====== 2018-06 [MPO] Maximum a Posteriori Policy Optimisation ====== * https://arxiv.org/abs/1806.06920 * https://paperswithcode.com/paper/maximum-a-posteriori-policy-optimisation * https://github.com/theogruner/rl_pro_telu {{tag>MPO DeepMind "Abbas Abdolmaleki" "Martin Riedmiller" 2018}}