@article{policycompositioninreinforcementlearning,
  title = {Policy composition in reinforcement learning via multi-objective policy optimization},
  author = {Shruti Mishra and Ankit Anand and Jordan Hoffmann and Nicolas Heess and Martin Riedmiller and Abbas Abdolmaleki and Doina Precup},
  year = {2023},
  eprint = {2308.15470},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2308.15470v2},
}