Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
SOPE: Stabilizing Off-Policy Evaluation for Online RL with Prior Data
Carlo Romeo, Girolamo Macaluso, Alessandro Sestini +1
Incorporating prior data into online reinforcement learning accelerates training but typically forces a difficult trade-off between high computational costs and long, multi-stage t…
cs.LG2025
SPEQ: Offline Stabilization Phases for Efficient Q-Learning in High Update-To-Data Ratio Reinforcement Learning
Carlo Romeo, Girolamo Macaluso, Alessandro Sestini +1
High update-to-data (UTD) ratio algorithms in reinforcement learning (RL) improve sample efficiency but incur high computational costs, limiting real-world scalability. We propose…
cs.LG2023
Small Dataset, Big Gains: Enhancing Reinforcement Learning by Offline Pre-Training with Model Based Augmentation
Girolamo Macaluso, Alessandro Sestini, Andrew D. Bagdanov
Offline reinforcement learning leverages pre-collected datasets of transitions to train policies. It can serve as effective initialization for online algorithms, enhancing sample e…