Results 31 to 40 of about 404,230 (315)

Flowsheet synthesis through hierarchical reinforcement learning and graph neural networks [PDF]

AIChE Journal, 2022
Process synthesis experiences a disruptive transformation accelerated by digitization and artificial intelligence. We propose a reinforcement learning algorithm for chemical process design based on a state-of-the-art actor-critic logic.
Laura Stops, Roel Leenhouts, Qitong Gao, Artur M. Schweidtmann   +3 more
semanticscholar   +1 more source

Hierarchical reinforcement learning for automatic disease diagnosis

Bioinformatics, 2022
AbstractMotivationDisease diagnosis-oriented dialog system models the interactive consultation procedure as the Markov decision process, and reinforcement learning algorithms are used to solve the problem. Existing approaches usually employ a flat policy structure that treat all symptoms and diseases equally for action making.
Cheng Zhong, Kangenbei Liao, Wei Chen, Qianlong Liu, Baolin Peng, Xuanjing Huang, Jiajie Peng, Zhongyu Wei   +7 more
openaire   +3 more sources

Hierarchical Reinforcement Learning for Air-to-Air Combat [PDF]

International Conference on Unmanned Aircraft Systems, 2021
Artificial Intelligence (AI) is becoming a critical component in the defense industry, as recently demonstrated by DARPA's AlphaDogfight Trials (ADT). ADT sought to vet the feasibility of AI algorithms capable of piloting an F-16 in simulated air-to-air ...
Adrian P. Pope, J. Ide, Daria Mićović, Henry Diaz, D. Rosenbluth, Lee Ritholtz, Jason C. Twedt, Thayne T. Walker, K. Alcedo, D. Javorsek   +9 more
semanticscholar   +1 more source

Hierarchical Reinforcement Learning Under Mixed Observability

, 2022
Accepted at the 15th International Workshop on the Algorithmic Foundations of Robotics (WAFR) 2022, University of Maryland, College Park.
Nguyen, Hai, Yang, Zhihan, Baisero, Andrea, Ma, Xiao, Platt, Robert, Amato, Christopher   +5 more
openaire   +2 more sources

Option-Critic Algorithm Based on Mutual Information Optimization [PDF]

Jisuanji kexue
As an important research content of hierarchical reinforcement learning,temporal abstraction allows hierarchical reinforcement learning agents to learn policies at different time scales,which can effectively solve the sparse reward problem that is ...
LI Junwei, LIU Quan, XU Yapeng
doaj   +1 more source

Optimal Hierarchical Learning Path Design With Reinforcement Learning

Applied Psychological Measurement, 2020
E-learning systems are capable of providing more adaptive and efficient learning experiences for learners than traditional classroom settings. A key component of such systems is the learning policy. The learning policy is an algorithm that designs the learning paths or rather it selects learning materials for learners based on information such as the ...
Xiao Li, Hanchen Xu, Jinming Zhang, Hua-hua Chang   +3 more
openaire   +4 more sources

A Reward Optimization Method Based on Action Subrewards in Hierarchical Reinforcement Learning

The Scientific World Journal, 2014
Reinforcement learning (RL) is one kind of interactive learning methods. Its main characteristics are “trial and error” and “related reward.” A hierarchical reinforcement learning method based on action subrewards is proposed to solve the problem of ...
Yuchen Fu, Quan Liu, Xionghong Ling, Zhiming Cui   +3 more
doaj   +1 more source

Planning Irregular Object Packing via Hierarchical Reinforcement Learning [PDF]

IEEE Robotics and Automation Letters, 2022
Object packing by autonomous robots is an important challenge in warehouses and logistics industry. Most conventional data-driven packing planning approaches focus on regular cuboid packing, which are usually heuristic and limit the practical use in ...
Sichao Huang, Ziwei Wang, Jie Zhou, Jiwen Lu   +3 more
semanticscholar   +1 more source

A Hierarchical Goal-Biased Curriculum for Training Reinforcement Learning

Proceedings of the International Florida Artificial Intelligence Research Society Conference, 2022
Hierarchy and curricula are two techniques commonly used to improve training for Reinforcement Learning (RL) agents. Yet few works have examined how to leverage hierarchical planning to generate a curriculum for training RL Options.
Sunandita Patra, Mark Cavolowsky, Onur Kulaksizoglu, Ruoxi Li, Laura Hiatt, Mark Roberts, Dana Nau   +6 more
doaj   +1 more source

UAV Swarm Confrontation Using Hierarchical Multiagent Reinforcement Learning

International Journal of Aerospace Engineering, 2021
With the development of unmanned aerial vehicle (UAV) technology, UAV swarm confrontation has attracted many researchers’ attention. However, the situation faced by the UAV swarm has substantial uncertainty and dynamic variability.
Baolai Wang, Shengang Li, Xianzhong Gao, Tao Xie   +3 more
doaj   +1 more source