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 …

Diffusion model is an effective planner and data synthesizer for multi-task reinforcement learning

H He, C Bai, K Xu, Z Yang, W Zhang… - Advances in neural …, 2023 - proceedings.neurips.cc
Diffusion models have demonstrated highly-expressive generative capabilities in vision and
NLP. Recent studies in reinforcement learning (RL) have shown that diffusion models are …

How to backdoor diffusion models?

SY Chou, PY Chen, TY Ho - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
Diffusion models are state-of-the-art deep learning empowered generative models that are
trained based on the principle of learning forward and reverse diffusion processes via …

Idql: Implicit q-learning as an actor-critic method with diffusion policies

P Hansen-Estruch, I Kostrikov, M Janner… - arXiv preprint arXiv …, 2023 - arxiv.org
Effective offline RL methods require properly handling out-of-distribution actions. Implicit Q-
learning (IQL) addresses this by training a Q-function using only dataset actions through a …

Contrastive energy prediction for exact energy-guided diffusion sampling in offline reinforcement learning

C Lu, H Chen, J Chen, H Su, C Li… - … on Machine Learning, 2023 - proceedings.mlr.press
Guided sampling is a vital approach for applying diffusion models in real-world tasks that
embeds human-defined guidance during the sampling procedure. This paper considers a …

Elastic decision transformer

YH Wu, X Wang, M Hamaya - Advances in Neural …, 2024 - proceedings.neurips.cc
Abstract This paper introduces Elastic Decision Transformer (EDT), a significant
advancement over the existing Decision Transformer (DT) and its variants. Although DT …

Generative ai for self-adaptive systems: State of the art and research roadmap

J Li, M Zhang, N Li, D Weyns, Z Jin, K Tei - ACM Transactions on …, 2024 - dl.acm.org
Self-adaptive systems (SASs) are designed to handle changes and uncertainties through a
feedback loop with four core functionalities: monitoring, analyzing, planning, and execution …

Diffusion models for reinforcement learning: A survey

Z Zhu, H Zhao, H He, Y Zhong, S Zhang, H Guo… - arXiv preprint arXiv …, 2023 - arxiv.org
Diffusion models surpass previous generative models in sample quality and training
stability. Recent works have shown the advantages of diffusion models in improving …

Supported policy optimization for offline reinforcement learning

J Wu, H Wu, Z Qiu, J Wang… - Advances in Neural …, 2022 - proceedings.neurips.cc
Policy constraint methods to offline reinforcement learning (RL) typically utilize
parameterization or regularization that constrains the policy to perform actions within the …

Villandiffusion: A unified backdoor attack framework for diffusion models

SY Chou, PY Chen, TY Ho - Advances in Neural …, 2024 - proceedings.neurips.cc
Abstract Diffusion Models (DMs) are state-of-the-art generative models that learn a
reversible corruption process from iterative noise addition and denoising. They are the …