Understanding multi-step deep reinforcement learning: A systematic study of the DQN target
JF Hernandez-Garcia, RS Sutton - arXiv preprint arXiv:1901.07510, 2019 - arxiv.org
Multi-step methods such as Retrace ($\lambda $) and $ n $-step $ Q $-learning have
become a crucial component of modern deep reinforcement learning agents. These …
become a crucial component of modern deep reinforcement learning agents. These …
Understanding Multi-Step Deep Reinforcement Learning: A Systematic Study of the DQN Target
JF Hernandez-Garcia, RS Sutton - arXiv e-prints, 2019 - ui.adsabs.harvard.edu
Multi-step methods such as Retrace ($\lambda $) and $ n $-step $ Q $-learning have
become a crucial component of modern deep reinforcement learning agents. These …
become a crucial component of modern deep reinforcement learning agents. These …
[PDF][PDF] Understanding Multi-Step Deep Reinforcement Learning: A Systematic Study of the DQN Target
JF Hernandez-Garcia, RS Sutton - incompleteideas.net
Multi-step methods such as Retrace (λ) and n-step Q-learning have become a crucial
component of modern deep reinforcement learning agents. These methods are often …
component of modern deep reinforcement learning agents. These methods are often …
[PDF][PDF] Understanding Multi-Step Deep Reinforcement Learning: A Systematic Study of the DQN Target
JF Hernandez-Garcia, RS Sutton - incompleteideas.net
Multi-step methods such as Retrace (λ) and n-step Q-learning have become a crucial
component of modern deep reinforcement learning agents. These methods are often …
component of modern deep reinforcement learning agents. These methods are often …