Meta-DT: Offline Meta-RL as Conditional Sequence Modeling with World Model Disentanglement

Z Wang, L Zhang, W Wu, Y Zhu… - Advances in Neural …, 2025‏ - proceedings.neurips.cc
A longstanding goal of artificial general intelligence is highly capable generalists that can
learn from diverse experiences and generalize to unseen tasks. The language and vision …

Entropy Regularized Task Representation Learning for Offline Meta-Reinforcement Learning

A Scannell, J Pajarinen - ar** the Unseen Gaps in High Dimensional Data
X Zhang, T Estro, G Kuenning, E Zadok… - arxiv preprint arxiv …, 2025‏ - arxiv.org
We present a comprehensive pipeline, augmented by a visual analytics system
named``GapMiner'', that is aimed at exploring and exploiting untapped opportunities within …

Offline Critic-Guided Diffusion Policy for Multi-User Delay-Constrained Scheduling

Z Li, R Chen, H Zhong, L Huang - arxiv preprint arxiv:2501.12942, 2025‏ - arxiv.org
Effective multi-user delay-constrained scheduling is crucial in various real-world
applications, such as instant messaging, live streaming, and data center management. In …

Disentangled Task Representation Learning for Offline Meta Reinforcement Learning

S Cong, C Yu, Y Wang, D Jiang… - 2024 IEEE International …, 2024‏ - ieeexplore.ieee.org
In this paper, we aim to address the generalization problem in Offline Meta-Reinforcement
Learning (OMRL) when both task objectives and environmental parameters vary …