Loaded DiCE: Trading off Bias and Variance in Any-Order Score Function Estimators for Reinforcement Learning

Farquhar G, Whiteson S, Foerster J
23 September 2019
preprint
Book Title:
arXiv
No abstract available
Keywords:

46 Information and Computing Sciences

,

4602 Artificial Intelligence

,

4611 Machine Learning

DOI
10.48550/arxiv.1909.10549