cs.AI, cs.LG, cs.RO, cs.SY, eess.SY, math.OC

Adaptive Smooth Tchebycheff Attention for Multi-Objective Policy Optimization

arXiv:2605.12771v1 Announce Type: new
Abstract: Multi-objective reinforcement learning in robotic domains requires balancing complex, non-convex trade-offs between conflicting objectives. While linear scalarization methods provide stability, they are …