RDD distills a Gaussian-random target and rewards the squared deviation of the predictor from the target mean, giving an unbiased estimator of 1/n visits that unifies RND and pseudo-count exploration.
Count-based exploration with neural density models,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Exploration by Random Distribution Distillation
RDD distills a Gaussian-random target and rewards the squared deviation of the predictor from the target mean, giving an unbiased estimator of 1/n visits that unifies RND and pseudo-count exploration.