Results 81 to 90 of about 112,162 (267)

Multiagent Deep Reinforcement Learning Algorithms in StarCraft II: A Review

IEEE Access
StarCraft II, as a real-time strategy game, features multiagent collaboration, complex decision-making processes, partially observable environments, and long-term credit assignment; thus, it is an ideal platform for exploring, validating, and optimizing ...
Yanyan Li, Yijun Wang, Yiwei Zhou
doaj   +1 more source

What Do Large Language Models Know About Materials?

Advanced Engineering Materials, EarlyView.
If large language models (LLMs) are to be used inside the material discovery and engineering process, they must be benchmarked for the accurateness of intrinsic material knowledge. The current work introduces 1) a reasoning process through the processing–structure–property–performance chain and 2) a tool for benchmarking knowledge of LLMs concerning ...
Adrian Ehrenhofer, Thomas Wallmersperger, Gianaurelio Cuniberti   +2 more
wiley   +1 more source

Improving sample efficiency and exploration in upside-down reinforcement learning

Journal of Information and Intelligence
Supervised learning has been demonstrated to be a stable approach for training deep neural networks. Upside-down reinforcement learning solves reinforcement learning problems by using supervised learning, but this method suffers from weak sample ...
Mohammadreza Nakhaei, Reza Askari Moghadam   +1 more
doaj   +1 more source

Thermodynamic Pathways of Nonequilibrium Solidification in Wire‐Arc Additive Manufacturing Fe‐Based Multicomponent Alloy Structures

Advanced Engineering Materials, EarlyView.
Geometry‐driven thermal behavior in wire‐arc additive manufacturing (WAAM) influences microstructural evolution during nonequilibrium solidification of a chemically complex Fe–Cr–Nb–W–Mo–C nanocomposite system. By comparing different deposits configurations, distinct entropy–cooling rate correlations, segregation, and carbide evolution are revealed ...
Blanca Palacios, Anthony Gonzalez, Aleksander Aleman, Tyler Dolmetsch, Tanaji Paul, Arvind Agarwal   +5 more
wiley   +1 more source

A Simplified Laminar Flow Model for the Pultrusion of Glass Fiber/Polyethylene Terephthalate Commingled Yarns

Advanced Engineering Materials, EarlyView.
A simplified thermoplastic pultrusion model is developed to predict thermal fields in glass fiber/polyethylene terephthalate (GF/PET) composites with reduced computational cost. By combining effective material homogenization, validation against literature data, and Gaussian‐process‐based optimization, the study reveals how heating limits, pulling speed,
Elder Soares, Nadège Bouchonneau, Christian Jochum, Donald Radford   +3 more
wiley   +1 more source

Learning to Hint for Reinforcement Learning

CoRR
Group Relative Policy Optimization (GRPO) is widely used for reinforcement learning with verifiable rewards, but it often suffers from advantage collapse: when all rollouts in a group receive the same reward, the group yields zero relative advantage and thus no learning signal.
Yu Xia 0007, Canwen Xu, Zhewei Yao, Julian J. McAuley, Yuxiong He   +4 more
openaire   +2 more sources

Is an Apple an Orange? A Large Language Model Benchmark for Candidate Term Extraction and Subclass Decisions Against Upper Ontologies in Engineering and Materials Science

Advanced Engineering Materials, EarlyView.
Building machine‐readable vocabularies for materials science is slow, expert‐driven work. This study benchmarks 13 large language models on two of its first steps: finding candidate terms in engineering articles and deciding where they belong in a class hierarchy.
Thomas Bjarsch, Maximilian Holland, Klaus Drechsler, Johannes Schilp   +3 more
wiley   +1 more source

A Lightweight Procedural Layer for Hybrid Experimental–Computational Workflows in Materials Science

Advanced Engineering Materials, EarlyView.
We unveil a prototype hybrid‐workflow framework that fuses automatedcomputation with hands‐on experiments. Built atop pyiron, a lightweight, parameterized layer translates procedure descriptions into executable manual steps, syncing instrument settings, human interventions, and data capture in real‐time today.
Steffen Brinckmann, Sarath Menon, Raphael Röske, Johannes Steinhülb, Michael Selzer, Jan Janssen, Tilmann Hickel, Ruth Schwaiger, Jörg Neugebauer   +8 more
wiley   +1 more source

Reinforcement learning-based energy management for hybrid electric vehicles: A comprehensive up-to-date review on methods, challenges, and research gaps

Energy and AI
Reinforcement learning is widely used for control applications and has also been successfully implemented for efficient energy management within hybrid electric vehicles.
Mohamed Nadir Boukoberine, Muhammad Fahad Zia, Tarek Berghout, Mohamed Benbouzid   +3 more
doaj   +1 more source

Review of Generative Reinforcement Learning Based on Sequence Modeling [PDF]

Jisuanji kexue
Reinforcement learning is a branch of machine learning on how to learn decisions,which is a sequential decision-making problem that involves repeatedly interacting with the environment to find the optimal strategy through trial and error.Reinforcement ...
YAO Tianlei, CHEN Xiliang, YU Peiyi
doaj   +1 more source