Geometric deep learning enables the encoding of physical symmetries in modeling 3D objects.

Theproposed algorithm first formulates a multi-task learning problem as a multiobjective optimization problem, and then decomposes the multiobjective optimization problem into a set of constrained subproblems with different trade-off preferences.

To address this, some works have proposed piecewise linear scalar-izations inspired by economics [Busa-Fekete et al., 2017], while for multi-armed bandits, scalarized

While some workshowsthatmulti-task networkstrained viaunitary scalarization exhibit superior performance to independent per-task models [29, 35], others suggest the opposite [30, 54, 58]. However, SMTOs usually require access to per-task gradients either with respect to the shared parameters, or to the shared representation.

However, there are still quite a few challenges between the traditional RL research and real-worldtasks.