3 papers
cs.LG2025
Experience-Efficient Model-Free Deep Reinforcement Learning Using Pre-Training
Ruoxing Yang
We introduce PPOPT - Proximal Policy Optimization using Pretraining, a novel, model-free deep-reinforcement-learning algorithm that leverages pretraining to achieve high training e…
cs.LG2025
DP-Adam-AC: Privacy-preserving Fine-Tuning of Localizable Language Models Using Adam Optimization with Adaptive Clipping
Ruoxing Yang
Large language models (LLMs) such as ChatGPT have evolved into powerful and ubiquitous tools. Fine-tuning on small datasets allows LLMs to acquire specialized skills for specific t…
cs.NI2024
An Algorithmic Approach to Line Construction in Existing Transit Networks
Zezhi Deng, Ruoxing Yang
Transit networks often have existing infrastructure that cannot be modified when designing new lines for the network. This paper provides an algorithm to generate a line within a t…