Concept-Guided Spatial Regularization for World Models in Atari Pong
World models are usually evaluated as components of model-based reinforcement learning (MBRL) systems, while the world models themselves are rarely studied in isolation. We examine five representative visual world-model agents in Atari Pong: DreamerV3, DIAMOND, TWISTER, Simulus, and STORM. After reproducing their training pipelines and matching the reported agent performance, we freeze the learned world models and evaluate them with a closed-loop rollout diagnostic: a policy trained separately from the corresponding MBRL agent interacts with each frozen model, and the generated video traject
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 48%Gradient-based Planning for World Models at Longer Horizons →
- LinkedLinked via arxiv author · 85%Yukuan Lu →
“Concept-Guided Spatial Regularization for World Models in Atari Pong”
- LinkedLinked via arxiv author · 85%Zaishuo Xia →
“Concept-Guided Spatial Regularization for World Models in Atari Pong”
- LinkedLinked via arxiv author · 85%Weyl Lu →
“Concept-Guided Spatial Regularization for World Models in Atari Pong”
- LinkedLinked via arxiv author · 85%Yubei Chen →
“Concept-Guided Spatial Regularization for World Models in Atari Pong”