@article{intentionallyunderestimatedvaluefunction,
  title = {Intentionally-underestimated Value Function at Terminal State for Temporal-difference Learning with Mis-designed Reward},
  author = {Taisuke Kobayashi},
  year = {2023},
  eprint = {2308.12772},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2308.12772v1},
}