@online{huangnddistributional,
  author       = {Huang, Xuanqiang Angelo},
  title        = {Distributional Reinforcement Learning},
  organization = {Xuanqiang Angelo Huang's Blog},
  url          = {https://flecart.github.io/notes/distributional-reinforcement-learning/},
  langid       = {english},
  abstract     = {Distributional Reinforcement Learning \# Motivation: Why Bother With the Whole Distribution? \# Standard value-based RL collapses the random return into a single scalar via expectation: Q ( s , a ) = E [ Z ( s , a )] . The distributional perspective (Bellemare, Dabney, Munos, 2017)}
}