Dynamic Spectrum Access for Ambient Backscatter Communication-assisted D2D Systems with Quantum Reinforcement Learning

no code implementations • 23 Oct 2024 • Nguyen Van Huynh, Bolun Zhang, Dinh-Hieu Tran, Dinh Thai Hoang, Diep N. Nguyen, Gan Zheng, Dusit Niyato, Quoc-Viet Pham

For that, we develop a novel quantum reinforcement learning (RL) algorithm that can achieve a faster convergence rate with fewer training parameters compared to DRL thanks to the quantum superposition and quantum entanglement principles.

Deep Reinforcement Learning Reinforcement Learning (RL)

Self-Alignment of Large Language Models via Monopolylogue-based Social Scene Simulation

no code implementations • 8 Feb 2024 • Xianghe Pang, Shuo Tang, Rui Ye, Yuxin Xiong, Bolun Zhang, Yanfeng Wang, Siheng Chen

Drawing from the sociological insight that acknowledging all parties' concerns is a key factor in shaping human values, this paper proposes a novel direction to align LLMs by themselves: social scene simulation.

Deep Deterministic Policy Gradient for End-to-End Communication Systems without Prior Channel Knowledge

no code implementations • 12 May 2023 • Bolun Zhang, Nguyen Van Huynh

Unfortunately, this E2E learning architecture requires a prior differentiable channel model to jointly train the deep neural networks (DNNs) at the transceivers, which is hardly obtained in practice.