Sigmoid-weighted linear units for neural network function approximation in reinforcement learning

• Published in: Neural networks Vol. 107; pp. 3 - 11
• Main Authors: Elfwing, Stefan, Uchibe, Eiji, Doya, Kenji
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.11.2018
• Subjects: Atari 2600; Deep Learning; Function approximation; Neural Networks (Computer); Reinforcement learning; Sigmoid-weighted linear unit; Tetris; Deep learning; Atari 2600; Sigmoid-weighted linear unit; Function approximation; Tetris; Reinforcement learning

In recent years, neural networks have enjoyed a renaissance as function approximators in reinforcement learning. Two decades after Tesauro’s TD-Gammon achieved near top-level human performance in backgammon, the deep reinforcement learning algorithm DQN achieved human-level performance in many Atari...