Multi-objective decision-theoretic planning: abstract

Diederik M. Roijers

Abstract

Decision making is hard. It often requires reasoning about uncertain environments, partial observability and action spaces that are too large to enumerate. In such tasks decision-theoretic agents can often assist us. In most research on decision-theoretic agents, the desirability of actions and their effects is codified in a scalar reward function. However, many real-world decision problems have multiple objectives. In such cases the problem is more naturally expressed using a vector-valued reward function, leading to a multi-objective decision problem (MODP).
BibTeX
@article{roijers2016multi,
  author = {Diederik M. Roijers},
  title = {{Multi-objective decision-theoretic planning: abstract}},
  journal = {AI Matters},
  year = {2016},
  doi = {10.1145/3008665.3008670},
}

Loading related content...

Figure