Results 71 to 80 of about 9,252,589 (289)

Deep reinforcement learning: Bridging learning and control in intelligent systems

Deep Reinforcement Learning (DRL) has gained popularity as a new approach in artificial intelligence that successfully integrates representation learning through Deep Learning with decision making in Reinforcement Learning.
Şahin, C. B., Raza, A., Zitar, R. A., Abualigah, L., Thanh, H. V., Smerat, A., Al-Okbi, N. K., Liu, Z., Izci, D.   +8 more
core   +1 more source

Advanced Manufacturing of Composite‐Based Systems for Energy Applications

Advanced Materials Technologies, EarlyView.
Advanced manufacturing enables the integration of polymers, ceramics, metal oxides, and composites into architected microstructures with tailored transport pathways. By coupling material selection, manufacturing strategy, and structural design, multifunctional energy systems can simultaneously improve electrochemical performance, thermal management ...
Sri Vaishnavi Thummalapalli, Dhanush Patil, Libin Yang, M. Taylor Sobczak, Anshul Kulkarni, Xiao Sun, Arunachalam Ramanathan, Tiantian Li, Ramaraja P. Ramasamy, Jason J. Locklin, Yanyu Chen, Xianqiao Wang, Arunachala Mada Kannan, Kenan Song   +13 more
wiley   +1 more source

The Future of Research in Cognitive Robotics: Foundation Models or Developmental Cognitive Models?

Advanced Robotics Research, EarlyView.
Research in cognitive robotics founded on principles of developmental psychology and enactive cognitive science would yield what we seek in autonomous robots: the ability to perceive its environment, learn from experience, anticipate the outcome of events, act to pursue goals, and adapt to changing circumstances without resorting to training with ...
David Vernon
wiley   +1 more source

Deep reinforcement learning for integrated vessel path planning with safe anchorage allocation

Brodogradnja
This study addresses vessel path planning and anchorage allocation through a reinforcement learning approach. To improve maritime safety and efficiency, we developed an integrated system that combines Deep Q-Network and Artificial Potential Field ...
Gil-Ho Shin, Hyun Yang
doaj   +1 more source

On the Limits of Digital Twins for Safe Deep Reinforcement Learning in Robotic Networks

IEEE INFOCOM 2024 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)
Successfully training models which address the complex nature of real environments in Smart Cities and robotic networks is challenging, due to the vast amount of data needed. When employing Reinforcement Learning (RL) models, it is also impossible to let them explore all the actions in the real world, due to potential damages and inappropriate actions.
Balghouthi M. I., Chiariotti F., Bedogni L.   +2 more
openaire   +3 more sources

Spectral normalisation for deep reinforcement learning: an optimisation perspective [PDF]

, 2021
Most of the recent deep reinforcement learning advances take an RL-centric perspective and focus on refinements of the training objective. We diverge from this view and show we can recover the performance of these developments not by changing the ...
Berariu, Tudor, Rosca, Mihaela, Clopath, Claudia, Gogianu, Florin, Pascanu, Razvan, Busoniu, Lucian   +5 more
core  

Nonlocomotory Robotic Strategies for Dynamic Rotation Control in Terrestrial Robots: A Review

Advanced Robotics Research, EarlyView.
Terrestrial robots increasingly require rapid body rotation to maintain stability and agility in complex environments. This review shows nonlocomotory rotational control strategies that operate without ground contact, including reaction wheels, tails, bars, limbs, and thrusters.
Y. Liang, J. An, X. Zheng, D. Wang, S. Wang, X. Wang, P. Zhu, J. Pei, S. Li, J. Paripurana, Y. Han, Z. Tang, X. Gan, Q. He, X. Ma   +14 more
wiley   +1 more source

Adaptive Action-Constraint Safe Driving Decision Control Algorithm Based on Deep Reinforcement Learning

IEEE Open Journal of Intelligent Transportation Systems
Autonomous driving has the potential to greatly enhance traffic efficiency, and its effectiveness depends on robust decision-making in complex real-world environments.
Rui Guo, Xinyu Li, Zhonghao Fu, Lei Wang
doaj   +1 more source

Resilience Improvement Strategy for the Electrification-Transportation Coupling Network Based on Safe Deep Reinforcement Learning [PDF]

Dianli jianshe
[Objective] To address the problems that when large-scale electrification-transportation coupling network （ETCN） encounters sudden resilience faults， traditional schemes have slow generation speed， are difficult to respond to dynamic information ...
XU Ding, YANG Qiming, WU Mingming, FU Chaoran, XING Qiang, ZHANG Guoli, WANG Mingshen
doaj   +1 more source

Safe Deep Model-Based Reinforcement Learning with Lyapunov Functions

CoRR
Model-based Reinforcement Learning (MBRL) has shown many desirable properties for intelligent control tasks. However, satisfying safety and stability constraints during training and rollout remains an open question. We propose a new Model-based RL framework to enable efficient policy learning with unknown dynamics based on learning model predictive ...
openaire   +3 more sources