Research

Reward Observability and the Limits of Offline Checkpoint Selection in RSSM World Models

Single source1 source9 Oct 2026

arXiv:2607.01736v3 Announce Type: replace-cross Abstract: We study the closed-loop properties of a recurrent state-space model (RSSM) world model trained on human demonstrations in Gymnasium's LunarLander-v3.

Reported by 1 source

arxiv.orghttps://arxiv.org/abs/2607.01736

← Back to all developments · Signals are a development reported by more than one source. See the methodology.