Results 131 to 140 of about 171,350 (313)
Optoelectronic Devices for In‐Sensor Computing
Advanced Materials, EarlyView.The raw data obtained directly from sensors in the noisy analogue domain is often unstructured, which lacks a predefined format or organization and does not conform to a specific data model. Optoelectronic devices for in‐sensor visual processing can integrate perception, memory, and processing functions in the same physical units, which can compress ...
Qinqi Ren +7 more
wiley +1 more source
We present flow Q-learning (FQL), a simple and performant offline reinforcement learning (RL) method that leverages an expressive flow-matching policy to model arbitrarily complex action distributions in data. Training a flow policy with RL is a tricky problem, due to the iterative nature of the action generation process.
Park, Seohong +2 more
openaire +2 more sources
Finite-Time Error Analysis of Soft Q-Learning: Switching System Approach [PDF]
arXivSoft Q-learning is a variation of Q-learning designed to solve entropy regularized Markov decision problems where an agent aims to maximize the entropy regularized value function. Despite its empirical success, there have been limited theoretical studies of soft Q-learning to date.
arxiv
Advanced Materials, EarlyView.In this review, the recent development of deep‐blue (≤465 nm) perovskite light‐emitting diodes (PeLEDs) are summarized, using different perovskite nanomaterials, including nanocrystals (NCs), quantum dots (QDs), nanoplatelets (NPLs), quasi‐2D thin film, 3D bulk thin film, as well as lead‐free perovskite nanomaterials.
Pui Kei Ko +6 more
wiley +1 more source
Q-learning model of insight problem solving and the effects of learning traits on creativity. [PDF]
Front Psychol, 2023 Harada T.
europepmc +1 more source
Unified ODE Analysis of Smooth Q-Learning Algorithms [PDF]
arXivConvergence of Q-learning has been the focus of extensive research over the past several decades. Recently, an asymptotic convergence analysis for Q-learning was introduced using a switching system framework. This approach applies the so-called ordinary differential equation (ODE) approach to prove the convergence of the asynchronous Q-learning modeled
arxiv
Advanced Materials, EarlyView.The SciAgents AI model drives hypothesis generation by harnessing multi‐agent graph reasoning, extracting insights from knowledge graphs constructed from scientific papers. Each agent plays a specific role: the Ontologist defines concepts, the Scientists draft and refine proposals, and the Critic reviews.
Alireza Ghafarollahi, Markus J. Buehler
wiley +1 more source
Efficient learning of reactive robot behaviors with a Neural-Q/spl I.bar/learning approach [PDF]
, 2003 Marc Carreras +3 more
openalex +1 more source
Advanced Materials, EarlyView.The rise of lead halide perovskite semiconductors has enabled high‐performance LEDs with internal quantum efficiencies approaching 100%. In order to further enhance the external quantum efficiencies limited by light outcoupling effects, in this account, the strategies for reducing energy dissipation through the substrate, waveguide, and evanescent ...
Tommaso Marcato +2 more
wiley +1 more source
Modified interactive Q-learning for attenuating the impact of model misspecification with treatment effect heterogeneity. [PDF]
Stat Methods Med Res, 2023 Zhang Y, Vock DM, Patrick ME, Murray TA.
europepmc +1 more source