetti Marcello Restelli

Published in: NeurIPS (2021)

Keyphrases

markov decision processes
cooperative
reinforcement learning
learning algorithm
model based reinforcement learning
stochastic games
dynamic programming
infinite horizon
state space
least squares
finite state
partially observable
multi agent systems
planning under uncertainty
state abstraction