English
Related papers

Related papers: Physics-Informed Causal MDPs for Sequential Constr…

200 papers

In XR downlink transmission, energy-efficient power scheduling (EEPS) is essential for conserving power resource while delivering large data packets within hard-latency constraints. Traditional constrained reinforcement learning (CRL)…

Systems and Control · Electrical Eng. & Systems 2025-03-13 Kexuan Wang , An Liu

Robust reinforcement learning is essential for deploying reinforcement learning algorithms in real-world scenarios where environmental uncertainty predominates. Traditional robust reinforcement learning often depends on rectangularity…

Machine Learning · Computer Science 2024-06-13 Adil Zouitine , David Bertoin , Pierre Clavier , Matthieu Geist , Emmanuel Rachelson

Despite extensive progress on image generation, common deep generative model architectures are not easily applied to lossless compression. For example, VAEs suffer from a compression cost overhead due to their latent variables. This…

Machine Learning · Computer Science 2022-03-17 Anji Liu , Stephan Mandt , Guy Van den Broeck

Machine learning classifiers in dynamic environments face concept drift -- changes in the data-generating process that degrade performance. Conventional evaluation via static test sets or noise perturbations fails to preserve causal…

Machine Learning · Computer Science 2026-05-12 Julien Lafrance , Richard Khoury , Véronique Tremblay

Risk averse decision making under uncertainty in partially observable domains is a fundamental problem in AI and essential for reliable autonomous agents. In our case, the problem is modeled using partially observable Markov decision…

Artificial Intelligence · Computer Science 2024-06-11 Yaacov Pariente , Vadim Indelman

Determination of inspection and maintenance policies for minimizing long-term risks and costs in deteriorating engineering environments constitutes a complex optimization problem. Major computational challenges include the (i) curse of…

Artificial Intelligence · Computer Science 2020-07-06 C. P. Andriotis , K. G. Papakonstantinou

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

At the forefront of control techniques is Model Predictive Control (MPC). While MPCs are effective, their requisite to recompute an optimal control given a new state leads to sparse response to the system and may make their implementation…

Systems and Control · Electrical Eng. & Systems 2024-10-22 Josue N. Rivera , Jianqi Ruan , XiaoLin Xu , Shuting Yang , Dengfeng Sun , Neera Jain

We study online learning in constrained Markov decision processes (CMDPs) with adversarial losses and stochastic hard constraints, under bandit feedback. We consider three scenarios. In the first one, we address general CMDPs, where we…

Machine Learning · Computer Science 2025-02-10 Francesco Emanuele Stradi , Matteo Castiglioni , Alberto Marchesi , Nicola Gatti

Partial differential equations (PDEs) govern a wide range of physical systems, and recent multimodal foundation models have shown promise for learning PDE solution operators across diverse equation families. However, existing multi-operator…

Machine Learning · Computer Science 2025-12-30 Min Zhu , Jingmin Sun , Zecheng Zhang , Hayden Schaeffer , Lu Lu

We present a method for solving implicit (factored) Markov decision processes (MDPs) with very large state spaces. We introduce a property of state space partitions which we call epsilon-homogeneity. Intuitively, an epsilon-homogeneous…

Artificial Intelligence · Computer Science 2013-02-08 Thomas L. Dean , Robert Givan , Sonia Leach

Traditional electrostatic simulation are meshed-based methods which convert partial differential equations into an algebraic system of equations and their solutions are approximated through numerical methods. These methods are time…

Machine Learning · Computer Science 2024-12-03 Kart-Leong Lim , Rahul Dutta , Mihai Rotaru

LiDAR point cloud compression is vital for autonomous systems to handle massive data from high-resolution sensors. While learned entropy modeling built upon octree structures yields high compression gains, it faces two critical bottlenecks:…

Computer Vision and Pattern Recognition · Computer Science 2026-05-05 Jiahao Zhu , Kang You , Dandan Ding , Zhan Ma

Cross-Project Defect Prediction (CPDP), which borrows data from similar projects by combining a transfer learner with a classifier, have emerged as a promising way to predict software defects when the available data about the target project…

Software Engineering · Computer Science 2020-09-01 Ke Li , Zilin Xiang , Tao Chen , Kay Chen Tan

We study model-free reinforcement learning (RL) algorithms in episodic non-stationary constrained Markov Decision Processes (CMDPs), in which an agent aims to maximize the expected cumulative reward subject to a cumulative constraint on the…

Machine Learning · Computer Science 2023-03-13 Honghao Wei , Arnob Ghosh , Ness Shroff , Lei Ying , Xingyu Zhou

We optimize pipeline parallelism for deep neural network (DNN) inference by partitioning model graphs into $k$ stages and minimizing the running time of the bottleneck stage, including communication. We give practical and effective…

Machine Learning · Computer Science 2024-06-05 Aaron Archer , Matthew Fahrbach , Kuikui Liu , Prakash Prabhu

Robust Markov decision processes (r-MDPs) extend MDPs by explicitly modelling epistemic uncertainty about transition dynamics. Learning r-MDPs from interactions with an unknown environment enables the synthesis of robust policies with…

Machine Learning · Computer Science 2025-11-21 Yannik Schnitzer , Alessandro Abate , David Parker

Balancing exploration and exploitation is crucial in reinforcement learning (RL). In this paper, we study model-based posterior sampling for reinforcement learning (PSRL) in continuous state-action spaces theoretically and empirically.…

Machine Learning · Computer Science 2021-11-18 Ying Fan , Yifei Ming

While machine learning (ML) in experimental research has demonstrated impressive predictive capabilities, inductive reasoning and knowledge extraction remain elusive tasks, in part because of the difficulty extracting fungible knowledge…

Materials Science · Physics 2021-06-22 Richa Ramesh Naik , Armi Tiihonen , Janak Thapa , Clio Batali , Zhe Liu , Shijing Sun , Tonio Buonassisi

This paper studies the fundamental limits of reinforcement learning (RL) in the challenging \emph{partially observable} setting. While it is well-established that learning in Partially Observable Markov Decision Processes (POMDPs) requires…

Machine Learning · Computer Science 2023-02-03 Fan Chen , Huan Wang , Caiming Xiong , Song Mei , Yu Bai