RQIQN introduces a Wasserstein DRO-based correction to Bellman quantile targets that enlarges distributional spread without altering risk-neutral averages.
Atari-5: Distilling the arcade learning environment down to five games
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1roles
dataset 1polarities
use dataset 1representative citing papers
citing papers explorer
-
Quantile Geometry Regularization for Distributional Reinforcement Learning
RQIQN introduces a Wasserstein DRO-based correction to Bellman quantile targets that enlarges distributional spread without altering risk-neutral averages.