J. Bhargav, M. Ghasemi, and S. Sundaram, Submodular Information Selection for Hypothesis Testing with Misclassification Penalties, Annual Learning for Dynamics & Control (L4DC), 2024.
Q. Elahi*, L. Wei*, M. Kocaoglu, and M. Ghasemi, Adaptive Online Experimental Design for Causal Discovery, International Conference on Machine Learning (ICML), 2024. [Spotlight]
M. Ahmed and M. Ghasemi, Privacy-Preserving Decentralized Actor-Critic for Cooperative Multi-Agent Reinforcement Learning, International Conference on Artificial Intelligence and Statistics (AISTATS), 2024.
S. Oguchienti and M. Ghasemi, Inverse Reinforcement Learning with Learning and Leveraging Demonstrators’ Varying Expertise Levels, Allerton Conference on Communication, Control, and Computing, 2023.
L.Wei, Q. Elahi, M. Ghasemi, and M. Kocaoglu, Approximate Allocation Matching for Structural Causal Bandits with Unobserved Confounders, Conference on Neural Information Processing Systems (NeurIPS), 2023.
J. Bhargav, M. Ghasemi, and S. Sundaram, On the Complexity and Approximability of Optimal Sensor Selection for Mixed-Observable Markov Decision Processes, American Control Conference (ACC), 2023.
B. He, M. Ghasemi, U. Topcu, and L. Sentis, A Barrier Pair Method for Safe Human-Robot Shared Autonomy, Conference on Decision and Control (CDC), 2021.
M. Ghasemi*, A. Hashemi*, H. Vikalo, U. Topcu, No-Regret Learning with High-Probability in Adversarial Markov Decision Processes, Conference on Uncertainty in Artificial Intelligence (UAI), 2021.
M. Ghasemi*, E. Scope Crafts*, B. Zhao, and U. Topcu, Multiple Plans are Better than One: Diverse Stochastic Planning, International Conference on Automated Planning and Scheduling (ICAPS), 2021.
M. Ghasemi, A. Hashemi, U. Topcu, H. Vikalo, Online Learning with Implicit Exploration in Episodic Markov Decision Processes, American Control Conference (ACC), 2021.
M. Ghasemi, E. A. Bulgur, and U. Topcu, Task-Oriented Active Perception and Planning in Environments with Partially Known Semantics, International Conference on Machine Learning (ICML), 2020.
M. Ghasemi, A. Hashemi, H. Vikalo, U. Topcu, Identifying Low-Dimensional Structures in Markov Chains: A Nonnegative Matrix Factorization Approach, American Control Conference (ACC), 2020.
M. Ghasemi and U. Topcu, Perception-Aware Point-Based Value Iteration for Partially Observable Markov Decision Processes, International Joint Conferences on Artificial Intelligence (IJCAI), 2019.
M. Ghasemi*, A. Hashemi*, H. Vikalo, U. Topcu, On Submodularity of Quadratic Observation Selection in Constrained Networked Sensing Systems, American Control Conference (ACC), 2019.
M. Ghasemi and U. Topcu, Online Greedy Active Perception for Partially Observable Markov Decision Processes, Conference on Decision and Control (CDC), 2019.
A. Hashemi, M. Ghasemi, H. Vikalo, U. Topcu, Submodular Observation Selection and Information Gathering for Quadratic Models, International Conference on Machine Learning (ICML), 2019.
R. Dimitrova, M. Ghasemi, and U. Topcu, Maximum Realizability for Linear Temporal Logic Specifications, International Symposium on Automated Technology for Verification and Analysis (ATVA), 2018.
A. Hashemi, M. Ghasemi, H. Vikalo, U. Topcu, A Randomized Greedy Algorithm for Near-Optimal Sensor Scheduling in Large-Scale Sensor Networks, American Control Conference (ACC), 2018. [Finalist for Student Best Paper Award]
L. Feng, M. Ghasemi, K. W. Chang, and U. Topcu, Counterexamples for Robotic Planning Explained in Structured Natural Language, IEEE International Conference on Robotics and Automation (ICRA), 2018.
T. Wongpiromsarn, M. Ghasemi, M. Cubuktepe, G. Bakirtzis, S. Carr, M. O. Karabag, C. Neary, P. Gohari, and U. Topcu, Formal Methods for Autonomous Systems, Foundation and Trends in Systems and Control, 2023.
N. Lauffer, M. Ghasemi, A. Hashemi, Y. Savas, and U. Topcu, No-Regret Learning in Dynamic Stackelberg Games, IEEE Transactions on Automatic Control (TAC), 2023.
R. Dimitrova*, M. Ghasemi*, and U. Topcu, Reactive Synthesis with Maximum Realizability of Linear Temporal Logic Specifications, Acta Informatica Special Issue on Synthesis, 2019.
A. Hashemi, M. Ghasemi, H. Vikalo, U. Topcu, Randomized greedy sensor selection: Leveraging weak submodularity, IEEE Transactions on Automatic Control (TAC), 2019.
Q. Elahi, M. Ghasemi, and M. Kocaoglu, Identification of Average Treatment Effects in Confounded Additive Noise Models, Workshop on Causality for Robotics: Answering the Question of Why at International Conference on Intelligent Robots and Systems (IROS), 2023.
M. Ghasemi and U. Topcu, Perception-Aware Point-Based Value Iteration for Partially Observable Markov Decision Processes, Workshop on Structure & Priors in Reinforcement Learning (SPiRL) at International Conference on Learning Representations (ICLR), 2019.
R. Dimitrova, M. Ghasemi, and U. Topcu, Maximum Realizability for Linear Temporal Logic Specifications, Seventh Workshop on Synthesis (SYNT), 2018.
Efficient, Reliable, and Interpretable Decision-Making for Human-Autonomy Co-Existence, Ph.D. Dissertation, The University of Texas at Austin, 2021.
Synthesis of Reactive Controllers for Reconfigurable Networked Systems, Master’s Thesis, The University of Texas at Austin, 2017.
Reviving the Control system and Simulating the Dynamics of a Rover Robot, Bachelor’s Thesis, Sharif University of Technolog, 2014.