Existing works mainly focus on arranging the levels to explicitly form a curriculum. In this work, we take a close look atthelearning process itself under themulti-leveltraining inProcgen.

Different from previous work, CaSPR learns representations thatsupport spacetime continuity,arerobusttovariable andirregularly spacetime-sampled point clouds, and generalize to unseen object instances. Our approach divides the problem into two subtasks.

Deep Neural Networks and Reinforcement Learning methods have empirically shown great promise in tackling challenging combinatorial problems.