[KongchangAI]
ModelQuantile Regression DQN

QR-DQN

A distributional reinforcement learning algorithm that learns the return distribution through quantile regression. It belongs to the class of quantile methods.

Timeline (last 90 days)

Oct 22

QR-DQN, proposed by Dabney et al. in 2018, uses quantile regression to learn the quantiles of the return distribution, directly parameterizing the quantiles and avoiding projection error.

Unverified50%
Oct 22

The paper's quantile fixed-point estimator can be viewed as the theoretical counterpart of QR-DQN, and its rate analysis explains why QR-DQN performs well in practice.

Unverified50%

All Facts (2)

Source Articles