78 citations · 174 across the 16 of their papers we have counts for
16 papers
RLHF and IIA: Perverse Incentives
Wanqiao Xu, Shi Dong, Xiuyuan Lu +3
Existing algorithms for reinforcement learning from human feedback (RLHF) can incentivize responses at odds with preferences because they are based on models that assume independen…
Approximate Thompson Sampling via Epistemic Neural Networks
Ian Osband, Zheng Wen, Seyed Mohammad Asghari +4
Thompson sampling (TS) is a popular heuristic for action selection, but it requires sampling from a posterior distribution. Unfortunately, this can become computationally intractab…
Robustness of Epinets against Distributional Shifts
Xiuyuan Lu, Ian Osband, Seyed Mohammad Asghari +4
Recent work introduced the epinet as a new approach to uncertainty modeling in deep learning. An epinet is a small neural network added to traditional neural networks, which, toget…
Ensembles for Uncertainty Estimation: Benefits of Prior Functions and Bootstrapping
Vikranth Dwaracherla, Zheng Wen, Ian Osband +3
In machine learning, an agent needs to estimate uncertainty to efficiently explore and adapt and to make effective decisions. A common approach to uncertainty estimation maintains…
An Analysis of Ensemble Sampling
Chao Qin, Zheng Wen, Xiuyuan Lu +1
Ensemble sampling serves as a practical approximation to Thompson sampling when maintaining an exact posterior distribution over model parameters is computationally intractable. In…
Evaluating High-Order Predictive Distributions in Deep Learning
Ian Osband, Zheng Wen, Seyed Mohammad Asghari +3
Most work on supervised learning research has focused on marginal predictions. In decision problems, joint predictive distributions are essential for good performance. Previous wor…
Event-based Motion Segmentation by Cascaded Two-Level Multi-Model Fitting
Xiuyuan Lu, Yi Zhou, Shaojie Shen
Among prerequisites for a synthetic agent to interact with dynamic scenes, the ability to identify independently moving objects is specifically important. From an application persp…
The Neural Testbed: Evaluating Joint Predictions
Ian Osband, Zheng Wen, Seyed Mohammad Asghari +7
Predictive distributions quantify uncertainties ignored by point estimates. This paper introduces The Neural Testbed: an open-source benchmark for controlled and principled evaluat…
From Predictions to Decisions: The Importance of Joint Predictive Distributions
Zheng Wen, Ian Osband, Chao Qin +5
A fundamental challenge for any intelligent system is prediction: given some inputs, can you predict corresponding outcomes? Most work on supervised learning has focused on produci…
Epistemic Neural Networks
Ian Osband, Zheng Wen, Seyed Mohammad Asghari +4
Intelligence relies on an agent's knowledge of what it does not know. This capability can be assessed based on the quality of joint predictions of labels across multiple inputs. In…
GVINS: Tightly Coupled GNSS-Visual-Inertial Fusion for Smooth and Consistent State Estimation
Shaozu Cao, Xiuyuan Lu, Shaojie Shen
Visual-Inertial odometry (VIO) is known to suffer from drifting especially over long-term runs. In this paper, we present GVINS, a non-linear optimization based system that tightly…
Reinforcement Learning, Bit by Bit
Xiuyuan Lu, Benjamin Van Roy, Vikranth Dwaracherla +3
Reinforcement learning agents have demonstrated remarkable achievements in simulated environments. Data efficiency poses an impediment to carrying this success over to real environ…
Event-based Motion Segmentation with Spatio-Temporal Graph Cuts
Yi Zhou, Guillermo Gallego, Xiuyuan Lu +2
Identifying independently moving objects is an essential task for dynamic scene understanding. However, traditional cameras used in dynamic scenes may suffer from motion blur or ex…
Hypermodels for Exploration
Vikranth Dwaracherla, Xiuyuan Lu, Morteza Ibrahimi +3
We study the use of hypermodels to represent epistemic uncertainty and guide exploration. This generalizes and extends the use of ensembles to approximate Thompson sampling. The co…
Information-Theoretic Confidence Bounds for Reinforcement Learning
Xiuyuan Lu, Benjamin Van Roy
We integrate information-theoretic concepts into the design and analysis of optimistic algorithms and Thompson sampling. By making a connection between information-theoretic quanti…
Ensemble Sampling
Xiuyuan Lu, Benjamin Van Roy
Thompson sampling has emerged as an effective heuristic for a broad range of online decision problems. In its basic form, the algorithm requires computing and sampling from a poste…