Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Gumaste, Rohan"'
Large Language Models (LLMs) are widely used for tasks such as natural language and code generation. Still, their outputs often suffer from issues like privacy violations, and semantically inaccurate code generation. Current libraries for LLM generat
Externí odkaz:
http://arxiv.org/abs/2410.07295
Offline reinforcement learning has become one of the most practical RL settings. However, most existing works on offline RL focus on the standard setting with scalar reward feedback. It remains unknown how to universally transfer the existing rich un
Externí odkaz:
http://arxiv.org/abs/2406.10445
We study the problem of universal black-boxed reward poisoning attacks against general offline reinforcement learning with deep neural networks. We consider a black-box threat model where the attacker is entirely oblivious to the learning algorithm,
Externí odkaz:
http://arxiv.org/abs/2402.09695
Autor:
Xu, Yinglun, Suresh, Tarun, Gumaste, Rohan, Zhu, David, Li, Ruirui, Wang, Zhengyang, Jiang, Haoming, Tang, Xianfeng, Yin, Qingyu, Cheng, Monica Xiao, Zeng, Qi, Zhang, Chao, Singh, Gagandeep
Preference-based reinforcement learning (PBRL) in the offline setting has succeeded greatly in industrial applications such as chatbots. A two-step learning framework where one applies a reinforcement learning step after a reward modeling step has be
Externí odkaz:
http://arxiv.org/abs/2401.00330