pytorch-nfspImplementation of Deep Reinforcement Learning from Self-Play in Imperfect-Information Games (Heinrich and Silver, 2016)
pymarl2Fine-tuned MARL algorithms on SMAC (100% win rates on most scenarios)
MavaA library of multi-agent reinforcement learning components and systems
CDS[NeurIPS 2021] CDS achieves remarkable success in challenging benchmarks SMAC and GRF by balancing sharing and diversity.
marltoolboxA toolbox with the goal of speeding up research on bargaining in MARL (cooperation problems in MARL).