Beyond deep reinforcement learning: A tutorial on generative diffusion models in network optimization

H Du, R Zhang, Y Liu, J Wang, Y Lin, Z Li… - arXiv preprint arXiv …, 2023 - arxiv.org
Generative Diffusion Models (GDMs) have emerged as a transformative force in the realm of
Generative Artificial Intelligence (GAI), demonstrating their versatility and efficacy across a …

Opportunities and challenges of diffusion models for generative AI

M Chen, S Mei, J Fan, M Wang - National Science Review, 2024 - academic.oup.com
Diffusion models, a powerful and universal generative AI technology, have achieved
tremendous success and opened up new possibilities in diverse applications. In these …

Noise contrastive alignment of language models with explicit rewards

H Chen, G He, L Yuan, G Cui, H Su, J Zhu - arXiv preprint arXiv …, 2024 - arxiv.org
User intentions are typically formalized as evaluation rewards to be maximized when fine-
tuning language models (LMs). Existing alignment methods, such as Direct Preference …

Simple hierarchical planning with diffusion

C Chen, F Deng, K Kawaguchi, C Gulcehre… - arXiv preprint arXiv …, 2024 - arxiv.org
Diffusion-based generative methods have proven effective in modeling trajectories with
offline datasets. However, they often face computational challenges and can falter in …

Consistency models as a rich and efficient policy class for reinforcement learning

Z Ding, C Jin - arXiv preprint arXiv:2309.16984, 2023 - arxiv.org
Score-based generative models like the diffusion model have been testified to be effective in
modeling multi-modal data from image generation to reinforcement learning (RL). However …

Safe offline reinforcement learning with feasibility-guided diffusion model

Y Zheng, J Li, D Yu, Y Yang, SE Li, X Zhan… - arXiv preprint arXiv …, 2024 - arxiv.org
Safe offline RL is a promising way to bypass risky online interactions towards safe policy
learning. Most existing methods only enforce soft constraints, ie, constraining safety …

Boosting continuous control with consistency policy

Y Chen, H Li, D Zhao - arXiv preprint arXiv:2310.06343, 2023 - arxiv.org
Due to its training stability and strong expression, the diffusion model has attracted
considerable attention in offline reinforcement learning. However, several challenges have …

Tfg: Unified training-free guidance for diffusion models

H Ye, H Lin, J Han, M Xu, S Liu, Y Liang, J Ma… - arXiv preprint arXiv …, 2024 - arxiv.org
Given an unconditional diffusion model and a predictor for a target property of interest (eg, a
classifier), the goal of training-free guidance is to generate samples with desirable target …

Score regularized policy optimization through diffusion behavior

H Chen, C Lu, Z Wang, H Su, J Zhu - arXiv preprint arXiv:2310.07297, 2023 - arxiv.org
Recent developments in offline reinforcement learning have uncovered the immense
potential of diffusion modeling, which excels at representing heterogeneous behavior …

Enhancing Deep Reinforcement Learning: A Tutorial on Generative Diffusion Models in Network Optimization

H Du, R Zhang, Y Liu, J Wang, Y Lin… - … Surveys & Tutorials, 2024 - ieeexplore.ieee.org
Generative Diffusion Models (GDMs) have emerged as a transformative force in the realm of
Generative Artificial Intelligence (GenAI), demonstrating their versatility and efficacy across …