Neural Algorithmic Reasoners are Implicit Planners

no code implementations • NeurIPS 2021 • Andreea Deac, Petar Veličković, Ognjen Milinković, Pierre-Luc Bacon, Jian Tang, Mladen Nikolić

We find that prior approaches either assume that the environment is provided in such a tabular form -- which is highly restrictive -- or infer "local neighbourhoods" of states to run value iteration over -- for which we discover an algorithmic bottleneck effect.

Self-Supervised Learning

XLVIN: eXecuted Latent Value Iteration Nets

no code implementations • 25 Oct 2020 • Andreea Deac, Petar Veličković, Ognjen Milinković, Pierre-Luc Bacon, Jian Tang, Mladen Nikolić

Value Iteration Networks (VINs) have emerged as a popular method to incorporate planning algorithms within deep reinforcement learning, enabling performance improvements on tasks requiring long-range reasoning and understanding of environment dynamics.

Graph Representation Learning Self-Supervised Learning