← back to paper

Review history

arxiv: 2607.04364 · 2 revisions

RL Forgets! Towards Continual Policy Optimization

1. 2026-07-14 CONDITIONAL HIGH v1.1.0-grok45 novelty 6.5
   49926 ms 35208 in 4051 out 2026-07-14T16:21:44.113897+00:00
2. 2026-07-11 CONDITIONAL HIGH v1.1.0-grok45 novelty 6.5
   40783 ms 35208 in 2845 out 2026-07-11T19:45:04.239445+00:00