Výsledky vyhledávání

The robustness of neural networks is paramount in safety-critical applications. While most current robustness verification methods assess the worst-case output under the assumption that the input space is known, identifying a verifiable input space $

Externí odkaz: http://arxiv.org/abs/2408.08824

Zobrazit plný text záznamu

Report

CAT: Caution Aware Transfer in Reinforcement Learning via Distributional Risk

Autor: Chehade, Mohamad Fares El Hajj, Bedi, Amrit Singh, Zhang, Amy, Zhu, Hao

Transfer learning in reinforcement learning (RL) has become a pivotal strategy for improving data efficiency in new, unseen tasks by utilizing knowledge from previously learned tasks. This approach is especially beneficial in real-world deployment sc

Externí odkaz: http://arxiv.org/abs/2408.08812

Zobrazit plný text záznamu

Report

Should we use model-free or model-based control? A case study of battery management systems

Autor: Chehade, Mohamad Fares El Hajj, Cho, Young-ho, Chinchali, Sandeep, Zhu, Hao

Reinforcement learning (RL) and model predictive control (MPC) each offer distinct advantages and limitations when applied to control problems in power and energy systems. Despite various studies on these methods, benchmarks remain lacking and the pr

Externí odkaz: http://arxiv.org/abs/2407.15313

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání