Simple statistical gradient-following algorithms for connectionist reinforcement learning

Ronald J. Williams

Năm xuất bản1992

Nguồn học thuậtMachine Learning

Định danhDOI 10.1007/bf00992696

TRÍCH DẪN ĐỀ XUẤT

Ronald J. Williams (1992). Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine Learning, 8(3-4), 229-256. https://doi.org/10.1007/bf00992696

Thông tin thư mục

Nguồn/Tạp chí: Machine Learning
Tập: 8
Số: 3-4
Trang: 229-256
Nhà xuất bản: Springer Science+Business Media
DOI: 10.1007/bf00992696 ↗

Từ khóa

Reinforcement learning; Connectionism; Computer science; Simple (philosophy); Reinforcement; Associative property; Artificial intelligence; Algorithm; Artificial neural network; Backpropagation; Limiting; Class (philosophy); Machine learning; Mathematics