Tag
This paper addresses objective mismatch in model-based RL by proposing offline diagnostics to predict closed-loop performance of latent world models. On LunarLander-v3, the Reward Observability Fraction (ROF) and a Composite score (CROF) enable selecting checkpoints that yield strong MPC and model-based RL policies with far fewer real-environment interactions.
This paper addresses the challenge of robust checkpoint selection for multimodal LLMs under evaluation uncertainty, proposing a multi-stage framework that integrates curated real-world data, LLM-based judgment, and ranking protocols with confidence estimation.
This paper reveals that during pre-training, language models frequently and suddenly switch between pattern-matching and generalization behaviors, a phenomenon called mode-hopping, and presents a toy evaluation suite to study it.