5 papers
Revisiting TD Target Aggregation under Uncertainty in Q-Learning
Lipeng Zu, Xiaonan Zhang
Deep Q-Networks (DQNs) learn value functions through bootstrapped temporal-difference updates, where future returns are approximated using a greedy maximization over next-state act…
From Static Constraints to Dynamic Adaptation: Sample-Level Constraint Relaxation for Offline-to-Online Reinforcement Learning
Lipeng Zu, Yu Qian, Shayok Chakraborty +1
Offline-to-online reinforcement learning (O2O RL) faces a central challenge between retaining offline conservatism and adapting to online feedback under distribution shift. This ch…
CORE: Compensable Reward as a Catalyst for Improving Offline RL in Wireless Networks
Lipeng Zu, Hansong Zhou, Yu Qian +4
Real-world wireless data are expensive to collect and often lack sufficient expert demonstrations, causing existing offline RL methods to overfit suboptimal behaviors and exhibit u…
Enhancing Q-Value Updates in Deep Q-Learning via Successor-State Prediction
Lipeng Zu, Hansong Zhou, Xiaonan Zhang
Deep Q-Networks (DQNs) estimate future returns by learning from transitions sampled from a replay buffer. However, the target updates in DQN often rely on next states generated by…
Behavior-Adaptive Q-Learning: A Unifying Framework for Offline-to-Online RL
Lipeng Zu, Hansong Zhou, Xiaonan Zhang
Offline reinforcement learning (RL) enables training from fixed data without online interaction, but policies learned offline often struggle when deployed in dynamic environments d…