Learning to Self-Modify Rewards with Bi-Level Gradients

EasyChair Preprint no. 8260, version history

Version	Date	Pages	Version notes
1	June 12, 2022	10	—
2	January 21, 2023	10	Corrected meta data for indexing. Scholar was not reading abstract or text

Keyphrases: meta-learning, Reinforcement Learning, Reward Shaping

BibTeX entry

BibTeX does not have the right entry for preprints. This is a hack for producing the correct reference:

@Booklet{EasyChair:8260,
  author = {Aiden Boyd and Shibani and Will Callaghan},
  title = {Learning to Self-Modify Rewards with Bi-Level Gradients},
  howpublished = {EasyChair Preprint no. 8260},

  year = {EasyChair, 2023}}