Results 71 to 80 of about 57,740 (314)

Deep Residual Reinforcement Learning

, 2019
We revisit residual algorithms in both model-free and model-based reinforcement learning settings. We propose the bidirectional target network technique to stabilize residual algorithms, yielding a residual version of DDPG that significantly outperforms vanilla DDPG in the DeepMind Control Suite benchmark.
Zhang, S, Boehmer, W, Whiteson, S
openaire   +3 more sources

Deep learning, reinforcement learning, and world models

Neural Networks, 2022
Deep learning (DL) and reinforcement learning (RL) methods seem to be a part of indispensable factors to achieve human-level or super-human AI systems. On the other hand, both DL and RL have strong connections with our brain functions and with neuroscientific findings.
Yutaka Matsuo, Yann LeCun, Maneesh Sahani, Doina Precup, David Silver, Masashi Sugiyama, Eiji Uchibe, Jun Morimoto   +7 more
openaire   +3 more sources

Impact of a senior research thesis on students' perceptions of scientific inquiry in distinct student populations

FEBS Open Bio, EarlyView.
This study addressed how a senior research thesis is perceived by undergraduate students. It assessed students' perception of research skills, epistemological beliefs, and career goals in Biochemistry (science) and BDC (science‐business) students. Completing a thesis improved confidence in research skills, resilience, scientific identity, closed gender‐
Celeste Suart, Haley L. Zubyk, Michelle Ogrodnik, Caitlin E. Mullarkey, Felicia Vulcu   +4 more
wiley   +1 more source

A new approach for drone tracking with drone using Proximal Policy Optimization based distributed deep reinforcement learning

SoftwareX, 2023
In this paper, a distributed deep reinforcement learning algorithm based on Proximal Policy Optimization (PPO) is proposed for an unmanned aerial vehicle (UAV) to autonomously track another UAV. Accordingly, this paper makes three important contributions
Ziya Tan, Mehmet Karaköse
doaj   +1 more source

A Q‐Learning Algorithm to Solve the Two‐Player Zero‐Sum Game Problem for Nonlinear Systems

International Journal of Adaptive Control and Signal Processing, Volume 39, Issue 3, Page 566-581, March 2025.
A Q‐learning algorithm to solve the two‐player zero‐sum game problem for nonlinear systems. ABSTRACT This paper deals with the two‐player zero‐sum game problem, which is a bounded L2$$ {L}_2 $$‐gain robust control problem. Finding an analytical solution to the complex Hamilton‐Jacobi‐Issacs (HJI) equation is a challenging task.
Afreen Islam, Anthony Siming Chen, Guido Herrmann   +2 more
wiley   +1 more source

Aero-Engine Modeling and Control Method with Model-Based Deep Reinforcement Learning

Aerospace, 2023
Due to the strong representation ability and capability of learning from data measurements, deep reinforcement learning has emerged as a powerful control method, especially for nonlinear systems, such as the aero-engine control system.
Wenbo Gao, Muxuan Pan, Wenxiang Zhou, Feng Lu, Jin-Quan Huang   +4 more
doaj   +1 more source

3D In Vitro Models of Breast Cancer: Current Challenges and Future Prospects Toward Recapitulating the Microenvironment and Mimicking Key Processes

Advanced Biology, EarlyView.
In vitro cancer models are advantageous for studying important processes such as tumorigenesis, cancer growth, invasion, and metastasis. The complexity and biological relevance increase depending on the model structure, organization, and composition of materials and cells.
Kyndra S. Higgins, Ah Joung Yu, Cheryl T. Gomillion   +2 more
wiley   +1 more source

Bridging Nature and Technology: A Perspective on Role of Machine Learning in Bioinspired Ceramics

Advanced Engineering Materials, EarlyView.
Machine learning (ML) is revolutionizing the development of bioinspired ceramics. This article investigates how ML can be used to design new ceramic materials with exceptional performance, inspired by the structures found in nature. The research highlights how ML can predict material properties, optimize designs, and create advanced models to unlock a ...
Hamidreza Yazdani Sarvestani, Aditi Singh, Behnam Ashrafi   +2 more
wiley   +1 more source

Review of Deep Reinforcement Learning-Based Object Grasping: Techniques, Open Challenges, and Recommendations

IEEE Access, 2020
The motivation behind our work is to review and analyze the most relevant studies on deep reinforcement learning-based object manipulation. Various studies are examined through a survey of existing literature and investigation of various aspects, namely,
Marwan Qaid Mohammed, Kwek Lee Chung, Chua Shing Chyi   +2 more
doaj   +1 more source

Static and Dynamic Behavior of Novel Y‐Shaped Sandwich Beams Subjected to Compressive Loadings: Integration of Supervised Learning and Experimentation

Advanced Engineering Materials, EarlyView.
In this study, the mechanical response of Y‐shaped core sandwich beams under compressive loading is investigated, using deep feed‐forward neural networks (DFNNs) for predictive modeling. The DFNN model accurately captures stress–strain behavior, influenced by design parameters and loading rates.
Ali Khalvandi, Saeed Kamarian, Mahdi Bodaghi, Saeed Saber‐Samandari, Jung‐il Song   +4 more
wiley   +1 more source