410 citations · 441 across the 8 of their papers we have counts for
3 papers · 1 filter
Synthesizing Decentralized Controllers with Graph Neural Networks and Imitation Learning
Fernando Gama, Qingbiao Li, Ekaterina Tolstaya +2
Dynamical systems consisting of a set of autonomous agents face the challenge of having to accomplish a global task, relying only on local information. While centralized controller…
Graph Neural Networks for Decentralized Controllers
Fernando Gama, Ekaterina Tolstaya, Alejandro Ribeiro
Dynamical systems comprised of autonomous agents arise in many relevant problems such as multi-agent robotics, smart grids, or smart cities. Controlling these systems is of paramou…
Nonparametric Stochastic Compositional Gradient Descent for Q-Learning in Continuous Markov Decision Problems
Alec Koppel, Ekaterina Tolstaya, Ethan Stump +1
We consider Markov Decision Problems defined over continuous state and action spaces, where an autonomous agent seeks to learn a map from its states to actions so as to maximize it…