English
Related papers

Related papers: Learning Optimal Defender Strategies for CAGE-2 us…

200 papers

This work investigates multi-objective imitation learning: the problem of recovering policies that lie on the Pareto front given demonstrations from multiple Pareto-optimal experts in a Multi-Objective Markov Decision Process (MOMDP).…

Machine Learning · Computer Science 2026-05-19 Ziyad Sheebaelhamd , Luca Viano , Volkan Cevher , Claire Vernade

Through using only a well-trained classifier, model-inversion (MI) attacks can recover the data used for training the classifier, leading to the privacy leakage of the training data. To defend against MI attacks, previous work utilizes a…

Machine Learning · Computer Science 2022-07-19 Xiong Peng , Feng Liu , Jingfen Zhang , Long Lan , Junjie Ye , Tongliang Liu , Bo Han

Markov Decision Processes (MDPs) are a popular class of models suitable for solving control decision problems in probabilistic reactive systems. We consider parametric MDPs (pMDPs) that include parameters in some of the transition…

Logic in Computer Science · Computer Science 2018-06-14 Sebastian Arming , Ezio Bartocci , Krishnendu Chatterjee , Joost-Pieter Katoen , Ana Sokolova

Control policies, trained using the Deep Reinforcement Learning, have been recently shown to be vulnerable to adversarial attacks introducing even very small perturbations to the policy input. The attacks proposed so far have been designed…

Machine Learning · Computer Science 2019-08-02 Alessio Russo , Alexandre Proutiere

Efficient and effective attacks are crucial for reliable evaluation of defenses, and also for developing robust models. Projected Gradient Descent (PGD) attack has been demonstrated to be one of the most successful adversarial attacks.…

Computer Vision and Pattern Recognition · Computer Science 2022-02-01 Mengting Xu , Tao Zhang , Zhongnian Li , Daoqiang Zhang

We present a mathematical framework and computational methods to optimally design a finite number of sequential experiments. We formulate this sequential optimal experimental design (sOED) problem as a finite-horizon partially observable…

Machine Learning · Computer Science 2024-03-28 Wanggang Shen , Xun Huan

In this paper, we present a novel reinforcement learning framework designed to optimize molecular dynamics by focusing on the entire trajectory rather than just the final molecular configuration. Leveraging a stochastic version of…

Optimization and Control · Mathematics 2024-10-22 Chandrajit Bajaj , Minh Nguyen , Conrad Li

Selfish mining is strategic rule-breaking to maximize rewards in proof-of-work protocols. Markov Decision Processes (MDPs) are the preferred tool for finding optimal strategies in Bitcoin and similar linear chain protocols. Protocols…

Cryptography and Security · Computer Science 2025-06-24 Patrik Keller

We study reinforcement learning with linear function approximation and finite-memory approximations for partially observed Markov decision processes (POMDPs). We first present an algorithm for the value evaluation of finite-memory feedback…

Optimization and Control · Mathematics 2025-05-22 Ali Devran Kara

Optimizing a partially observable Markov decision process (POMDP) policy is challenging. The policy graph improvement (PGI) algorithm for POMDPs represents the policy as a fixed size policy graph and improves the policy monotonically. Due…

Artificial Intelligence · Computer Science 2020-09-07 Joni Pajarinen

We introduce the Pontryagin-Guided Direct Policy Optimization (PG-DPO) framework for high-dimensional continuous-time portfolio choice. Our approach combines Pontryagin's Maximum Principle (PMP) with backpropagation through time (BPTT) to…

Portfolio Management · Quantitative Finance 2025-09-12 Jeonggyu Huh , Jaegi Jeon , Hyeng Keun Koo , Byung Hwa Lim

Memoryless and finite-memory policies offer a practical alternative for solving partially observable Markov decision processes (POMDPs), as they operate directly in the output space rather than in the high-dimensional belief space. However,…

Machine Learning · Computer Science 2025-12-15 Roy van Zuijlen , Duarte Antunes

In this review/tutorial article, we present recent progress on optimal control of partially observed Markov Decision Processes (POMDPs). We first present regularity and continuity conditions for POMDPs and their belief-MDP reductions, where…

Optimization and Control · Mathematics 2025-01-03 Ali Devran Kara , Serdar Yuksel

Engagement-optimized adaptive tutoring systems may prioritize short-term behavioral signals over sustained learning outcomes, creating structural incentives for reward hacking in reinforcement learning policies. We formalize this challenge…

Artificial Intelligence · Computer Science 2026-04-07 Oluseyi Olukola , Nick Rahimi

The robust constrained Markov decision process (RCMDP) is a recent task-modelling framework for reinforcement learning that incorporates behavioural constraints and that provides robustness to errors in the transition dynamics model through…

Machine Learning · Computer Science 2024-05-16 David M. Bossens

In this work, we model Moving Target Defence (MTD) as a partially observable stochastic game between an attacker and a defender. The attacker tries to compromise the system through probing actions, while the defender minimizes the risk by…

Computer Science and Game Theory · Computer Science 2025-08-26 Mandar Datar , Yann Dujardin

Partially-Observable Markov Decision Processes (POMDPs) are typically solved by finding an approximate global solution to a corresponding belief-MDP. In this paper, we offer a new planning algorithm for POMDPs with continuous state, action…

Artificial Intelligence · Computer Science 2012-03-19 Tom Erez , William D. Smart

We describe and study a model for an Automated Online Recommendation System (AORS) in which a user's preferences can be time-dependent and can also depend on the history of past recommendations and play-outs. The three key features of the…

Machine Learning · Computer Science 2016-03-31 Rahul Meshram , Aditya Gopalan , D. Manjunath

In many practical settings control decisions must be made under partial/imperfect information about the evolution of a relevant state variable. Partially Observable Markov Decision Processes (POMDPs) is a relatively well-developed framework…

Machine Learning · Computer Science 2021-12-30 Yanling Chang , Alfredo Garcia , Zhide Wang , Lu Sun

This paper studies the performance and resilience of a cyber-physical control system (CPCS) with attack detection and reactive attack mitigation. It addresses the problem of deriving an optimal sequence of false data injection attacks that…

Cryptography and Security · Computer Science 2017-06-07 Subhash Lakshminarayana , Teo Zhan Teng , David K. Y. Yau , Rui Tan