Mahsa Ghasemi

Publication Activity (10 Years)

Years Active: 2017-2024
Publications (10 Years): 37

Top Topics

Markov Decision Process

Reinforcement Learning

Negative Matrix Factorization

Linear Temporal Logic

Top Venues

Publications

Jayanth Bhargav, Mahsa Ghasemi, Shreyas Sundaram
Submodular information selection for hypothesis testing with misclassification penalties. L4DC (2024)
Mahsa Ghasemi, Hamid Hassanpour
FRIH: A face recognition framework using image hashing. Multim. Tools Appl. 83 (21) (2024)
Jayanth Bhargav, Mahsa Ghasemi, Shreyas Sundaram
Optimal Sensor and Actuator Selection for Factored Markov Decision Processes: Complexity, Approximability and Algorithms. CoRR (2024)
Jayanth Bhargav, Mahsa Ghasemi, Shreyas Sundaram
Submodular Information Selection for Hypothesis Testing with Misclassification Penalties. CoRR (2024)
Muhammad Qasim Elahi, Lai Wei, Murat Kocaoglu, Mahsa Ghasemi
Adaptive Online Experimental Design for Causal Discovery. CoRR (2024)
Maheed H. Ahmed, Mahsa Ghasemi
Privacy-Preserving Decentralized Actor-Critic for Cooperative Multi-Agent Reinforcement Learning. AISTATS (2024)
Niklas T. Lauffer, Mahsa Ghasemi, Abolfazl Hashemi, Yagiz Savas, Ufuk Topcu
No-Regret Learning in Dynamic Stackelberg Games. IEEE Trans. Autom. Control. 69 (3) (2024)
Tichakorn Wongpiromsarn, Mahsa Ghasemi, Murat Cubuktepe, Georgios Bakirtzis, Steven Carr, Mustafa O. Karabag, Cyrus Neary, Parham Gohari, Ufuk Topcu
Formal Methods for Autonomous Systems. Found. Trends Syst. Control. 10 (3-4) (2023)
Tichakorn Wongpiromsarn, Mahsa Ghasemi, Murat Cubuktepe, Georgios Bakirtzis, Steven Carr, Mustafa O. Karabag, Cyrus Neary, Parham Gohari, Ufuk Topcu
Formal Methods for Autonomous Systems. CoRR (2023)
Lai Wei, Muhammad Qasim Elahi, Mahsa Ghasemi, Murat Kocaoglu
Approximate Allocation Matching for Structural Causal Bandits with Unobserved Confounders. NeurIPS (2023)
Jayanth Bhargav, Mahsa Ghasemi, Shreyas Sundaram
On the Complexity and Approximability of Optimal Sensor Selection for Mixed-Observable Markov Decision Processes. ACC (2023)
Somtochukwu Oguchienti, Mahsa Ghasemi
Inverse Reinforcement Learning with Learning and Leveraging Demonstrators' Varying Expertise Levels. Allerton (2023)
Niklas T. Lauffer, Mahsa Ghasemi, Abolfazl Hashemi, Yagiz Savas, Ufuk Topcu
No-Regret Learning in Dynamic Stackelberg Games. CoRR (2022)
Mahsa Ghasemi, Evan Scope Crafts, Bo Zhao, Ufuk Topcu
Multiple Plans are Better than One: Diverse Stochastic Planning. ICAPS (2021)
Mahsa Ghasemi, Abolfazl Hashemi, Haris Vikalo, Ufuk Topcu
No-regret learning with high-probability in adversarial Markov decision processes. UAI (2021)
Mahsa Ghasemi, Abolfazl Hashemi, Haris Vikalo, Ufuk Topcu
Online Learning with Implicit Exploration in Episodic Markov Decision Processes. ACC (2021)
Binghan He, Mahsa Ghasemi, Ufuk Topcu, Luis Sentis
A Barrier Pair Method for Safe Human-Robot Shared Autonomy. CoRR (2021)
Abolfazl Hashemi, Mahsa Ghasemi, Haris Vikalo, Ufuk Topcu
Randomized Greedy Sensor Selection: Leveraging Weak Submodularity. IEEE Trans. Autom. Control. 66 (1) (2021)
Binghan He, Mahsa Ghasemi, Ufuk Topcu, Luis Sentis
A Barrier Pair Method for Safe Human-Robot Shared Autonomy. CDC (2021)
Mahsa Ghasemi, Evan Scope Crafts, Bo Zhao, Ufuk Topcu
Multiple Plans are Better than One: Diverse Stochastic Planning. CoRR (2020)
Mahsa Ghasemi, Erdem Bulgur, Ufuk Topcu
Task-Oriented Active Perception and Planning in Environments with Partially Known Semantics. ICML (2020)
Mahsa Ghasemi, Abolfazl Hashemi, Haris Vikalo, Ufuk Topcu
Identifying Sparse Low-Dimensional Structures in Markov Chains: A Nonnegative Matrix Factorization Approach. ACC (2020)
Rayna Dimitrova, Mahsa Ghasemi, Ufuk Topcu
Reactive synthesis with maximum realizability of linear temporal logic specifications. Acta Informatica 57 (1-2) (2020)
Mahsa Ghasemi, Ufuk Topcu
Online Active Perception for Partially Observable Markov Decision Processes with Limited Budget. CoRR (2019)
Abolfazl Hashemi, Mahsa Ghasemi, Haris Vikalo, Ufuk Topcu
Submodular Observation Selection and Information Gathering for Quadratic Models. ICML (2019)
Rayna Dimitrova, Mahsa Ghasemi, Ufuk Topcu
Reactive Synthesis with Maximum Realizability of Linear Temporal Logic Specifications. CoRR (2019)
Mahsa Ghasemi, Ufuk Topcu
Online Active Perception for Partially Observable Markov Decision Processes with Limited Budget. CDC (2019)
Mahsa Ghasemi, Abolfazl Hashemi, Haris Vikalo, Ufuk Topcu
Identifying Low-Dimensional Structures in Markov Chains: A Nonnegative Matrix Factorization Approach. CoRR (2019)
Mahsa Ghasemi, Abolfazl Hashemi, Ufuk Topcu, Haris Vikalo
On Submodularity of Quadratic Observation Selection in Constrained Networked Sensing Systems. ACC (2019)
Mahsa Ghasemi, Ufuk Topcu
Perception-Aware Point-Based Value Iteration for Partially Observable Markov Decision Processes. IJCAI (2019)
Rayna Dimitrova, Mahsa Ghasemi, Ufuk Topcu
Maximum Realizability for Linear Temporal Logic Specifications. CoRR (2018)
Abolfazl Hashemi, Mahsa Ghasemi, Haris Vikalo, Ufuk Topcu
A Randomized Greedy Algorithm for Near-Optimal Sensor Scheduling in Large-Scale Sensor Networks. ACC (2018)
Lu Feng, Mahsa Ghasemi, Kai-Wei Chang, Ufuk Topcu
Counterexamples for Robotic Planning Explained in Structured Language. ICRA (2018)
Rayna Dimitrova, Mahsa Ghasemi, Ufuk Topcu
Maximum Realizability for Linear Temporal Logic Specifications. ATVA (2018)
Lu Feng, Mahsa Ghasemi, Kai-Wei Chang, Ufuk Topcu
Counterexamples for Robotic Planning Explained in Structured Language. CoRR (2018)
Abolfazl Hashemi, Mahsa Ghasemi, Haris Vikalo, Ufuk Topcu
A Randomized Greedy Algorithm for Near-Optimal Sensor Scheduling in Large-Scale Sensor Networks. CoRR (2017)
Pasquale Palumbo, Mahsa Ghasemi, Mohammad Fakhroleslam
On enzymatic reactions: The role of a feedback from the substrate. CDC (2017)