Kernel-nased just-in-time learning for passing expectation propagation messages by Jitkrittum, W, Gretton, A, Heess, N, Eslami, S, Lakshminarayanan, B, Sejdinovic, D, Szabó, Z

Distral: robust multitask reinforcement learning by Teh, YW, Bapst, V, Czarnecki, WM, Quan, J, Kirkpatrick, J, Hadsell, R, Heess, N, Pascanu, R

Filtering variational objectives by Maddison, C, Lawson, D, Tucker, G, Heess, N, Norouzi, M, Mnih, A, Doucet, A, Teh, Y

Neural probabilistic motor primitives for humanoid control by Merel, J, Hasenclever, L, Galashov, A, Ahuja, A, Pham, V, Wayne, G, Teh, Y, Heess, N

Information asymmetry in KL-regularized RL by Galashov, A, Jayakumar, SM, Hasenclever, L, Tirumala, D, Schwarz, J, Desjardins, G, Czarnecki, WM, Teh, YW, Pascanu, R, Heess, N