← back to paper

Review history

arxiv: 2509.10423 · 2 revisions

Mutual Information Tracks Policy Coherence in Reinforcement Learning

1. 2026-08-15 REJECT MODERATE v1.4.0-alltime-deepseek-medium novelty 4.0
   120378 ms 11932 in 15860 out 2026-08-15T15:54:37.559646+00:00
2. 2026-08-04 REJECT MODERATE v1.3.0-alltime-deepseek novelty 4.0
   135738 ms 11901 in 14192 out 2026-08-04T17:50:09.079949+00:00