Disentangling Policy from Offline Task Representation Learning via Adversarial Data Augmentation

[Free GPT-4]
[DeepSeek]
[PDF] arxiv.org

Energy-guided diffusion sampling for offline-to-online reinforcement learning

XH Liu, TS Liu, S Jiang, R Chen, Z Zhang… - ar** policies that can adjust to non-stationary environments is essential for real-world
reinforcement learning applications. However, learning such adaptable policies in offline …
Guardar Citar Citado por 1 Artículos relacionados Las 3 versiones Versión en HTML

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 …
Guardar Citar Artículos relacionados Las 2 versiones