2 citations · 3 across the 9 of their papers we have counts for
9 papers
Learning a Pessimistic Reward Model in RLHF
Yinglun Xu, Hangoo Kang, Tarun Suresh +2
This work proposes `PET', a novel pessimistic reward fine-tuning method, to learn a pessimistic reward model robust against reward hacking in offline reinforcement learning from hu…
SuperCoder: Assembly Program Superoptimization with Large Language Models
Anjiang Wei, Tarun Suresh, Huanmi Tan +4
Superoptimization is the task of transforming a program into a faster one, and ideally the very fastest possible one, while preserving its input-output behavior. In this work, we i…
Robust Thompson Sampling Algorithms Against Reward Poisoning Attacks
Yinglun Xu, Zhiwei Wang, Gagandeep Singh
Thompson sampling is one of the most popular learning algorithms for online sequential decision-making problems and has rich real-world applications. However, current Thompson samp…
Binary Reward Labeling: Bridging Offline Preference and Reward-Based Reinforcement Learning
Yinglun Xu, David Zhu, Rohan Gumaste +1
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 feedbac…
Universal Black-Box Reward Poisoning Attack against Offline Reinforcement Learning
Yinglun Xu, Rohan Gumaste, Gagandeep Singh
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 mode…
Two-Step Offline Preference-Based Reinforcement Learning with Constrained Actions
Yinglun Xu, Tarun Suresh, Rohan Gumaste +10
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 app…
On the Robustness of Epoch-Greedy in Multi-Agent Contextual Bandit Mechanisms
Yinglun Xu, Bhuvesh Kumar, Jacob Abernethy
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)…
Black-Box Targeted Reward Poisoning Attack Against Online Deep Reinforcement Learning
Yinglun Xu, Gagandeep Singh
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 environ…
Efficient Reward Poisoning Attacks on Online Deep Reinforcement Learning
Yinglun Xu, Qi Zeng, Gagandeep Singh
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 e…