Výsledky vyhledávání - "Huang, Weidong"

Report

Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark

Autor: Ji, Jiaming, Zhang, Borong, Zhou, Jiayi, Pan, Xuehai, Huang, Weidong, Sun, Ruiyang, Geng, Yiran, Zhong, Yifan, Dai, Juntao, Yang, Yaodong

Artificial intelligence (AI) systems possess significant potential to drive societal progress. However, their deployment often faces obstacles due to substantial safety concerns. Safe reinforcement learning (SafeRL) emerges as a solution to optimize

Externí odkaz: http://arxiv.org/abs/2310.12567

Zobrazit plný text záznamu

Report

SafeDreamer: Safe Reinforcement Learning with World Models

Autor: Huang, Weidong, Ji, Jiaming, Xia, Chunhe, Zhang, Borong, Yang, Yaodong

The deployment of Reinforcement Learning (RL) in real-world applications is constrained by its failure to satisfy safety criteria. Existing Safe Reinforcement Learning (SafeRL) methods, which rely on cost functions to enforce safety, often fail to ac

Externí odkaz: http://arxiv.org/abs/2307.07176

Zobrazit plný text záznamu

Report

OmniSafe: An Infrastructure for Accelerating Safe Reinforcement Learning Research

Autor: Ji, Jiaming, Zhou, Jiayi, Zhang, Borong, Dai, Juntao, Pan, Xuehai, Sun, Ruiyang, Huang, Weidong, Geng, Yiran, Liu, Mickel, Yang, Yaodong

AI systems empowered by reinforcement learning (RL) algorithms harbor the immense potential to catalyze societal advancement, yet their deployment is often impeded by significant safety concerns. Particularly in safety-critical applications, research

Externí odkaz: http://arxiv.org/abs/2305.09304

Zobrazit plný text záznamu