Results 131 to 140 of about 544,487 (316)
Accelerated Reinforcement Learning
2017 14th IEEE India Council International Conference (INDICON), 2017 Policy gradient methods are widely used in reinforcement learning algorithms to search for better policies in the parameterized policy space. They do gradient search in the policy space and are known to converge very slowly. Nesterov developed an accelerated gradient search algorithm for convex optimization problems. This has been recently extended for
openaire +3 more sources
An Adaptive Energy Management Strategy for Off-Road Hybrid Tracked Vehicles
EnergiesConventional energy management strategies based on reinforcement learning often fail to achieve their intended performance when applied to driving conditions that significantly deviate from their training conditions.
Lijin Han, Wenhui Shi, Ningkang Yang
doaj +1 more source
Effect of intertrial reinforcement and nonreinforcement on reversal learning [PDF]
, 1967 James Bowen
openalex +1 more source
Fast‐Charging Solid‐State Li Batteries: Materials, Strategies, and Prospects
Advanced Materials, EarlyView.This review addresses challenges and recent advances in fast‐charging solid‐state batteries, focusing on solid electrolyte and electrode materials, as well as interfacial chemistries. The role of multiscale modeling and simulation in understanding Li+ transport and interfacial phenomena is emphasized, providing insights into materials, strategies, and ...
Jing Yu +7 more
wiley +1 more source
Photonic Nanomaterials for Wearable Health Solutions
Advanced Materials, EarlyView.This review discusses the fundamentals and applications of photonic nanomaterials in wearable health technologies. It covers light‐matter interactions, synthesis, and functionalization strategies, device assembly, and sensing capabilities. Applications include skin patches and contact lenses for diagnostics and therapy. Future perspectives emphasize AI‐
Taewoong Park +3 more
wiley +1 more source
Naturalistic reinforcement learning
Trends in Cognitive SciencesHumans possess a remarkable ability to make decisions within real-world environments that are expansive, complex, and multidimensional. Human cognitive computational neuroscience has sought to exploit reinforcement learning (RL) as a framework within which to explain human decision-making, often focusing on constrained, artificial experimental tasks ...
Wise, Toby +2 more
openaire +2 more sources
A Survey Analyzing Generalization in Deep Reinforcement Learning [PDF]
arXivReinforcement learning research obtained significant success and attention with the utilization of deep neural networks to solve problems in high dimensional state or action spaces. While deep reinforcement learning policies are currently being deployed in many different fields from medical applications to large language models, there are still ongoing
arxiv
Smart Dust for Chemical Mapping
Advanced Materials, EarlyView.This review article explores the advancement of smart dust networks for high‐resolution spatial and temporal chemical mapping. Comprising miniature, wireless sensors, and communication devices, smart dust autonomously collects, processes, and transmits data via swarm‐based communication.
Indrajit Mondal, Hossam Haick
wiley +1 more source
Micro‐ and Nano‐Bots for Infection Control
Advanced Materials, EarlyView.This review presents a strategic vision for integrating micro‐ and nanobots in the pipeline for infection diagnosis, prevention, and treatment. To develop these robots as a practical solution for infection management, their design principles are clarified based on their propulsion mechanisms and then categorized infection management domains based on ...
Azin Rashidy Ahmady +5 more
wiley +1 more source
Fixed ratio schedule of reinforcement as a determinant of successive discrimination reversal learning in the pigeon [PDF]
, 1971 Ben A. Williams
openalex +1 more source