Results 111 to 120 of about 112,162 (267)

Fairness in Reinforcement Learning

, 2016
We initiate the study of fairness in reinforcement learning, where the actions of a learning algorithm may affect its environment and future rewards. Our fairness constraint requires that an algorithm never prefers one action over another if the long-term (discounted) reward of choosing the latter action is higher. Our first result is negative: despite
Shahin Jabbari, Matthew Joseph, Michael J. Kearns, Jamie Morgenstern, Aaron Roth 0001   +4 more
openaire   +3 more sources

Nanomaterial Strategies for Pulmonary Delivery of Immunotherapeutics in Lung Cancer Treatment

Advanced Healthcare Materials, EarlyView.
Inhalable immunotherapeutic nanomedicines enable organ‐selective immune modulation by overcoming pulmonary delivery barriers and concentrating therapy within lung tumors. This Review defines how nanomaterial properties govern airway deposition, retention, cellular partitioning, and immune activation across vaccines, checkpoint blockade, STING agonists,
Han Zhang, Wei Tang
wiley   +1 more source

Learning graph based individual intrinsic reward for multi-agent reinforcement learning

ICT Express
Designing a reward function is a critical challenge in reinforcement learning. However, as environments become more complex and tasks grow more difficult, designing a reward function that drives optimal behavior becomes increasingly challenging.
Seokhun Ju, Seungyub Han, Taehyun Cho, Jungwoo Lee, Taeyoung Lee, Minkyoung Kim, Jinho An   +6 more
doaj   +1 more source

Artificial Intelligence‐Assisted Workflow for Transmission Electron Microscopy: From Data Analysis Automation to Materials Knowledge Unveiling

Advanced Materials, EarlyView.
AI‐Assisted Workflow for (Scanning) Transmission Electron Microscopy: From Data Analysis Automation to Materials Knowledge Unveiling. Abstract (Scanning) transmission electron microscopy ((S)TEM) has significantly advanced materials science but faces challenges in correlating precise atomic structure information with the functional properties of ...
Marc Botifoll, Ivan Pinto‐Huguet, Enzo Rotunno, Thomas Galvani, Catalina Coll, Payam Habibzadeh Kavkani, Maria Chiara Spadaro, Yann‐Michel Niquet, Martin Børstad Eriksen, Sara Martí‐Sánchez, Georgios Katsaros, Giordano Scappucci, Peter Krogstrup, Giovanni Isella, Andreu Cabot, Gonzalo Merino, Pablo Ordejón, Stephan Roche, Vincenzo Grillo, Jordi Arbiol   +19 more
wiley   +1 more source

Beyond Presumptions: Toward Mechanistic Clarity in Metal‐Free Carbon Catalysts for Electrochemical H2O2 Production via Data Science

Advanced Materials, EarlyView.
Metal‐free carbon catalysts enable the sustainable synthesis of hydrogen peroxide via two‐electron oxygen reduction; however, active site complexity continues to hinder reliable interpretation. This review critiques correlation‐based approaches and highlights the importance of orthogonal experimental designs, standardized catalyst passports ...
Dayu Zhu, Hsi‐wen Wu, Xiao Wang, Jie Zhang   +3 more
wiley   +1 more source

Topology and Material Optimization in Ultra‐Soft Magneto‐Active Structures: Making Advantage of Residual Anisotropies

Advanced Materials, EarlyView.
Residual magnetization induces pronounced mechanical anisotropy in ultra‐soft magnetorheological elastomers, shaping deformation and actuation even without external magnetic fields. This study introduces a computational‐experimental framework integrating magneto‐mechanical coupling into topology optimization for designing soft magnetic actuators with ...
Carlos Perez‐Garcia, Rogelio Ortigosa, Jesús Martínez‐Frutos, Daniel Garcia‐Gonzalez   +3 more
wiley   +1 more source

Robustness evaluation of offline reinforcement learning for robot control against action perturbations

International Journal of Advanced Robotic Systems
Offline reinforcement learning, which learns solely from datasets without environmental interaction, has gained attention. This approach, similar to traditional online deep reinforcement learning, is particularly promising for robot control applications.
Shingo Ayabe, Takuto Otomo, Hiroshi Kera, Kazuhiko Kawamoto   +3 more
doaj   +1 more source

Enhancing Safe Exploration Through Subgoal Guidance

Technologies
Reinforcement learning is a widely used approach for autonomous navigation, but it often struggles to reach distant, long-horizon goals under safety constraints. The primary reason for this suboptimal performance is that safety requirements significantly
Gregory Gorbov, Aleksandr Panov
doaj   +1 more source

Experiential Reinforcement Learning

CoRR
Reinforcement learning has become the central approach for language models (LMs) to learn from environmental reward or feedback. In practice, the environmental feedback is usually sparse and delayed. Learning from such signals is challenging, as LMs must implicitly infer how observed failures should translate into behavioral changes for future ...
Taiwei Shi, Sihao Chen, Bowen Jiang, Linxin Song, Longqi Yang 0001, Jieyu Zhao 0001   +5 more
openaire   +2 more sources

Self‐Assembled Monolayers in p–i–n Perovskite Solar Cells: Molecular Design, Interfacial Engineering, and Machine Learning–Accelerated Material Discovery

Advanced Materials, EarlyView.
This review highlights the role of self‐assembled monolayers (SAMs) in perovskite solar cells, covering molecular engineering, multifunctional interface regulation, machine learning (ML) accelerated discovery, advanced device architectures, and pathways toward scalable fabrication and commercialization for high‐efficiency and stable single‐junction and
Asmat Ullah, Ying Luo, Stefaan De Wolf
wiley   +1 more source