no code implementations • 23 May 2023 • Max Olan Smith, Michael P. Wellman
We investigate the potential gain from co-learning these elements: a world model for dynamics and an empirical game for strategic interactions.
no code implementations • 1 Feb 2023 • Zun Li, Marc Lanctot, Kevin R. McKee, Luke Marris, Ian Gemp, Daniel Hennes, Paul Muller, Kate Larson, Yoram Bachrach, Michael P. Wellman
Multiagent reinforcement learning (MARL) has benefited significantly from population-based and game-theoretic training regimes.
no code implementations • 16 Jan 2014 • Yagil Engel, Michael P. Wellman
We develop multiattribute auctions that accommodate generalized additive independent (GAI) preferences.
no code implementations • 27 Mar 2013 • Michael P. Wellman
Bayesian networks provide a probabilistic semantics for qualitative assertions about likelihood.
no code implementations • 27 Mar 2013 • Michael P. Wellman, David Heckerman
Architectures for uncertainty handling that take statements in the calculus as objects to be reasoned about offer the prospect of retaining normative status with respect to decision making while supporting the other tasks in uncertain reasoning.
no code implementations • 27 Mar 2013 • Michael P. Wellman
Functional dependencies restrict the potential interactions among variables connected in a probabilistic network.