Mustafa O. Karabag

42 papers A* 2A 3C 3Journal 27Unranked 7
YearRankTypeTitle / Venue / Authors
2026 J jnl
When Should a Leader Act Suboptimally? The Role of Inferability in Repeated Stackelberg Games.
IEEE Trans. Autom. Control.
Mustafa O. Karabag, Sophia Smith, Negar Mehr, David Fridovich-Keil, Ufuk Topcu
2025 J jnl
Cooperative Bargaining Games Without Utilities: Mediated Solutions from Direction Oracles.
CoRR
Kushagra Gupta, Surya Murthy, Mustafa O. Karabag, Ufuk Topcu, David Fridovich-Keil
2025 J jnl
Deceptive Exploration in Multi-armed Bandits.
CoRR
I. Arda Vurankaya, Mustafa O. Karabag, Wesley A. Suttle, Jesse Milzman, David Fridovich-Keil, Ufuk Topcu
2025 J jnl
Deceptive Planning Exploiting Inattention Blindness.
CoRR
Mustafa O. Karabag, Jesse Milzman, Ufuk Topcu
2025 J jnl
Deceptive Sequential Decision-Making via Regularized Policy Optimization.
CoRR
Yerin Kim, Alexander Benvenuti, Bo Chen, Mustafa O. Karabag, Abhishek Ninad Kulkarni, Nathaniel D. Bastian, Ufuk Topcu, Matthew Hale
2025 J jnl
Designing Inferable Signaling Schemes for Bayesian Persuasion.
CoRR
Caleb Probine, Mustafa O. Karabag, Ufuk Topcu
2025 J jnl
Designing policies for transition-independent multiagent systems that are robust to communication loss.
Auton. Agents Multi Agent Syst.
Mustafa O. Karabag, Cyrus Neary, Ufuk Topcu
2025 J jnl
DiBS-MTL: Transformation-Invariant Multitask Learning with Direction Oracles.
CoRR
Surya Murthy, Kushagra Gupta, Mustafa O. Karabag, David Fridovich-Keil, Ufuk Topcu
2025 J jnl
Do LLMs Strategically Reveal, Conceal, and Infer Information? A Theoretical and Empirical Analysis in The Chameleon Game.
CoRR
Mustafa O. Karabag, Ufuk Topcu
2025 A conf
Policies with Sparse Inter-Agent Dependencies in Dynamic Games: A Dynamic Programming Approach.
AAMAS
Xinjie Liu, Jingqi Li, Filippos Fotiadis, Mustafa O. Karabag, Jesse Milzman, David Fridovich-Keil, Ufuk Topcu
2025 — conf
Value of Information-based Deceptive Path Planning Under Adversarial Interventions.
CDC
Wesley A. Suttle, Jesse Milzman, Mustafa O. Karabag, Brian M. Sadler, Ufuk Topcu
2025 J jnl
Value of Information-based Deceptive Path Planning Under Adversarial Interventions.
CoRR
Wesley A. Suttle, Jesse Milzman, Mustafa O. Karabag, Brian M. Sadler, Ufuk Topcu
2024 — conf
A Decentralized Shotgun Approach for Team Deception.
GameSec
Caleb Probine, Mustafa O. Karabag, Ufuk Topcu
2024 J jnl
Autonomous Negotiation Using Comparison-Based Gradient Estimation.
CoRR
Surya Murthy, Mustafa O. Karabag, Ufuk Topcu
2024 C conf
Deceptive Planning for Resource Allocation.
ACC
Shenghui Chen, Yagiz Savas, Mustafa O. Karabag, Brian M. Sadler, Ufuk Topcu
2024 — conf
Defining and Measuring Deception in Sequential Decision Systems: Application to Network Defense.
MILCOM
Yerin Kim, Alexander Benvenuti, Bo Chen, Mustafa O. Karabag, Abhishek Ninad Kulkarni, Nathaniel D. Bastian, Ufuk Topcu, Matthew Hale
2024 C conf
Encouraging Inferable Behavior for Autonomy: Repeated Bimatrix Stackelberg Games with Observations.
ACC
Mustafa O. Karabag, Sophia Smith, David Fridovich-Keil, Ufuk Topcu
2024 J jnl
Identity concealment games: How I learned to stop revealing and love the coincidences.
Autom.
Mustafa O. Karabag, Melkior Ornik, Ufuk Topcu
2024 J jnl
Policies with Sparse Inter-Agent Dependencies in Dynamic Games: A Dynamic Programming Approach.
CoRR
Xinjie Liu, Jingqi Li, Filippos Fotiadis, Mustafa O. Karabag, Jesse Milzman, David Fridovich-Keil, Ufuk Topcu
2023 A conf
Differential Privacy in Cooperative Multiagent Planning.
UAI
Bo Chen, Calvin Hawkins, Mustafa O. Karabag, Cyrus Neary, Matthew T. Hale, Ufuk Topcu
2023 J jnl
Differential Privacy in Cooperative Multiagent Planning.
CoRR
Bo Chen, Calvin Hawkins, Mustafa O. Karabag, Cyrus Neary, Matthew T. Hale, Ufuk Topcu
2023 J jnl
Encouraging Inferable Behavior for Autonomy: Repeated Bimatrix Stackelberg Games with Observations.
CoRR
Mustafa O. Karabag, Sophia Smith, David Fridovich-Keil, Ufuk Topcu
2023 J jnl
Exploiting Partial Observability for Optimal Deception.
IEEE Trans. Autom. Control.
Mustafa O. Karabag, Melkior Ornik, Ufuk Topcu
2023 J jnl
Formal Methods for Autonomous Systems.
CoRR
Tichakorn Wongpiromsarn, Mahsa Ghasemi, Murat Cubuktepe, Georgios Bakirtzis, Steven Carr, Mustafa O. Karabag, Cyrus Neary, Parham Gohari, Ufuk Topcu
2023 J jnl
Formal Methods for Autonomous Systems.
Found. Trends Syst. Control.
Tichakorn Wongpiromsarn, Mahsa Ghasemi, Murat Cubuktepe, Georgios Bakirtzis, Steven Carr, Mustafa O. Karabag, Cyrus Neary, Parham Gohari, Ufuk Topcu
2023 A* conf
On the Sample Complexity of Vanilla Model-Based Offline Reinforcement Learning with Dependent Samples.
AAAI
Mustafa O. Karabag, Ufuk Topcu
2023 J jnl
On the Sample Complexity of Vanilla Model-Based Offline Reinforcement Learning with Dependent Samples.
CoRR
Mustafa O. Karabag, Ufuk Topcu
2023 — conf
Scenario-Game ADMM: A Parallelized Scenario-Based Solver for Stochastic Noncooperative Games.
CDC
Jingqi Li, Chih-Yuan Chiu, Lasse Peters, Fernando Palafox, Mustafa O. Karabag, Javier Alonso-Mora, Somayeh Sojoudi, Claire J. Tomlin, David Fridovich-Keil
2023 J jnl
Scenario-Game ADMM: A Parallelized Scenario-Based Solver for Stochastic Noncooperative Games.
CoRR
Jingqi Li, Chih-Yuan Chiu, Lasse Peters, Fernando Palafox, Mustafa O. Karabag, Javier Alonso-Mora, Somayeh Sojoudi, Claire J. Tomlin, David Fridovich-Keil
2023 — conf
Simulator-Driven Deceptive Control via Path Integral Approach.
CDC
Apurva Patil, Mustafa O. Karabag, Takashi Tanaka, Ufuk Topcu
2023 J jnl
Simulator-Driven Deceptive Control via Path Integral Approach.
CoRR
Apurva Patil, Mustafa O. Karabag, Takashi Tanaka, Ufuk Topcu
2022 — conf
Alternating Direction Method of Multipliers for Decomposable Saddle-Point Problems.
Allerton
Mustafa O. Karabag, David Fridovich-Keil, Ufuk Topcu
2022 J jnl
Alternating Direction Method of Multipliers for Decomposable Saddle-Point Problems.
CoRR
Mustafa O. Karabag, David Fridovich-Keil, Ufuk Topcu
2022 J jnl
Deception in Supervisory Control.
IEEE Trans. Autom. Control.
Mustafa O. Karabag, Melkior Ornik, Ufuk Topcu
2022 J jnl
Deceptive Planning for Resource Allocation.
CoRR
Yagiz Savas, Mustafa O. Karabag, Brian M. Sadler, Ufuk Topcu
2022 A conf
Planning Not to Talk: Multiagent Systems that are Robust to Communication Loss.
AAMAS
Mustafa O. Karabag, Cyrus Neary, Ufuk Topcu
2022 J jnl
Planning Not to Talk: Multiagent Systems that are Robust to Communication Loss.
CoRR
Mustafa O. Karabag, Cyrus Neary, Ufuk Topcu
2021 J jnl
Identity Concealment Games: How I Learned to Stop Revealing and Love the Coincidences.
CoRR
Mustafa O. Karabag, Melkior Ornik, Ufuk Topcu
2021 A* conf
Smooth Convex Optimization Using Sub-Zeroth-Order Oracles.
AAAI
Mustafa O. Karabag, Cyrus Neary, Ufuk Topcu
2020 J jnl
Entropy Maximization for Markov Decision Processes Under Temporal Logic Constraints.
IEEE Trans. Autom. Control.
Yagiz Savas, Melkior Ornik, Murat Cubuktepe, Mustafa O. Karabag, Ufuk Topcu
2019 C conf
Least Inferable Policies for Markov Decision Processes.
ACC
Mustafa O. Karabag, Melkior Ornik, Ufuk Topcu
2019 — conf
Optimal Deceptive and Reference Policies for Supervisory Control.
CDC
Mustafa O. Karabag, Melkior Ornik, Ufuk Topcu