Inverse modeling of non-cooperative agents via mixture of utilities

We describe a new method of parametric utility learning for non-cooperative, continuous games using a probabilistic interpretation for combining multiple utility functions - thereby creating a mixture of utilities - under non-spherical noise terms. We present an adaptation of mixture of regression models that takes in to account heteroskedasticity. We show the performance of the proposed method by estimating the utility functions of players using data from a social game experiment designed to encourage energy efficient behavior amongst building occupants. Using occupant voting data we simulate the new game defined by the estimated mixture of utilities and show that the resulting forecast is more accurate than robust utility learning methods such as constrained Feasible Generalized Least Squares (cFGLS), ensemble methods such as bagging, and classical methods such as Ordinary Least Squares (OLS).

[1]  J. Goodman.  Note on Existence and Uniqueness of Equilibrium Points for Concave N-Person Games , 1965 .

[2]  A. Tversky,et al.  The framing of decisions and the psychology of choice. , 1981, Science.

[3]  D. Freedman,et al.  Bootstrapping a Regression Equation: Some Empirical Results , 1984 .

[4]  M. Gendreau.  On the location of eigenvalues of off-diagonal constant matrices , 1986 .

[5]  John H. Sheesley,et al.  Quality Engineering in Production Systems , 1988 .

[6]  S. Flåm.  Solving non-cooperative games by continuous subgradient projection methods , 1990 .

[7]  Lei Xu,et al.  An experimental comparative study on several soft and hard-cut EM algorithms for mixture of experts , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).

[8]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction , 2001, Springer Series in Statistics.

[9]  Francisco Cribari-Neto,et al.  Asymptotic inference under heteroskedasticity of unknown form , 2004, Comput. Stat. Data Anal..

[10]  David A. Freedman,et al.  Statistical Models: Theory and Practice: References , 2005 .

[11]  Christoph F. Reinhart,et al.  Adding advanced behavioural models in whole building energy simulation: A study on the total energy impact of manual and automated lighting control , 2006 .

[12]  Rob J Hyndman,et al.  Another look at measures of forecast accuracy , 2006 .

[13]  M. Boman,et al.  Energy Saving and Added Customer Value in Intelligent Buildings , 2007 .

[14]  Mohammed H. Albadi,et al.  A summary of demand response in electricity markets , 2008 .

[15]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition , 2001, Springer Series in Statistics.

[16]  S. Mitter,et al.  Dynamic Pricing and Stabilization of Supply and Demand in Modern Electric Power Grids , 2010, 2010 First IEEE International Conference on Smart Grid Communications.

[17]  M Morari,et al.  Energy efficient building climate control using Stochastic Model Predictive Control and weather predictions , 2010, Proceedings of the 2010 American Control Conference.

[18]  Stephen P. Boyd,et al.  Imputing a convex objective function , 2011, 2011 IEEE International Symposium on Intelligent Control.

[19]  Johanna L. Mathieu,et al.  Quantifying Changes in Building Electricity Use, With Application to Demand Response , 2011, IEEE Transactions on Smart Grid.

[20]  Francesco Borrelli,et al.  A distributed predictive control approach to building temperature regulation , 2011, Proceedings of the 2011 American Control Conference.

[21]  Duncan S. Callaway,et al.  Using Residential Electric Loads for Fast Demand Response: The Potential Resource and Revenues, the Costs, and Policy Recommendations , 2012 .

[22]  David E. Culler,et al.  Identifying models of HVAC systems using semiparametric regression , 2012, 2012 American Control Conference (ACC).

[23]  Henrik Ohlsson,et al.  Incentive Design and Utility Learning via Energy Disaggregation , 2013, 1312.1394.

[24]  Julian Padget,et al.  'just enough' sensing to ENLITEN: a preliminary demonstration of sensing strategy for the 'energy literacy through an intelligent home energy advisor' (ENLITEN) project , 2013, e-Energy '13.

[25]  Ming Jin,et al.  Social game for building energy efficiency: Incentive design , 2014, 2014 52nd Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[26]  Jinwen Ma,et al.  A Precise Hard-Cut EM Algorithm for Mixtures of Gaussian Processes , 2014, ICIC.

[27]  Ming Jin,et al.  Social Game for Building Energy Efficiency: Utility Learning, Simulation, and Analysis , 2014, ArXiv.

[28]  Ming Jin,et al.  PresenceSense: zero-training algorithm for individual presence detection based on power monitoring , 2014, BuildSys@SenSys.

[29]  Lillian J. Ratliff,et al.  Incentivizing Efficiency in Societal-Scale Cyber-Physical Systems , 2015 .

[30]  S. Shankar Sastry,et al.  On the Characterization of Local Nash Equilibria in Continuous Games , 2014, IEEE Transactions on Automatic Control.

[31]  Ioannis C. Konstantakopoulos,et al.  Smart building energy efficiency via social game: a robust utility learning framework for closing–the–loop , 2016, 2016 1st International Workshop on Science of Smart City Operations and Platforms Engineering (SCOPE) in partnership with Global City Teams Challenge (GCTC) (SCOPE - GCTC).