Pith. sign in

← back to paper

Review history

arxiv: 2509.02737 · 2 revisions

Imitate Optimal Policy: Prevail and Induce Action Collapse in Policy Gradient

  1. 2026-08-15 REJECT MODERATE v1.4.0-alltime-deepseek-medium novelty 6.0
    129108 ms 15837 in 15393 out 2026-08-15T16:34:48.090236+00:00
  2. 2026-08-05 REJECT MODERATE v1.4.0-alltime-deepseek-medium novelty 4.0
    227505 ms 15904 in 19985 out 2026-08-05T11:28:43.910178+00:00