Multi-Objective Policy Gradients with Topological Constraints

Kyle Hollins Wray,Stas Tiomkin,Mykel J. Kochenderfer,Pieter Abbeel,Kyle Hollins Wray,Stas Tiomkin,Mykel J. Kochenderfer,Pieter Abbeel

Multi-objective optimization models that encode ordered sequential constraints provide a solution to model various challenging problems including encoding preferences, modeling a curriculum, and enforcing measures of safety. A recently developed theory of topological Markov decision processes (TMDPs) captures this range of problems for the case of discrete states and actions. In this work, we exte...