Results 121 to 130 of about 212,484 (267)
Q-learning with Posterior Sampling
CoRRBayesian posterior sampling techniques have demonstrated superior empirical performance in many exploration-exploitation settings. However, their theoretical analysis remains a challenge, especially in complex settings like reinforcement learning. In this paper, we introduce Q-Learning with Posterior Sampling (PSQL), a simple Q-learning-based algorithm
Priyank Agrawal +2 more
openaire +2 more sources
Advanced Materials, EarlyView.Path‐decoupled III–V van der Waals memtransistors spatially separate ionic and electronic transport to overcome the conventional trade‐off between accuracy and energy in neuromorphic hardware. Mobile K+ ions in the vdW gaps set a wide conductance window, Gmax/Gmin, while gate‐tunable hole conduction lowers programming energy, enabling reliable ...
Jihong Bae +13 more
wiley +1 more source
MathematicsRegarding autonomous vehicle navigation, reinforcement learning is a technique that has demonstrated significant results. Nevertheless, it is a technique with a high number of parameters that need to be optimised without prior information, and correctly ...
Mireya Cabezas-Olivenza +4 more
doaj +1 more source
Measuring the Hall Effect in Hysteretic Materials
Advanced Materials, EarlyView.The authors highlight common pitfalls in measuring the Hall effect: in hysteretic magnets, improper data processing can create signals that look exotic but are not real. This Perspective explains the origin of these artifacts and presents practical measurement strategies that help researchers identify reliable Hall responses in complex magnetic ...
Jaime M. Moya +6 more
wiley +1 more source
Advanced Materials, EarlyView.Co1/3TaS2${\rm Co}_{1/3}{\rm TaS}_{2}$ hosts a triple‐Q noncoplanar antiferromagnetic state with coexisting Z3${\rm Z}_3$ electronic nematicity. We report rotational hysteresis observed in both magnetoresistance and magnetic torque, revealing strongly pinned in‐plane weak ferromagnetic moments in the triple‐Q phase and the magnetism‐driven nature of ...
Joonyoung Choi +5 more
wiley +1 more source
Q-learning as a monotone scheme
CoRRStability issues with reinforcement learning methods persist. To better understand some of these stability and convergence issues involving deep reinforcement learning methods, we examine a simple linear quadratic example. We interpret the convergence criterion of exact Q-learning in the sense of a monotone scheme and discuss consequences of function ...
openaire +3 more sources
Advanced Materials, EarlyView.A transparent, deformable stevia–PVA hydrogel triboelectric nanogenerator delivers significantly enhanced mechanical strength and electrical output through biomimetic hydrogen‐bonded networks. Coupled with machine learning–assisted signal recognition, the self‐powered hydrogel enables accurate human‐motion sensing for intelligent wearable and IoT ...
Thien Trung Luu +5 more
wiley +1 more source
Phase Engineering of Nanomaterials (PEN): Evolution, Current Challenges, and Future Opportunities
Advanced Materials, EarlyView.This review summarizes the synthesis, phase transition, advanced characterization spanning ex situ to in situ and operando techniques, and diverse applications of phase engineering of nanomaterials (PEN). It further outlines key challenges and future opportunities, such as phase stability, architecture control, and artificial intelligence (AI)‐driven ...
Ye Chen +7 more
wiley +1 more source
Advanced Materials, EarlyView.This review summarizes the principles and challenges of nonaqueous lithium‐oxygen batteries and recent advances in cathode catalysts, including carbon‐based materials, metals, oxides, sulfides, nitrides, carbides, and redox mediators. It highlights emerging design strategies and artificial intelligence‐driven approaches, emphasizing data‐assisted ...
Yuqing Yao +8 more
wiley +1 more source
Advanced Materials, EarlyView.We introduce a computational workflow that combines quantum chemical calculations and machine learning techniques to predict the catalytic performance of a wide range of catalysts in the nitrogen reduction reaction (NRR). The analysis of the trained models provides insights into the complex structure–activity relationship in experimental catalytic ...
Leonardo Di Ciano +5 more
wiley +1 more source