← back to paper

Review history

arxiv: 2607.01736 · 2 revisions

Predicting Closed-Loop Performance of Latent World Models: Offline Checkpoint Selection for MPC and Model-Based RL Under Non-Markovian Rewards in LunarLander

1. 2026-07-12 CONDITIONAL MODERATE v1.1.0-grok45 novelty 6.0
   28294 ms 18926 in 3633 out 2026-07-12T08:38:05.508164+00:00
2. 2026-07-03 UNVERDICTED LOW v0.9.1-grok novelty 5.0
   21240 ms 5781 in 1418 out 2026-07-03T17:41:46.799471+00:00