MARKOVIAN EMBEDDINGS FOR COALITIONAL BARGAINING GAMES

Lucia Cipolina-Kun

Keywords: game theory, bargaining, multi-agent reinforcement learning, stochastic processes

TL;DR: Convert a non-markovian process into a markovian one through 'markovian embeddings'

Abstract: We examine the Markovian properties of coalition bargaining games, in particular, the case where past rejected proposals cannot be repeated. We propose a Markovian embedding with filtrations to render the sates Markovian and thus, fit into the framework of stochastic games.