Yunhao Tang: "Reinforcement Learning for Integer Programming: Learning to Cut"

[@scj491]

Thank you for great presentation. Regarding c^T|x*_T - x*|, |x*_T-x*| is scalar obtained from norming inside vector and multipliying vector c^T results in another vector. To my understanding, the equation should be c^T(x*_T - x*), which means the change in objective value.

[@chengjing9029]

Nice explanation!!

[@farhanhyder6378]

Interesting approach and a good presentation