Exploring the limits of hierarchical world models in reinforcement learning

R Schiewer, A Subramoney, L Wiskott - Scientific Reports, 2024 - nature.com
Hierarchical model-based reinforcement learning (HMBRL) aims to combine the sample
efficiency of model-based reinforcement learning with the abstraction capability of …

Learn A Flexible Exploration Model for Parameterized Action Markov Decision Processes

Z Wang, B Wang, M Shao, H Dou, B Tao - arxiv preprint arxiv:2501.02774, 2025 - arxiv.org
Hybrid action models are widely considered an effective approach to reinforcement learning
(RL) modeling. The current mainstream method is to train agents under Parameterized …

Generate explorative goals with large language model guidance

X Yuan, YAN ZHENG, F Zhang, D ZHANG, H Mao… - openreview.net
Reinforcement learning (RL) struggles with sparse reward environments. Recent
developments in intrinsic motivation have revealed the potential of language models to …

Nonmyopic Bayesian Optimization in Dynamic Cost Settings

ST Truong, DQ Nguyen, W Neiswanger, RR Griffiths… - openreview.net
Bayesian optimization (BO) is a popular framework for optimizing black-box functions,
leveraging probabilistic models such as Gaussian processes. However, conventional BO …

Navigation with QPHIL: Offline Goal-Conditioned RL in a Learned Discretized Space

A Canesse, M Petitbois, L Denoyer, R Portelas - openreview.net
Offline Reinforcement Learning (RL) has emerged as a powerful alternative to imitation
learning for behavior modeling in various domains, particularly in complex navigation tasks …

World-Model based Hierarchical Planning with Semantic Communications for Autonomous Driving

D Gao, H Wang, S Cai, H Zhou, N Ammar, S Mishra… - openreview.net
World-model (WM) is a highly promising approach for training AI agents. However, in
complex learning systems such as autonomous driving, AI agents interact with others in a …