6 papers
Improving Weak World Models Behind Strong Agents in Atari Pong
Yukuan Lu, Zaishuo Xia, Weyl Lu +1
Strong world-model agents frequently contain weak world models. We study this agent-world-model gap by reproducing five visual world-model agents in Atari Pong: DreamerV3, DIAMOND,…
Deep Networks Favor Simple Data
Weyl Lu, Chenjie Hao, Yubei Chen
Estimated density is often interpreted as indicating how typical a sample is under a model. Yet deep models trained on one dataset can assign higher density to simpler out-of-distr…
When Models Know When They Do Not Know: Calibration, Cascading, and Cleaning
Chenjie Hao, Weyl Lu, Yuko Ishiwaka +3
When a model knows when it does not know, many possibilities emerge. The first question is how to enable a model to recognize that it does not know. A promising approach is to use…
SmallWorlds: Assessing Dynamics Understanding of World Models in Isolated Environments
Xinyi Li, Zaishuo Xia, Weyl Lu +2
Current world models lack a unified and controlled setting for systematic evaluation, making it difficult to assess whether they truly capture the underlying rules that govern envi…
Neural Motion Simulator: Pushing the Limit of World Models in Reinforcement Learning
Chenjie Hao, Weyl Lu, Yifan Xu +1
An embodied system must not only model the patterns of the external world but also understand its own motion dynamics. A motion dynamic model is essential for efficient skill acqui…
RA-PbRL: Provably Efficient Risk-Aware Preference-Based Reinforcement Learning
Yujie Zhao, Jose Efraim Aguilar Escamill, Weyl Lu +1
Reinforcement Learning from Human Feedback (RLHF) has recently surged in popularity, particularly for aligning large language models and other AI systems with human intentions. At…