首页 > AI前沿 > Correcting Within-Group Self-Selection Bias in Prioritized Replay

Correcting Within-Group Self-Selection Bias in Prioritized Replay

arXiv机器学习 2026-09-22 02:41 4 阅读 查看原文

Prioritized experience replay (PER) improves sample efficiency by replaying high-priority transitions, usually according to absolute temporal-difference error.

In stochastic environments, PER can distort the distribution of realized outcomes replayed from transitions with the same state-action pair. We call this within-group self-selection.

We quantify the resulting changes in within-group outcome frequencies and mean Bellman targets.

We decompose PER into between-group allocation and conditional sibling selection, and derive fixed-buffer corrections that preserve current group-level priority mass:

  • SAMPLE selects a group through PER and trains on a uniformly sampled sibling;
  • AVG averages sibling Bellman targets;
  • MODEL samples from an empirical full-outcome model.

In exact state-action environments with rare high-magnitude outcomes, sibling-aware replay improves learning efficiency over PER, although matched parameter sweeps show that tuning can narrow some gaps.

In MinAtar, approximate VQ-VAE groups with SAMPLE mitigate degradation under mean-preserving reward tails in four of five games.

Sibling-aware replay thus retains the focus on high-priority state-action regions while recovering their empirical outcome frequencies.