2025
Contextual Bandits for Large-Scale Structured Discrete Constrained Optimization Problems. P Harsha, C Subramanian, N Abe, S Subramanian, A Ba, K A Fernández Román, M L Garrido, M Liu, A Lozano, C Narayanaswami, NeurIPS 2025 Workshop MLxOR: Mathematical Foundations and Operational Integration of Machine Learning for Uncertainty-Aware Decision-Making [link]
Meta-D2AG: Causal Graph Learning with Interventional Dynamic Data. T Gao, S Lu, J Lee, N Nelson, D Bhattacharjya, Y Yu, M Liu, NeurIPS2025 [link]
Bridging the Gap: Unifying HCI & ML Perspectives on Mutual Theory of Mind. Z Ashktorab, D Bouneffouf, K Brimijoin, R Bellamy, M Campbell, A Goldberg, G E Gonzalez, S Houde, M Liu, D S Moran, M Riemer and J D Weisz, the Workshop on Generative AI and Theory of Mind in Communicating Agent at IJCAI 2025 [link]
Position: Theory of Mind Benchmarks are Broken for Large Language Models. M Riemer, Z Ashktorab, D Bouneffouf, P Das, M Liu J D Weisz and M Campbell, ICML2025 [link]
Evaluating the Prompt Steerability of Large Language Models. E Miehling, M Desmond, K N Ramamurthy, E M Daly, K R Varshney, E Farchi, P Dognin, J Rios, D Bouneffouf, M Liu, P Sattigeri, NAACL 2025 [link]
A Generalist Hanabi Agent. A V Sudhakar, H Nekoei, M Reymond, M Liu, J Rajendran, Sarath Chandar, ICLR2025 [link]
Q-function Decomposition with Intervention Semantics for Factored Action Spaces. J Lee, T Gao, E Nelson, M Liu, D Bhattacharjya, S Lu, AISTATS2025 [link]
Contextual Value Alignment. P Dognin, J Rios, R Luss, P Sattigeri, M Liu, I Padhi, M Riemer, M Nagireddy, K Varshney, D Bouneffouf, ICASSP2025 [link]
2024
Evaluating the Prompt Steerability of Large Language Models. E Miehling, M Desmond, K Ramamurthy, E Daly, P Dognin, J Rios, D Bouneffouf, M Liu, Pluralistic Alignment Workshop at NeurIPS 2024 [link]
SF-DQN: Provable Knowledge Transfer using Successor Feature for Deep Reinforcement Learning. S Zhang, H Fernando, M Liu, K Murugesan, S Lu, P Chen, T Chen, M Wang, ICML 2024 [link]
ComVas: Contextual Moral Values Alignment System. I Padhi, P Dognin, J Rios, R Luss, S Achintalwar, M Riemer, M Liu, P Sattigeri, M Nagireddy, K Varshney, Djallel Bouneffouf, IJCAI2024 Demo Track [link]
Multi-agent text-based Hanabi challenge. H Nekoei, A V Sudhakar, J Rajendran, M Liu, S Chandar, ICLR 2024 Workshop on Generative Models for Decision Making [link]
Variance Reduction Can Improve Trade-off In Multi-Objective Learning. H Fernando, L Chen, S Lu, P Chen, M Liu, S Chaudhury, K Murugesan, G Liu, M Wang, T Chen, ICASSP2024 [link]
A Neuro-Symbolic Approach to Multi-Agent RL for Interpretability and Probabilistic Decision Making, C Subramanian, M Liu , N Khan, J Lenchner , A Amarnath, S Swaminathan, R Riegel , A Gray [link]
2023
On the Convergence and Sample Complexity Analysis of Deep Q-Networks with e-Greedy Exploration. S Zhang, M Wang, H Li, M Liu, P Chen, S Lu, S Liu, K Murugesan, S Chaudhury, In Proc. of 37th Conference on Neural Information Processing Systems (NeurIPS), 2023 [link]
Towards Few-shot Coordination: Revisiting Ad-Hoc Teamplay Challenge in the Game of Hanabi. H Nekoei, X Zhao, J Rajendran, M Liu, S Chandar. In Proc. of the 2nd Conference on Lifelong Learning Agents (CoLLAs) 2023 [paper]
Model-free Causal Reinforcement Learning with Causal Diagrams. J Lee, T Gao, E Nelson, M Liu, D Bhattacharjya, The 1st International Workshop on Knowledge-Based Compositional Generalization (KBCG) at IJCAI 2023 [paper]
A Neuro-Symbolic Approach to Runtime Optimization in Resource Constrained Heterogeneous Systems. C K Subramanian, S Swaminathan, M Liu, M Longinos, A Amarnath, K Swaminathan, M Cochet, K Roman, and P Bose, Neuro-Symbolic Agents Workshop at IJCAI2023 [paper]
Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Approach. H D Fernando, H Shen, M Liu, S Chaudhury, K Murugesan and T Chen. In Proc. of the 11th International Conference on Learning Representations (ICLR), 2023 [paper][notable-top-5%]
Joint Edge-Model Sparse Learning is Provably Efficient for Graph Neural Networks. S Zhang, M Wang, P Chen, S Liu, S Lu and M Liu. In Proc. of the 11th International Conference on Learning Representations (ICLR), 2023 [paper]
Local Explanations for Reinforcement Learning. R. Luss, A. Dhurandhar, and M Liu. In Proc. of the 37th AAAI Conference on Artificial Intelligence (AAAI), 2023 [paper]
2022
Influencing Long-Term Behavior in Multiagent Reinforcement Learning. D K Kim, M Riemer, M Liu, J N Foerster, M Everett, C Sun, G Tesauro, J P How, In Proc. of 36th Conference on Neural Information Processing Systems (NeurIPS), 2022 [paper][MIT News]
Game-Theoretical Perspectives on Active Equilibria: A Preferred Solution Concept over Nash Equilibria. D K Kim, M Riemer, M Liu, J N Foerster, G Tesauro, J P How. Workshop on Strategic Multi-agent Interactions: Game Theory for Robot Learning and Decision Making at CoRL 2022 [link]
Learning Multi-Objective Curricula for Robotic Policy Learning. J Kang, M Liu, A Gupta, C Pal, X Liu, and J Fu. In Proc. of the 6th Annual Conference on Robot Learning (CoRL), 2022 [link]
Cost-Efficient Reinforcement Learning for Optimal Trade Execution on Dynamic Market Environment. D Chen, Y Zhu, M Liu, and J Li. In the 3rd ACM International Conference on AI in Finance (ICAIF), 2022 [link]
IDYNO: Learning Nonparametric DAGs from Interventional Dynamic Data. T Gao, D Bhattacharjya, E Nelson, M Liu, and Y Yu. In Proc. of the 39th International Conference on Machine Learning (ICML), 2022 [paper][link]
Linerizing Contextual Bandits with Latent State Dynamics. E Nelson, D. Bhattacharjya, T. Gao, M Liu, D. Bouneffouf, and P Poupart. In Proc. of Conference on Uncertainty in Artificial Intelligence (UAI), 2022 [paper][link]
Context-specific representation abstraction for deep option learning. M Abdulhai, D K Kim, M Riemer, M Liu, G Tesauro, and J. P. How. In Proc. of the AAAI, 2022 [paper][code]
2021
A Policy Gradient Algorithm for Learning to Learn in Multiagent Reinforcement Learning. D K Kim, M Liu, M Riemer, C Sun, M Abdulhai, G Habibi, S Lopez-Cot, G Tesauro and J P How., in Proc. of the 38th International Conference on Machine Learning (ICML), 2021 [paper][code]
RL Generalization in a Theory of Mind Game Through a Sleep Metaphor. T Malloy, T Klinger, M Liu, G Tesauro, M Riemer, and C R Sims. In Proc. of the AAAI, 2021 [paper]
Capacity-Limited Decentralized Actor-Critic for Multi-Agent Games. T Malloy, C R Sims, T Klinger, M. Liu, M. Riemer, and G Tesauro. In Proc. of the IEEE Conference on Games (CoG), 2021 [paper]
Modeling Capacity-Limited Decision Making Using a Variational Autoencoder. T Malloy, T. Klinger, M Liu, G Tesauro, M Riemer, and C R Sims. In Proc. of the Annual Meeting of the Cognitive Science Society, 2021 [paper]
Consolidation via Policy Information Regularization in Deep RL for Multi-Agent Games. T Malloy, T Klinger, M Liu, M Riemer, G Tesauro, C R Sims, AAAI-21 Workshop on Reinforcement Learning in Games [paper]
AI Planning Annotation in Reinforcement Learning: Options and Beyond. J Lee, M Katz, D J Agravante, M Liu, T Klinger, M Campbell, S Soharbi, and G Tesauro. In ICAPS21 workshop on Bridging the Gap Between AI Planning and Reinforcement Learning [paper]
2020
Learning Hierarchical Teaching Policies for Cooperative Agents. D K Kim, M Liu, S Omidshafiei, S Lopez-Cot, M Riemer, G Habibi, G Tesauro, S Mourad, M Campbell, and J P How. In the Proc. of the 19th International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2020 [paper]
On the Role of Weights Sharing. M Riemer, I Cases, C Rosenbaum, M Liu, and G Tesauro. In Proc. of the 34th AAAI Conference on Artificial Intelligence (AAAI), 2020 [paper]
Deep RL with information constrained policies: Generalization in continuous control. T Malloy, C R Sims, T Klinger, M Liu, M Riemer, G Tesauro [paper]
2019
Automatic Pan-Tilt Camera Control for Learning Dirichlet Process Gaussian Process (DPGP) Mixture Models of Multiple Moving Targets. H Wei, P Zhu, M Liu, J P How, and S Ferrari. IEEE Transactions on Automatic Control,64(1):159-173, 2019 [link]
Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference. M Riemer, I Cases, R Ajemian, M Liu, I Rish, Y Tu, and G Tesauro. In Proc. of the 7th International Conference on Learning Representations (ICLR), 2019 [paper][link][code][Media report]
Learning to Teach in Cooperative Multiagent Reinforcement Learning. S Omidshafiei, D K Kim, M Liu, G Tesauro, M Riemer, C Amato, M Campbell, and J P How. In Proc. of the 33th AAAI Conference on Artificial Intelligence (AAAI), 2019 [paper][MIT News, IBM Blog][Outstanding Student Paper Honorable Mention]
2018
Gaussian Processes for Learning and Control — Tutorial with Examples. M Liu, G Chowdhary, B da Silva, S Liu, and J P How. Control Systems Magazine, IEEE, September 2018 [Link]
Learning Abstract Options. M Riemer, M Liu, and G Tesauro. Neural Information Processing Systems (NeurIPS), 2018 [paper]
Eigenoption Discovery through the Deep Successor Representation. M C Machado, C Rosenbaum, X Guo, M Liu, G Tesauro, and M S Campbell. In Proc of the 6th International Conference on Learning Representations (ICLR), 2018
2017
The Eigenoption Critic Framework. M Liu, M C Machado, G Tesauro and M S Campbell, In NeurIPS Workshop on Hierarchical Reinforcement Learning, 2017 [paper]
Learning for Multi-robot Cooperation in Partially Observable Stochastic Environments with Macro-actions. M Liu, K. Sivakumar, S Omidshafiei, C Amato and J P How. In Proc. of the 30th IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2017 [paper][link]
Socially Aware Motion Planning with Deep Reinforcement Learning. Y Chen, M Everett, M Liu, and J P How, In Proc. of the 30th IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2017 [paper][link][MIT News, Siliconrepublic, Neowin][Best Student Paper Award and Finalist-Best Paper Award on Cognitive Robotics]
Decentralized Non-communicating Multiagent Collision Avoidance with Deep Reinforcement Learning. Y Chen, M. Liu, M. Everett and J P How. In Proc. of the IEEE International Conference on Robotics and Automation (ICRA), 2017 [paper] [Finalist-Best Multi-Robot System Paper]
Semantic-level Decentralized Multi-Robot Decision-Making using Probabilistic Macro-Observations. S Omidshafiei, S Liu, M. Everett and B T Lopez, C Amato, M Liu, J P How, and J. Vian. In Proc. of the IEEE International Conference on Robotics and Automation (ICRA), 2017 [paper]
Scalable Accelerated Decentralized MultiRobot Policy Search in Continuous Observation Spaces. S Omidshafiei, C Amato, M Liu, J P How and J. Vian. In the IEEE International Conference on Robotics and Automation (ICRA), 2017 [paper]
A Quickest Change Detection Approach for Dynamic Decision Making in Nonstationary Environments, T Benerjee, M Liu, and J P How. In Proc. of the American Control Conference (ACC), 2017 [paper]
2016
Learning for Multiagent Decentralized Control in Large, Partially-Observable Stochastic Environments. M Liu, C Amato, E Anesta, J D Griffith, and J P How. In Proc. of the 30th AAAI Conference on Artificial Intelligence (AAAI), 2016 [link]
Motion Planning with Diffusion Maps. Y Chen, S Liu, M Liu, J Miller, and J P How. In Proc. of The IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2016 [paper]
Augmented Dictionary Learning for Sparse Representations of Trajectories with Application to Motion Prediction. Y Chen, M Liu, and J P How. In Proc. of the IEEE International Conference on Robotics and Automation (ICRA), 2016 [paper]
Predictive Modeling of Pedestrian Motion Patterns with Bayesian Nonparametrics. Y Chen, M Liu, S Liu, J Miller, and J P How. AIAA Guidance, Navigation, and Control Conference (GNC), 2016. [link][paper]
2015
Stick-Breaking Policy Learning in DECPOMDPs. M Liu, C Amato, X Liao, L Carin, and J P How. In Proc. of the 24rd International Joint Conference on Artificial Intelligence (IJCAI), 2015 [paper][longer version]
Learning for Multiagent Decentralized Control in Large Partially-Observable Stochastic Environments. M Liu, C Amato, E Anesta, J D Griffith, and J P How. In Proc. of the 2nd Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM), 2015
Policy Based Reinforcement Learning in DEC-POMDPs with Bayesian Nonparametrics. M Liu and J P How. NeurIPS Workshop on Learning, Inference and Control of Multi-Agent Systems, 2015 [Best Poster Award]
2014 and Before
Efficient Bayesian Nonparametric Methods for Model-Free Reinforcement Learning in Centralized and Decentralized Sequential Environments, M Liu, Duke University PhD Thesis, 2014. [link]
Off-policy Reinforcement Learning with Gaussian processes. G Chowdhary, M Liu, R C Grande, T J Walsh, L Carin and J P How. IEEE/CAA Journal of Automatica Sinica, Volume: 1, Issue: 3, July 2014. [link]
Dynamic Clustering via Asymptotics of the Dependent Dirichlet Process Mixture.T Campbell, M Liu, B Kulis, J P How, and L Carin., in Proc. of Neural Information Processing Systems (NeurIPS), 2013. [paper]
Online Expectation Maximization for Reinforcement Learning in POMDPs, M Liu, X Liao, and L Carin. In Proc. of the 23rd Int’l Joint Conf. on Artificial Intelligence (IJCAI), 2013. [paper]
Transfer Learning for Reinforcement Learning with Dependent Dirichlet Process and Gaussian Process. M Liu, G Girish, J P How, and L Carin. NeurIPS Workshop on Bayesian Nonparametric Models for Reliable Planning and Decision-Making Under Uncertainty, 2012. [paper, poster]
Infinite Regionalized Policy Representation. M Liu, X Liao, and L Carin. In Proc. of the 28th Int’l Conf. on Machine Learning (ICML), 2011. [paper]
Uterine Contraction Modeling and Simulation. M Liu, L Belfore, Y Shen, and M. Scerbo. In Selected Papers Presented at MODSIM World 2009 Conference and Expo, pages 135-140. NASA, Virginia Beach, Virginia, US, 2010. [link]
Multi-frame Super Resolution Based on Block Motion Vector Processing and Kernel Constrained Convex Set Projection. M Liu and Y Shen. In Proceedings of SPIE Visual Communications and Image Processing (VCIP), volume 7257, page 72571J, 2009 [link]
A Near Optimum Detection in Alpha-Stable Impulse Noise. X Li, Y Jiang, and M Liu, In IEEE Int’l Conf. on Acoustics, Speech, and Signal Processing (ICASSP), pages 3305-3308, 2009. [link]
Bi-parameter CGM model for approximation of alpha-stable PDF. XT Li, J Sun, LW Jin, and M Liu. IEE Letter V44, Issue 18, August 2008 [link]
A Survey of Computerized Fetal Heart Rate Monitoring and Interpretation Techniques. M Li, Y Shen, and M. Scerbo. Modeling and Simulation Capstone Conference, 2008 [pdf]
New Edge Detection Based on Pyramid-Structure Wavelet Transform. S Yi, H Cao, X Li, and M Liu. In SPIE Proc. Visual Information Processing XV, page 62460U, 2006. [link]
A New Texture Representation with Multi-scale Wavelet Feature. S Yi, H Cao, X Li, and M Liu. In SPIE Proc. Visual Information Processing XV, page 62460X, 2006. [link]
A zero-watermarking algorithm based on DWT and chaotic modulation. H Cao, H Xiang, X. Li, M Liu, S Yi, and F. Wei. In Defense and Security Symposium, pages 624716-624716. International Society for Optics and Photonics, 2006. [link]
Super Resolution Reconstruction Based on Motion Estimation Error and Edge Adaptive Constraints. M Liu, H Cao, X Li, and S Yi, In SPIE Proc. Visual Information Processing XV, page 62460B, 2006. [link]
Patents
Online Learning System with Contextual Bandits Feedback and Latent State Dynamics. E. Nelson, D. Bouneffouf, D. Bhattacharjya, T. Gao and M Liu P20220497
A System and Method for Understanding Reinforcement Learning Policies by Identifying Strategic States. R Luss, A Dhurandhar and M Liu, P202103551
A System and Method for Integrating AI Planners and Reinforcement Learning Agents through AI planning annotation in Reinforcement Learning. J Lee, M Katz, D J Agravante, M Liu, T Klinger, M Campbell, S Soharbi. P202102362
System and Method for Optimal Trade Execution. Y Zhu, M Liu, P Dey, N Gaur and A Gray. P202006957
Dialog Agent for Conducting Task-Oriented Computer-based Communications. M S Campbell, M Liu, B Srivastava. US Patent 10740370
A Super-Resolution Video Reconstruction Method. L Xiong, H Cao, M Liu, Chinese Patent CN1863272A