On the Expressivity of Neural Networks for Deep Reinforcement LearningDownload PDFOpen Website

2020 (modified: 26 Mar 2022)ICML 2020Readers: Everyone
Abstract: We compare the model-free reinforcement learning with the model-based approaches through the lens of the expressive power of neural networks for policies, Q-functions, and dynamics. We show, theore...
0 Replies

Loading