4 papers
The Hidden Power of Scaling Factor in LoRA Optimization
Zicheng Zhang, Haoran Li, Jiaxing Wang +10
In Low-Rank Adaptation (LoRA), the scaling factor is often treated as a mere complement to the learning rate, yet its role in optimization remains poorly understood. In this p…
Towards Optimal Adversarial Robust Reinforcement Learning with Infinity Measurement Error
Haoran Li, Zicheng Zhang, Wang Luo +4
Ensuring the robustness of deep reinforcement learning (DRL) agents against adversarial attacks is critical for their trustworthy deployment. Recent research highlights the challen…
Preference-based opponent shaping in differentiable games
Xinyu Qiao, Yudong Hu, Congying Han +2
Strategy learning in game environments with multi-agent is a challenging problem. Since each agent's reward is determined by the joint strategy, a greedy learning strategy that aim…
Towards Optimal Adversarial Robust Q-learning with Bellman Infinity-error
Haoran Li, Zicheng Zhang, Wang Luo +4
Establishing robust policies is essential to counter attacks or disturbances affecting deep reinforcement learning (DRL) agents. Recent studies explore state-adversarial robustness…