69 citations · 201 across the 15 of their papers we have counts for
Showing 2020Show all
2 papers · 1 filter
cs.LG2020★ 6 cited
XLVIN: eXecuted Latent Value Iteration Nets
Andreea Deac, Petar Veličković, Ognjen Milinković +3
Value Iteration Networks (VINs) have emerged as a popular method to incorporate planning algorithms within deep reinforcement learning, enabling performance improvements on tasks r…
cs.LG2020★ 6 cited
Graph neural induction of value iteration
Andreea Deac, Pierre-Luc Bacon, Jian Tang
Many reinforcement learning tasks can benefit from explicit planning based on an internal model of the environment. Previously, such planning components have been incorporated thro…