← back to paper

Review history

arxiv: 2604.18530 · 2 revisions

OGER: A Robust Offline-Guided Exploration Reward for Hybrid Reinforcement Learning

1. 2026-07-05 CONDITIONAL UNKNOWN v1.1.0-glm novelty 4.0
   159007 ms 26675 in 2068 out 2026-07-05T11:26:31.899719+00:00
2. 2026-05-10 UNVERDICTED LOW v0.9.0 novelty 5.0
   42879 ms 5489 in 1361 out 2026-05-10T04:26:14.828634+00:00