← back to paper

Review history

arxiv: 2604.00860 · 2 revisions

Policy Improvement Reinforcement Learning

1. 2026-07-13 UNVERDICTED LOW v1.1.0-grok45 novelty 5.0
   24541 ms 6179 in 2786 out 2026-07-13T14:48:17.495469+00:00
2. 2026-05-13 UNVERDICTED LOW v0.9.0 novelty 6.0
   41569 ms 5564 in 1502 out 2026-05-13T22:44:54.577345+00:00