Leveraging Separated World Model for Exploration in Visually Distracted Environments

K Huang, S Wan, M Shao, HH Sun… - Advances in …, 2025‏ - proceedings.neurips.cc
Abstract Model-based unsupervised reinforcement learning (URL) has gained prominence
for reducing environment interactions and learning general skills using intrinsic rewards …

TWIST: Teacher-Student World Model Distillation for Efficient Sim-to-Real Transfer

J Yamada, M Rigter, J Collins… - 2024 IEEE International …, 2024‏ - ieeexplore.ieee.org
Model-based RL is a promising approach for real-world robotics due to its improved sample
efficiency and generalization capabilities compared to model-free RL. However, effective …

Learning Curricula in Open-Ended Worlds

M Jiang - arxiv preprint arxiv:2312.03126, 2023‏ - arxiv.org
Deep reinforcement learning (RL) provides powerful methods for training optimal sequential
decision-making agents. As collecting real-world interactions can entail additional costs and …

Multi-Agent Reinforcement Learning in Wireless Distributed Networks for 6G

J Zhang, Z Liu, Y Zhu, E Shi, B Xu, C Yuen… - arxiv preprint arxiv …, 2025‏ - arxiv.org
The introduction of intelligent interconnectivity between the physical and human worlds has
attracted great attention for future sixth-generation (6G) networks, emphasizing massive …

PrivilegedDreamer: Explicit Imagination of Privileged Information for Rapid Adaptation of Learned Policies

M Byrd, J Crandell, M Das, J Inman, R Wright… - arxiv preprint arxiv …, 2025‏ - arxiv.org
Numerous real-world control problems involve dynamics and objectives affected by
unobservable hidden pa-rameters, ranging from autonomous driving to robotic manipu …

Reinforcing automated machine learning-bridging AutoML and reinforcement learning

T Eimer - 2024‏ - repo.uni-hannover.de
Reinforcement learning is a machine learning paradigm that allows learning through
interaction. It intertwines data collection and model training into a single problem statement …

Investigating Online RL in World Models

U Berdica, K Li, M Beukman, AD Goldie, M Fellows‏ - openreview.net
Significant advances in online reinforcement learning (RL) remain limited by the need for
extensive environment interaction or accurate simulators. World models trained on large …