This paper introduces PettingZoo, a library of diverse sets of multi-age...
Partially Observable Stochastic Games (POSGs), are the most general mode...
The Arcade Learning Environment ("ALE") is a widely used library in the
...
In reinforcement learning, wrappers are universally used to transform th...
We introduce a new mathematical model of multi-agent reinforcement learn...
"Nonstationarity" is a fundamental problem in cooperative multi-agent
re...
The power of neural networks lies in their ability to generalize to unse...