1. Multi-agent actor-critic for mixed cooperative-competitive environments;lowe;Proc Neural Inf Process Syst,0
2. Qmix: Monotonic value function factorisation for deep multi-agent reinforcement learning;rashid;Proc Int Conf Mach Learn,0
3. Empirical evaluation of gated recurrent neural networks on sequence modeling;chung,0
4. Deep variational information bottleneck;alemi;Proc Int Conf Representation Learn,0
5. The information bottleneck method;tishby;Proc 37th Annu Allerton Conf Commun Control Comput (Allerton),0