Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Xu, Yinglun"'
Offline reinforcement learning has become one of the most practical RL settings. A recent success story has been RLHF, offline preference-based RL (PBRL) with preference from humans. However, most existing works on offline RL focus on the standard se
Externí odkaz:
http://arxiv.org/abs/2406.10445
We study the problem of reward poisoning attacks against general offline reinforcement learning with deep neural networks for function approximation. We consider a black-box threat model where the attacker is completely oblivious to the learning algo
Externí odkaz:
http://arxiv.org/abs/2402.09695
Autor:
Xu, Yinglun, Singh, Gagandeep
In this work, we consider the offline preference-based reinforcement learning problem. We focus on the two-phase learning approach that is prevalent in previous reinforcement learning from human preference works. We find a challenge in applying two-p
Externí odkaz:
http://arxiv.org/abs/2401.00330
Efficient learning in multi-armed bandit mechanisms such as pay-per-click (PPC) auctions typically involves three challenges: 1) inducing truthful bidding behavior (incentives), 2) using personalization in the users (context), and 3) circumventing ma
Externí odkaz:
http://arxiv.org/abs/2307.07675
Autor:
Xu, Yinglun, Singh, Gagandeep
We propose the first black-box targeted attack against online deep reinforcement learning through reward poisoning during training time. Our attack is applicable to general environments with unknown dynamics learned by unknown algorithms and requires
Externí odkaz:
http://arxiv.org/abs/2305.10681
We study reward poisoning attacks on online deep reinforcement learning (DRL), where the attacker is oblivious to the learning algorithm used by the agent and the dynamics of the environment. We demonstrate the intrinsic vulnerability of state-of-the
Externí odkaz:
http://arxiv.org/abs/2205.14842
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.