Follow
EMaQ: Expected-Max Q-Learning Operator for Simple Yet Effective Offline and Online RL. (arXiv:2007.11091v1 [cs.LG]) http://arxiv.org/abs/2007.11091
EMaQ: Expected-Max Q-Learning Operator for Simple Yet Effective Offline and Online RL. (arXiv:2007.11091v1 [cs.LG]) http://arxiv.org/abs/2007.11091