pith. sign in

← back to paper

Review history

arxiv: 2605.06474 · 2 revisions

Q-MMR: Off-Policy Evaluation via Recursive Reweighting and Moment Matching

  1. 2026-05-11 UNVERDICTED LOW v0.9.0 novelty 6.0
    37401 ms 5441 in 1234 out 2026-05-11T01:53:53.793649+00:00
  2. 2026-05-08 UNVERDICTED LOW v0.9.0 novelty 6.0
    51549 ms 5441 in 1346 out 2026-05-08T12:30:35.764855+00:00