28 citations · 56 across the 22 of their papers we have counts for
30 papers
Modular Pretraining Enables Access Control
Ethan Roland, Murat Cubuktepe, Erick Martinez +8
AI developers face a dual-use dilemma. An AI capability that helps one user cure a disease can help another synthesize one. This dilemma could be resolved with access control, limi…
Endogenous Resistance to Activation Steering in Language Models
Alex McKenzie, Keenan Pepper, Stijn Servaes +6
Large language models can recover mid-generation from task-misaligned activation steering, producing explicit verbal restarts (e.g., ``wait, that's not right'') and continuing on-t…
Formal Methods for Autonomous Systems
Tichakorn Wongpiromsarn, Mahsa Ghasemi, Murat Cubuktepe +6
Formal methods refer to rigorous, mathematical approaches to system development and have played a key role in establishing the correctness of safety-critical systems. The main buil…
Verifiable Reinforcement Learning Systems via Compositionality
Cyrus Neary, Aryaman Singh Samyal, Christos Verginis +2
We propose a framework for verifiable and compositional reinforcement learning (RL) in which a collection of RL subsystems, each of which learns to accomplish a separate subtask, a…
Task-Guided IRL in POMDPs that Scales
Franck Djeumou, Christian Ellis, Murat Cubuktepe +2
In inverse reinforcement learning (IRL), a learning agent infers a reward function encoding the underlying task using demonstrations from experts. However, many existing IRL techni…
Scenario-Based Verification of Uncertain Parametric MDPs
Thom Badings, Murat Cubuktepe, Nils Jansen +3
We consider parametric Markov decision processes (pMDPs) that are augmented with unknown probability distributions over parameter values. The problem is to compute the probability…
Convex Optimization for Parameter Synthesis in MDPs
Murat Cubuktepe, Nils Jansen, Sebastian Junges +2
Probabilistic model checking aims to prove whether a Markov decision process (MDP) satisfies a temporal logic specification. The underlying methods rely on an often unrealistic ass…
Probabilistic Control of Heterogeneous Swarms Subject to Graph Temporal Logic Specifications: A Decentralized and Scalable Approach
Franck Djeumou, Zhe Xu, Murat Cubuktepe +1
We develop a probabilistic control algorithm, , for swarms of agents with heterogeneous dynamics and objectives, subject to high-level task specifications. The r…
Verifiable and Compositional Reinforcement Learning Systems
Cyrus Neary, Christos Verginis, Murat Cubuktepe +1
We propose a framework for verifiable and compositional reinforcement learning (RL) in which a collection of RL subsystems, each of which learns to accomplish a separate subtask, a…
Polynomial-Time Algorithms for Multi-Agent Minimal-Capacity Planning
Murat Cubuktepe, František Blahoudek, Ufuk Topcu
We study the problem of minimizing the resource capacity of autonomous agents cooperating to achieve a shared task. More specifically, we consider high-level planning for a team of…
Task-Guided Inverse Reinforcement Learning Under Partial Information
Franck Djeumou, Murat Cubuktepe, Craig Lennon +1
We study the problem of inverse reinforcement learning (IRL), where the learning agent recovers a reward function using expert demonstrations. Most of the existing IRL techniques m…
Robust Finite-State Controllers for Uncertain POMDPs
Murat Cubuktepe, Nils Jansen, Sebastian Junges +3
Uncertain partially observable Markov decision processes (uPOMDPs) allow the probabilistic transition and observation functions of standard POMDPs to belong to a so-called uncertai…
Distributed Policy Synthesis of Multi-Agent Systems With Graph Temporal Logic Specifications
Murat Cubuktepe, Zhe Xu, Ufuk Topcu
We study the distributed synthesis of policies for multi-agent systems to perform \emph{spatial-temporal} tasks. We formalize the synthesis problem as a \emph{factored} Markov deci…
Scalable Synthesis of Minimum-Information Linear-Gaussian Control by Distributed Optimization
Murat Cubuktepe, Takashi Tanaka, Ufuk Topcu
We consider a discrete-time linear-quadratic Gaussian control problem in which we minimize a weighted sum of the directed information from the state of the system to the control in…
Policy Synthesis for Factored MDPs with Graph Temporal Logic Specifications
Murat Cubuktepe, Zhe Xu, Ufuk Topcu
We study the synthesis of policies for multi-agent systems to implement spatial-temporal tasks. We formalize the problem as a factored Markov decision process subject to so-called…
Robust Policy Synthesis for Uncertain POMDPs via Convex Optimization
Marnix Suilen, Nils Jansen, Murat Cubuktepe +1
We study the problem of policy synthesis for uncertain partially observable Markov decision processes (uPOMDPs). The transition probability function of uPOMDPs is only known to bel…
Policy Synthesis for Switched Linear Systems with Markov Decision Process Switching
Bo Wu, Murat Cubuktepe, Franck Djeumou +2
We study the synthesis of mode switching protocols for a class of discrete-time switched linear systems in which the mode jumps are governed by Markov decision processes (MDPs). We…
Scenario-Based Verification of Uncertain MDPs
Murat Cubuktepe, Nils Jansen, Sebastian Junges +2
We consider Markov decision processes (MDPs) in which the transition probabilities and rewards belong to an uncertainty set parametrized by a collection of random variables. The pr…
Synthesis of Provably Correct Autonomy Protocols for Shared Control
Murat Cubuktepe, Nils Jansen, Mohammed Alsiekh +1
We synthesize shared control protocols subject to probabilistic temporal logic specifications. More specifically, we develop a framework in which a human and an autonomy protocol c…
Switched Linear Systems Meet Markov Decision Processes: Stability Guaranteed Policy Synthesis
Bo Wu, Murat Cubuktepe, Ufuk Topcu
Switched linear systems are time-varying nonlinear systems whose dynamics switch between different modes, where each mode corresponds to different linear dynamics. They arise natur…
Reward-Based Deception with Cognitive Bias
Bo Wu, Murat Cubuktepe, Suda Bharadwaj +1
Deception plays a key role in adversarial or strategic interactions for the purpose of self-defence and survival. This paper introduces a general framework and solution to address…
The Partially Observable Games We Play for Cyber Deception
Mohamadreza Ahmadi, Murat Cubuktepe, Nils Jansen +3
Progressively intricate cyber infiltration mechanisms have made conventional means of defense, such as firewalls and malware detectors, incompetent. These sophisticated infiltratio…
Verification of Uncertain POMDPs Using Barrier Certificates
Mohamadreza Ahmadi, Murat Cubuktepe, Nils Jansen +1
We consider a class of partially observable Markov decision processes (POMDPs) with uncertain transition and/or observation probabilities. The uncertainty takes the form of probabi…
Entropy Maximization for Markov Decision Processes Under Temporal Logic Constraints
Yagiz Savas, Melkior Ornik, Murat Cubuktepe +2
We study the problem of synthesizing a policy that maximizes the entropy of a Markov decision process (MDP) subject to a temporal logic constraint. Such a policy minimizes the pred…