microsoft / FQF

FQF(Fully parameterized Quantile Function for distributional reinforcement learning) is a general reinforcement learning framework for Atari games, which can learn to play Atari games automatically by predicting return distribution in the form of a fully parameterized quantile function.
41Updated 4 years ago

Alternatives and similar repositories for FQF:

Users that are interested in FQF are comparing it to the libraries listed below