Ben Chasnov

About Me

I am a researcher in human-machine learning, at the intersection of robotics, game theory, dynamical systems. I am completing my PhD at the University of Washington in Seattle, WA.

Research

I am fourtunate to be advised by Prof. Sam Burden and Prof. Lillian Ratliff in the Electrical and Computer Engineering (ECE) department at UW. Our research focuses on how optimizers interact with each other (and with humans). We study multi-agent decision-making through the lens of game theory and bounded rationality and conduct online experiments to validate the theory. Our theory offers a compelling model for decision-making in continous action spaces when agents learn about each other, and our experiments that were conducted with annonymous participants also provide strong supporting evidence for the theory.

During my time at UW, I also collaborated with the Autonomous Control Laboratory (ACL) on human-machine interfaces and the Computational Neuroscience Center (CNC) community at UW on the co-adaptive interfaces.

My prior research at Harvey Mudd College was in the Lab for Autonomous and Intelligent Robotics (LAIR) on cooperative multi-agent underwater robotics and aerial vehicles, with an emphasis of deploying robot systems in challenging environments such as confined caves and open waters.

In my free time, I enjoy cooking, hiking, and music. I like to build things and dream up projects.

Pre-prints

• Benjamin J. Chasnov, Lillian J. Ratliff and Samuel A. Burden.
  Human adaptation to adaptive machines converges to game-theoretic equilibria.
  In submission, May 2023.

Publications

• Daniel J. Calderone, Benjamin J. Chasnov, Lillian J. Ratliff and Samuel A. Burden.
  Consistent Conjectural Variations Equilibrium: Characterization & Stability for a Class of Continuous Games
  In: IEEE Control Systems Letters (L-CSS), June 2023.
• Quoc-Liem Vu, Zane Alumbaugh, Ryan Ching, Quanchen Ding, Arnav Mahajan, Benjamin J. Chasnov, Samuel A. Burden, Lillian J Ratliff
  Stackelberg Policy Gradient: Evaluating the Performance of Leaders and Followers.
  In: ICLR 2022 Workshop on Gamification and Multiagent Solutions, May 2022.
• Liyuan Zheng, Tanner Fiez, Zane Alumbaugh, Benjamin J. Chasnov and Lillian Ratliff.
  Stackelberg Actor-Critic: Game-Theoretic Reinforcement Learning Algorithms.
  In: Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI), Feb. 2022.
• Skye Mceowen, Daniel Sullivan, Benjamin J. Chasnov, Dan Calderone, Oliver Sheridan and Behcet Acikmese.
  Visual Modeling System for Real-Time Optimal Trajectory Planning for Autonomous Aerial Drones.
  In: IEEE Aerospace Conference (AeroConf), Mar 2022.
• Benjamin J. Chasnov, Dan Calderone, Behcet Acikmese, Samuel A. Burden, Lillian J. Ratliff.
  Stability of Gradient Learning Dynamics in Continuous Games (Part I: Scalar Action Spaces, Part II: Vector Action Spaces)
  In: IEEE Conference on Decision and Control (CDC), Dec 2020.
• Tanner Fiez, Benjamin J. Chasnov and Lillian J. Ratliff.
  Implicit Learning Dynamics in Stackelberg Games: Equilibria Characterization, Convergence Analysis, and Empirical Study.
  In: Thirty-seventh International Conference on Machine Learning (ICML), July 2020.
• Benjamin J. Chasnov, Lillian J. Ratliff, Eric Mazumdar, Samuel A. Burden.
  Convergence Analysis of Gradient-Based Learning in Continuous Games.
  In: Uncertainty in Artificial Intelligence (UAI), pp. 935-944. Proceedings of Machine Learning Research, 2019.
• Tanner Fiez, Benjamin J. Chasnov and Lillian J. Ratliff.
  Characterizing Equilibria in Stackelberg Games.
  In: NeurIPS Smooth Games Optimization and Machine Learning Workshop: Bridging Game Theory and Deep Learning, Dec 2019.
• Benjamin J. Chasnov, Tanner Fiez and Lillian J. Ratliff.
  Opponent Anticipation via Conjectural Variations.
  In: NeurIPS Smooth Games Optimization and Machine Learning Workshop: Bridging Game Theory and Deep Learning, Dec 2019.
• Benjamin J. Chasnov, Momona Yamagami, Behnoosh Parsa, Lillian J. Ratliff, Samuel A. Burden.
  Experiments with Sensorimotor Games in Dynamic Human/Machine Interaction.
  In: Proceedings of SPIE Micro- and Nanotechnology Sensors, Systems, and Applications XI, May 2019.
• Benjamin J. Chasnov, Lillian J. Ratliff, Daniel Calderone, Eric Mazumdar, and Samuel A. Burden.
  Finite-Time Convergence of Gradient-Based Learning in Continuous Games.
  In: AAAI Workshop on Reinforcement Learning in Games, Jan 2019.
• Alistair Dobke, Joshua Vasquez, Lauren Lieu, Christopher Clark, Ian Dunn, Zoe J. Wood, and Timothy Gambin.
  Towards Three-Dimensional Underwater Mapping Without Odometry.
  In: Unmanned Untethered Submersible Technology Conference 2013 Proceedings: Portsmouth, NH. 2013.

Talks

• Jun 8, 2023: Defense Talk
• Mar 2023: Games, Learning, and Networks at the Institute for Mathematical Sciences, NUS.
• Jan 2023: Semiautonomous at Berkeley.
• Jan 2021: Neural Computation and Engineering Connection, (slides).
• Dec 2020: Conference on Decision and Control, (slides)
• Jun 2019: Dynamic Walking Conference (slides, video)
• Apr 2019: SPIE Conference Session on Human Machine Teaming (20min, slides)
• Jan 2019: AAAI Workshop on Reinforcement Learning in Games (20min, slides)
• Jan 2019: Neural Computation and Engineering Connection