Near-optimal Deep Reinforcement Learning Policies from Data for Zone Temperature Control

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Interactive simulations enhance science education and foster inquiry skills, but their open-ended nature can be cognitively overloading. While adaptive systems offer timely support, research on predicting conceptual understanding in these environments is l ...

Mountain regions face a variety of natural hazards that menace infrastructure and the people living in these areas. Human activity in these areas is intensifying, making hazard analysis and risk mitigation critical. Switzerland, with its densely populated ...

Integer linear programming (ILP) is an elegant approach to solve linear optimization problems, naturally described using integer decision variables. Within the context of physics-inspired machine learning (ML) applied to chemistry, we demonstrate the relev ...

For robots to operate in unstructured environments, they are required to interact with objects through contact. Those contacts may be used to push objects to the side, deform objects, or manipulate objects in-hand. This thesis addresses the problem of cont ...

This paper introduces a novel architecture for Quantum Graph Neural Networks, which is significantly different from previous approaches found in the literature. The proposed approach produces similar outcomes with respect to previous models but with fewer ...

Photorealistic synthetic data and novel rendering techniques significantly advanced computer vision research. However, datasets focused on computer vision applications cannot be easily applied to robotics because they typically lack physics-related informa ...

Deep learning (DL) has recently been proposed as a novel approach for 21cm foreground removal. Before applying DL to real observations, it is essential to assess its consistency with established methods, its performance across various simulation models, an ...

The physical mechanisms regulating the power sharing at the outer targets of L-mode double-null (DN) configurations are investigated using nonlinear, flux-driven, three-dimensional two-fluid simulations. Scans of parameters that regulate the turbulent leve ...

In this work, we provide important parameters to take into account when fabricating in-plane III-V photodetectors (PDs) integrated on silicon (Si) using template-assisted selective epitaxy (TASE). Their performance has previously been demonstrated, and her ...

A review is given on the highlights of a scatter-shot approach of developing machine-learning methods and artificial neural networks based fast predictors for the application to fusion exhaust. The aim is to enable and facilitate optimized and improved mod ...

The Industrial Internet of Things (IIoT) is reshaping manufacturing, industrial processes, and infrastructure management. By fostering new levels of automation, efficiency, and predictive maintenance, IIoT is transforming traditional industries into intell ...

The transition to sustainable energy demands a fundamental redesign of the electrical grid, especially at the distribution level. With the increasing deployment of distributed energy resources, the development of reliable models, accurate state estimation ...

Computational chemistry techniques offer tremendous potential for accelerating the discovery of sustainable chemical processes and reactions. However, the environmental impacts of the substantial computing power required for these digital methods are often ...

The proliferation of microscopy methods for live-cell imaging offers many new possibilities for users but can also be challenging to navigate. The prevailing challenge in live-cell fluorescence microscopy is capturing intra-cellular dynamics while preservi ...

Ride-hailing services are emerging as a mode of transportation, necessitating modeling and control methods for efficient management. In this paper, we propose a hierarchical control framework for the optimal positioning of idle vehicles for maximizing serv ...

The outstanding information processing capacity of the brain relies on numerous molecular mechanisms. It is an extremely energy-expensive function, which involves specialization and collaboration of different cell types. A common framework to study the com ...

In this article, we consider decentralized optimization problems where agents have individual cost functions to minimize subject to subspace constraints that require the minimizers across the network to lie in low-dimensional subspaces. This constrained fo ...

By supporting the access of multiple memory words at the same time, Bit-line Computing (BC) architectures allow the parallel execution of bit-wise operations in-memory. At the array periphery, arithmetic operations are then derived with little additional o ...

Reed-Muller (RM) codes achieve the capacity of general binary-input memoryless symmetric channels and are conjectured to have a comparable performance to that of random codes in terms of scaling laws. However, such results are established assuming maximum- ...

Activity-based models offer the potential of a far deeper understanding of daily mobility behaviour than trip-based models. However, activity-based models used both in research and practice have often relied on applying sequential choice models between sub ...

Near-optimal Deep Reinforcement Learning Policies from Data for Zone Temperature Control

Chat with Graph Search

One Code to Predict Them All: Universal Encoding for Inquiry Modeling

Granular Avalanche Impact on a Structure using DEM and FEM

Integer Linear Programming for Unsupervised Training Set Selection in Molecular Machine Learning

A Stochastic Approach to Contact-rich Manipulation

A Study on Quantum Graph Neural Networks Applied to Molecular Physics

GRADE: Generating Realistic and Dynamic Environments for robotics research with Isaac Sim

The stability of deep learning for 21cm foreground removal across various sky models and frequency-dependent systematics

Predictive power-sharing scaling law in double-null L-mode plasmas

Simulation and Fabrication of Monolithic III-V Photodetectors on Si: The Role of Growth Facets and Localization of Heterojunctions

Data-driven models in fusion exhaust: AI methods and perspectives

Physics-Enhanced Graph Neural Networks for Soft Sensing in Industrial Internet of Things

Estimation and control under uncertainty with application to power systems

Balancing computational chemistry's potential with its environmental impact

Live-cell imaging powered by computation

A Two-layer Approach for Rebalancing Ride-hailing Vehicles

Molecular reconstruction and simulation of the Neuron-Glia-Vasculature system

Quantization for Decentralized Learning Under Subspace Constraints

Bit-Line Computing for CNN Accelerators Co-Design in Edge AI Inference

Machine Learning-Aided Efficient Decoding of Reed-Muller Subcodes

OASIS: Optimisation-based Activity Scheduling with Integrated Simultaneous choice dimensions