Blar i NTNU Open på forfatter "Clemente, Alfredo Vicente"

Viser treff 1-1 av 1

Decoupling deep learning and reinforcement learning for stable and efficient deep policy gradient algorithms

Clemente, Alfredo Vicente (Master thesis, 2017)

This thesis explores the exciting new field of deep reinforcement learning (Deep RL). This field combines well known reinforcement learning algorithms with newly developed deep learning algorithms. With Deep RL it is ...