Learning to Coordinate Efficiently: A Model-based Approach
By Ronen I. Brafman, Moshe Tennenholtz. 2003
45 citations recorded by the source corpus.
In common-interest stochastic games all players receive an identical payoff. Players participating in such games must learn to coordinate with each other in order to receive the highest-possible value. A number of reinforcement learning algorithms have been proposed for this problem, and some have been shown to converge to good solutions in the limit. In this paper we show that using very simple model-based algorithms, much better (i.e., polynomial) convergence rates can be attained. Moreover, our model-based algorithms are guaranteed to converge to the optimal value, unlike many of the existing algorithms.
Subfields: Artificial Intelligence, Management Science and Operations Research
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Shimon Whiteson
- Wendelin Böhmer
- Christian Schröder de Witt
- Jakob N. Foerster
- Philip H. S. Torr
- Gregory Farquhar
- Chongjie Zhang
- Chris Amato
In Management Science and Operations Research
- Shimon Whiteson
- Wendelin Böhmer
- Christian Schröder de Witt
- Tuomas Sandholm
- Gregory Farquhar
- Nadine Le Fort-Piat
- Guillaume J. Laurent
- Laëtitia Matignon
Citations in the corpus
- Multi-Agent Common Knowledge Reinforcement Learning (2018, background): “Brafman and Tennenholtz (2003) use a common-knowledge protocol to improve coordination in common interest stochastic games but, in contrast to our approach, establish common knowledge about agents’ action sets and not about subsets of their observation spaces.”
- Independent reinforcement learners in cooperative Markov games: a survey regarding coordination problems (2012, background): “A way of overcoming this problem could be that the agents explore or exploit in unison (Brafman & Tennenholtz, 2003).”
- Computing Equilibria in Multiplayer Stochastic Games of Imperfect Information (2009, background): “Other algorithms are guaranteed to converge to an optimal Nash equilibrium in team stochastic games—games in which all agents receive the same payoff [2, 14].”
- Efficient learning equilibrium (2004, methodology): “First, to compute the policies π, ρ that maximizes U(·, ·) we use the algorithm described in [5].”