6 citations · 18 across the 10 of their papers we have counts for
Showing 2022Show all
2 papers · 1 filter
cs.RO2022★ 3 cited
VMAS: A Vectorized Multi-Agent Simulator for Collective Robot Learning
Matteo Bettini, Ryan Kortvelesy, Jan Blumenkamp +1
While many multi-robot coordination problems can be solved optimally by exact algorithms, solutions are often not scalable in the number of robots. Multi-Agent Reinforcement Learni…
cs.LG2022★ 4 cited
QGNN: Value Function Factorisation with Graph Neural Networks
Ryan Kortvelesy, Amanda Prorok
In multi-agent reinforcement learning, the use of a global objective is a powerful tool for incentivising cooperation. Unfortunately, it is not sample-efficient to train individual…