Graph networks as learnable physics engines for inference and control
Álvaro Sánchez‐González(Imperial College London), Peter Battaglia(Google DeepMind (United Kingdom)), Jost Tobias Springenberg(University of Freiburg), Raia Hadsell(Google DeepMind (United Kingdom)), Josh Merel, Nicolas Heess(Google DeepMind (United Kingdom)), Martin Riedmiller(Google (United States))
Cited by 280
Related Papers
Human-level control through deep reinforcement learning
|Nature|2015|29.9k
Playing Atari with Deep Reinforcement Learning
|arXiv (Cornell University)|2013|5.1k
A direct adaptive method for faster backpropagation learning: the RPROP algorithm
|IEEE International Conference on Neural Networks|2002|3.9k
Striving for Simplicity: The All Convolutional Net
|arXiv (Cornell University)|2014|2.6k
Deterministic policy gradient algorithms
|HAL (Le Centre pour la Communication Scientifique Directe)|2014|1.7k