Publications

2021

 
Stratis Skoulakis, Tanner Fiez, Ryann Sim, Georgios Piliouras, Lillian J. Ratliff. Evolutionary Game Theory Squared: Evolving Agents in Endogenously Evolving Games. AAAI Conference on Artificial Intelligence, 2021
 
Liyuan Zheng, Tanner Fiez, Zane Alumbaugh, Benjamin Chasnov, Lillian J. Ratliff. Stackelberg Actor-Critic: A Game-Theoretic Perspective, AAAI RLG Workshop, 2021.
 
Tanner Fiez, Lillian J. Ratliff. Gradient Descent-Ascent Provably Converges to Strict Local Minmax Equilibria with a Finite Timescale Separation. AAAI RLG Workshop 2021

2020
 
Tanner Fiez, Lillian J. Ratliff. Gradient Descent-Ascent Provably Converges to Strict Local Minmax Equilibria with a Finite Timescale Separation. 2020 (under review, arxiv)
 
Sarah Li, Lillian J. Ratliff, Behcet Acikmese. Disturbance Decoupling for Gradient-based Multi-Agent Learning with Quadratic Costs. IEEE Control System Letters (L-CSS) and CDC, 2020.
 
Tanner Fiez, Benjamin Chasnov, Lillian J. Ratliff. Implicit Learning Dynamics in Stackelberg Games: Equilibria Characterization, Convergence Analysis, and Empirical Study. International Conference on Machine Learning (ICML), 2020.
 
Tanner Fiez, Nihar Shah, and Lillian J. Ratliff. A Super* Algorithm to Determine Orderings of Items to Show Users. Uncertainty in Artificial Intelligence (UAI), 2020.
 
Eric Mazumdar, Lillian J. Ratliff, Micheal I. Jordan, S. Shankar Sastry. Policy-Gradient Algorithms Have No Guarantees of Convergence in Linear Quadratic Games. Autonomous Agents and Multi-Agent Systems (AAMAS), 2020. (arxiv)
 
Benjamin Chasnov, Daniel Calderone, Behcet Acikmese, Samuel Burden, Lillian J. Ratliff. The Local Stability of Equilibria in Two-Player Continuous Games. CDC, 2020.

2019
 
Tanner Fiez, Lalit Jain, Kevin Jamieson, and Lillian J. Ratliff. Sequential Experimental Design for Transductive Linear Bandits. NeuRIPs, arxiv:1906.08399, 2019. [ bib ] (arxiv)
 
Eric Mazumdar, Lillian J. Ratliff, S. Shankar Sastry. On the Convergence of Gradient Based Learning in Continuous Games. SIAM Journal on Mathematics of Data Science (SIMODS), 2019. (pdf)
 
Jingjing Bu, Lillian J. Ratliff, Mehran Mesbahi. Global Convergence of Policy Gradient for Sequential Zero-Sum Linear Quadratic Dynamic Games. arxiv:1911.04672, 2019. [ bib ] (arxiv)
 
Tanner Fiez, Benjamin Chasnov, Lillian J. Ratliff. Convergence of Learning in Stackelberg Games. Smooth Games Optimization and Machine Learning Workshop: Bridging Game Theory and Deep Learning, NeuRIPS, 2019.
 
Benjamin Chasnov, Tanner Fiez, Lillian J. Ratliff. Opponent Anticipation via Conjectural Variations. Smooth Games Optimization and Machine Learning Workshop: Bridging Game Theory and Deep Learning, NeuRIPS, 2019.
 
Eric Mazumdar, Lillian J. Ratliff, Shankar Sastry, Michael I. Jordan. Policy Gradient in Linear Quadratic Dynamic Games Has No Convergence Guarantees. Smooth Games Optimization and Machine Learning Workshop: Bridging Game Theory and Deep Learning, NeuRIPS, 2019.
 
Tanner Fiez, Nihar Shah, and Lillian J. Ratliff. A Super* Algorithm to Determine Orderings of Items to Show Users. workshop paper for Real-world Sequential Decision Making workshop at ICML, 2019. [ bib ] (pdf)
 
Tanner Fiez, Benjamin Chasnov, and Lillian J. Ratliff. Convergence of Learning Dynamics in Stackelberg Games. arxiv:1906.01217, 2019. [ bib ] (arxiv)
 
Benjamin Chasnov, Lillian J. Ratliff, Eric Mazumdar, and Samuel Burden. Convergence Guarantees for Gradient-Based Learning in Continuous Games. Uncertainty in Artificial Intelligence, 2019. [ bib ] (link)
 
Shahriar Talebi, Siavash Alemzadeh, Lillian J. Ratliff, and Mehran Mesbahi. Distributed Learning in Network Games: A Dual Averaging Approach. In Proceedings of the IEEE Conference on Decision and Control, 2019. [ bib ] (link)
 
Sarah H.Q. Li, Daniel Calderone, Lillian J. Ratliff, and Behcet Acikmese. Sensitivity Analysis for MDP Congestion Games. In Proceedings of the IEEE Conference on Decision and Control, 2019. [ bib ]
 
Yagiz Savas, Vijay Gupta, Melkior Ornik, , Lillian J. Ratliff, and Ufuk Topcu. Incentive Design for Temporal Logic Objectives. In Proceedings of the IEEE Conference on Decision and Control, 2019. [ bib ]
 
Eric Mazumdar and Lillian J. Ratliff. Local Nash Equilibria are Isolated, Strict Local Nash Equilibria in 'Almost All' Zero-Sum Continuous Games. In Proceedings of the IEEE Conference on Decision and Control, 2019. [ bib ] (arxiv)
 
Daniel Calderone and Lillian J. Ratliff. Multi-Dimensional Continuous Type Population Potential Games. In Proceedings of the IEEE Conference on Decision and Control, 2019. [ bib ]
 
Chase Dowling, Lillian J. Ratliff, and Baosen Zhang. Modeling Curbside Parking as a Network of Finite Capacity Queues. In IEEE Transactions on Intelligent Transportation Systems (accepted for publication), 2019. [ bib ]
 
Tyler Westenbroek, Roy Dong, Lillian J. Ratliff, and S. Shankar Sastry. Statistical Estimation with Strategic Data Sources in Competitive Settings. In IEEE Transactions on Automatic Control, 2019. [ bib ] (pdf)
 
Lillian J. Ratliff and Eric Mazumdar. Inverse Risk-Sensitive Reinforcement Learning. In IEEE Transactions on Automatic Control, 2019. [ bib ] (pdf)
 
Tanner Fiez and Lillian J. Ratliff. Data-Driven Spatio-Temporal Analysis of Curbside Parking Demand. accepted for publication in IEEE Transactions on Intelligent Transportation Systems, 2019 (submitted 2017). [ bib ]
Supplemental Material UAI 2019 Paper

Working Paper: Gradient Conjectures for Strategic Multi-Agent Learning, Chasnov, Fiez, Ratliff, 2019.

2018
 
Lillian J. Ratliff, Roy Dong, Shreyas Sekar, and Tanner Fiez. A Perspective on Incentive Design: Challenges and Opportunities. Annual Reviews of Controls, Robotics, and Autonomous Systems (to appear), 2018. [ bib ] (pdf)
 
Esther Ling, Lillian J. Ratliff, and Samuel Coogan. Koopman Operator Approach for Instability Detection and Mitigation in Signalized Traffic. In IEEE ITSC, 2018. [ bib ]
 
Hui (Sarah) Li, Yue Yu, Daniel Calderone, Lillian J. Ratliff, and Behcet Acikmese. Tolling for Constraint Satisfaction in Markov Decision Process Congestion Games. In under review, 2018. [ bib ]
 
Eric Mazumdar and Lillian J. Ratliff. On the Convergence of Competitive, Multi-Agent Gradient-Based Learning. arXiv:1804.05464, 2018. [ bib ]
 
Benjamin Chasnov, Lillian J. Ratliff, Daniel Calderone, Eric Mazumdar, and Samuel Burden. Finite-Time Convergence of Gradient-Based Learning in Continuous Games. AAAI-19 Workshop on Reinforcement Learning in Games, 2018. [ bib ]
 
Tanner Fiez, Shreyas Sekar, Liyuan Zheng, and Lillian J. Ratliff. Combinatorial Bandits for Incentivizing Agents with Dynamic Preferences. In Uncertainty in Artificial Intelligence, 2018. [ bib ] (pdf)
 
Lillian J. Ratliff and Tanner Fiez. Adaptive Incentive Design. (under review; IEEE TAC), 2018. [ bib ]
 
Shreyas Sekar, Liyuan Zheng, Lillian J. Ratliff, and Baosen Zhang. Uncertainty in Multi-Commodity Routing Networks: When does it help? In Proceedings of the American Control Conference, 2018. [ bib ]
 
Roy Dong, Alvaro A. Cárdenas, Lillian J. Ratliff, Henrik Ohlsson, and Shankar Sastry. Quantifying the Utility-Privacy Tradeoff in the Smart Grid. ACM Transactions on Cyber-Physical Systems, 2018. [ bib ]
 
Tanner Fiez, Lillian J. Ratliff, Chase Dowling, and Baosen Zhang. Data-Driven Spatio-Temporal Modeling of Parking Demand. In Proceedings of the American Control Conference, 2018. [ bib ]
2017
 
Ioannis Konstantakopoulos*, Lillian J. Ratliff*, Ming Jin, S. Shankar Sastry, and Costas Spanos. A Robust Utility Learning Framework via Inverse Optimization. IEEE Transactions on Control Systems Technology, PP(99):1--17, 2017. [ bib | DOI ]
 
Shreyas Sekar, Liyuan Zheng, Lillian J. Ratliff, and Baosen Zhang. Uncertainty in Multi-Commodity Routing Networks: When does it help? arxiv:1709.08441, 2017. [ bib ]
 
Lillian Ratliff, Shreyas Sekar, Liyuan Zheng, and Tanner Fiez. Incentives in the Dark: Multi-armed Bandits for Evolving Users with Unknown Type. in review (arXiv:1803.04008), 2017. [ bib ]
 
Kamil Nar, Lillian J. Ratliff, and S. Shankar Sastry. Learning Prospect Theory Value Function and Reference Point of a Sequential Decision Maker. In Proceedings of the 56th IEEE Conference on Decision and Control, 2017. [ bib ]
 
Eric Mazumdar, Lillian J. Ratliff, Tanner Fiez, and S. Shankar Sastry. Gradient--Based Inverse Risk-Sensitive Reinforcement Learning with Applications. In Proceedings of the 56th IEEE Conference on Decision and Control, 2017. [ bib ]
 
Chase Dowling, Tanner Fiez, Lillian J. Ratliff, and Baosen Zhang. Optimizing Curbside Parking Resources Subject to Congestion Constraints. In Proceedings of the 56th IEEE Conference on Decision and Control, 2017. [ bib ]
 
Tyler Westenbroek, Roy Dong, Lillian J. Ratliff, and S. Shankar Sastry. Statistical Estimation in Competitive Settings with Strategic Data Sources. In Proceedings of the 56th IEEE Conference on Decision and Control, 2017. [ bib ]
 
Chase Dowling, Tanner Fiez, Lillian J. Ratliff, and Baosen Zhang. How Much Urban Traffic is Searching for Parking? In arXiv:1702.06156, 2017. [ bib ]
 
Ioannis Konstantakopoulos*, Lillian J. Ratliff*, Ming Jin, and Costas Spanos. Leveraging Correlations in Utility Learning. In Proceedings of the American Control Conference, 2017. [ bib ]
2016
 
L. J. Ratliff, C. Dowling, E. Mazumdar, and B. Zhang. To observe or not to observe: Queuing game framework for urban parking. In Proceedings of the IEEE 55th Conference on Decision and Control (CDC), pages 5286--5291, Dec 2016. [ bib | DOI ]
 
D. Calderone, E. Mazumdar, L. J. Ratliff, and S. S. Sastry. Understanding the impact of parking on urban mobility via routing games on queue-flow networks. In Proceedings of the IEEE 55th Conference on Decision and Control, pages 7605--7610, Dec 2016. [ bib | DOI ]
 
Ioannis C. Konstantakopoulos, Lillian J. Ratliff, Ming Jin, Costas Spanos, and S. Shankar Sastry. Smart building energy efficiency via social game: a robust utility learning framework for closing-the-loop. In Proceedings of the 1st International Workshop on Science of Smart City Operations and Platforms Engineering (SCOPE) in partnership with Global City Teams Challenge (GCTC) (SCOPE - GCTC), pages 1--6, April 2016. [ bib | DOI ]
 
I. C. Konstantakopoulos, L. J. Ratliff, M. Jin, C. J. Spanos, and S. S. Sastry. Inverse modeling of non-cooperative agents via mixture of utilities. In Proceedings of the IEEE 55th Conference on Decision and Control, pages 6327--6334, Dec 2016. [ bib | DOI ]
 
Lillan J. Ratliff, Samuel A. Burden, and S. Shankar Sastry. On the Characterization of Local Nash Equilibria in Continuous Games. IEEE Transactions on Automatic Control, 61(8):2301--2307, Aug. 2016. [ bib | DOI ]
2015
 
Incentivizing Efficiency in Societal-Scale Cyber-Physical Systems. Lillian J. Ratliff. PhD thesis, University of California, Berkeley, 2015. [ bib ]
 
D. Scobee, L. Ratliff, R. Dong, H. Ohlsson, M. Verhaegen, and S. S. Sastry. Nuclear norm minimization for blind subspace identification (N2BSID). In Proceedings of the 54th IEEE Conference on Decision and Control, pages 2127--2132, Dec 2015. [ bib | DOI ]
 
Ming Jin, Lillian J. Ratliff, Ioannis Konstantakopoulos, Costas Spanos, and Shankar Sastry. REST: A Reliable Estimation of Stopping Time Algorithm for Social Game Experiments. In Proceedings of the ACM/IEEE Sixth International Conference on Cyber-Physical Systems, ICCPS '15, pages 90--99, New York, NY, USA, 2015. ACM. [ bib | DOI | http ]
 
D. J. Calderone, L. J. Ratliff, and S. S. Sastry. Lane pricing via decision-theoretic lane changing model of driver behavior. In Proceedings of the 54th IEEE Conference on Decision and Control, pages 3457--3462, Dec 2015. [ bib | DOI ]
2014
 
Lillian J. Ratliff, Roy Dong, Henrik Ohlsson, and S. Shankar Sastry. Energy Efficiency via Incentive Design and Utility Learning. In Proceedings of the 3rd International Conference on High Confidence Networked Systems, HiCoNS '14, pages 57--58, New York, NY, USA, 2014. ACM. [ bib | DOI ]
 
Roy Dong, Lillian Ratliff, Henrik Ohlsson, and S. Shankar Sastry. Fundamental Limits of Nonintrusive Load Monitoring. In Proceedings of the 3rd International Conference on High Confidence Networked Systems, HiCoNS '14, pages 11--18, New York, NY, USA, 2014. ACM. [ bib | DOI ]
 
Henrik Ohlsson, Lillian Ratliff, Roy Dong, and S. Shankar Sastry. Blind Identification via Lifting. In Proceedings of the 19th World Congress of the International Federation of Automatic Control, volume 47, pages 10367--10372, 2014. [ bib | DOI ]
 
Daniel Calderone, Lillian J. Ratliff, and S. Shankar Sastry. Pricing for Coordination in Open--Loop Differential Games. IFAC Proceedings Volumes, 47(3):9001 -- 9006, 2014. [ bib | DOI ]
 
L. J. Ratliff, R. Dong, H. Ohlsson, A. A. Cárdenas, and S. S. Sastry. Privacy and customer segmentation in the smart grid. In Proceedings of the 53rd IEEE Conference on Decision and Control, pages 2136--2141, Dec 2014. [ bib | DOI ]
 
L. J. Ratliff, S. A. Burden, and S. S. Sastry. Genericity and structural stability of non-degenerate differential Nash equilibria. In Proceedings of the American Control Conference, pages 3990--3995, June 2014. [ bib | DOI ]
 
L. J. Ratliff, M. Jin, I. C. Konstantakopoulos, C. Spanos, and S. S. Sastry. Social game for building energy efficiency: Incentive design. In Proceedings of the 52nd Annual Allerton Conference on Communication, Control, and Computing, pages 1011--1018, Sept 2014. [ bib | DOI ]
 
Lillian J Ratliff, Roy Dong, Henrik Ohlsson, and S Shankar Sastry. Incentive Design and Utility Learning via Energy Disaggregation. In Proceedings of the 19th World Congress of the International Federation of Automatic Control, volume 47, pages 3158--3163, 2014. [ bib | DOI ]
 
Lillian Ratliff, Carlos Barreto, Roy Dong, Henrik Ohlsson, Alvaro A. Cardenas, and S. Shankar Sastry. Effects of Risk on Privacy Contracts for Demand-Side Management. arxiv:1409.7926v3, 2014. [ bib ]
 
P. Kachroo, L. Ratliff, and S. Sastry. Analysis of the Godunov-Based Hybrid Model for Ramp Metering and Robust Feedback Control Design. IEEE Transactions on Intelligent Transportation Systems, 15(5):2132--2142, Oct 2014. [ bib | DOI ]
2013
 
Aaron Bestick, Lillian J. Ratliff, Posu Yan, Ruzena Bajcsy, and S. Shankar Sastry. An Inverse Correlated Equilibrium Framework for Utility Learning in Multiplayer, Noncooperative Settings. In Proceedings of the 2nd ACM International Conference on High Confidence Networked Systems, HiCoNS '13, pages 9--16, New York, NY, USA, 2013. ACM. [ bib | DOI ]
 
Henrik Ohlsson, Lillian Ratliff, Roy Dong, and S. Shankar Sastry. Blind Identification of ARX Models with Piecewise Constant Inputs. arxiv:1303.6719, 2013. [ bib ]
 
R. Dong, L. J. Ratliff, H. Ohlsson, and S. S. Sastry. Energy disaggregation via adaptive filtering. In Proceedings of the 51st Annual Allerton Conference on Communication, Control, and Computing, pages 173--180, Oct 2013. [ bib | DOI ]
 
L. J. Ratliff, S. A. Burden, and S. S. Sastry. Characterization and computation of local Nash equilibria in continuous games. In Proceedings of the 51st Annual Allerton Conference on Communication, Control, and Computing, pages 917--924, Oct 2013. [ bib | DOI ]
 
D. J. Calderone, L. J. Ratliff, and S. S. Sastry. Pricing design for robustness in linear quadratic games. In Proceedings of the 52nd IEEE Conference on Decision and Control, pages 4349--4354, Dec 2013. [ bib | DOI ]
 
L. J. Ratliff, R. Dong, H. Ohlsson, A. A. Cárdenas, and S. S. Sastry. Privacy and customer segmentation in the smart grid. In Proceedings of the 53rd IEEE Conference on Decision and Control, pages 2136--2141, Dec 2014. [ bib | DOI ]
 
S. Coogan, L. J. Ratliff, D. Calderone, C. Tomlin, and S. S. Sastry. Energy management via pricing in LQ dynamic games. In Proceedings of the American Control Conference, pages 443--448, June 2013. [ bib | DOI ]
 
R. Dong, L. Ratliff, H. Ohlsson, and S. S. Sastry. A dynamical systems approach to energy disaggregation. In Proceedings of the 52nd IEEE Conference on Decision and Control, pages 6335--6340, Dec 2013. [ bib | DOI ]
2012
 
L. J. Ratliff, S. Coogan, D. Calderone, and S. S. Sastry. Pricing in linear-quadratic dynamic games. In Proceedings of the 50th Annual Allerton Conference on Communication, Control, and Computing (Allerton), pages 1798--1805, Oct 2012. [ bib | DOI ]
2010
 
Lillian J. Ratliff and Pushkin Kachroo. Validating numerically consistent macroscopic traffic models using microscopic data. Transportation Research Board Annual Meeting, 2010. [ bib ]
Funding
This work is funded by the National Science Foundation (current: CNS-1736582, CNS-1836819, CNS-1931718, CNS-1907907, CNS-1844729, CNS-1952011; previous: CNS-1634136, CNS-1646912, CNS-1656873) and the Office of Naval Research (current: ONR YIP)

Awards & Recognition
  • 2020 ONR Young Investigator Award
  • 2019 National Academy of Engineering, Invited Speaker for the China-America Frontiers of Engineering Symposium
  • 2019 National Science Foundation CAREER Award
  • 2017 National Science Foundation CISE Research Initiation Initiative Award
  • 2009 National Science Foundation Graduate Research Fellowship