Search Results for author:
Found 13 papers, 6 papers with code
Efficient Exploration for LLMs
We present evidence of substantial benefit from efficient exploration in gathering human feedback to improve large language models.
Approximate Thompson Sampling via Epistemic Neural Networks
Further, we demonstrate that the \textit{epinet} -- a small additive network that estimates uncertainty -- matches the performance of large ensembles at orders of magnitude lower computational cost.
Robustness of Epinets against Distributional Shifts
However, these improvements are relatively small compared to the outstanding issues in distributionally-robust deep learning.
Ensembles for Uncertainty Estimation: Benefits of Prior Functions and Bootstrapping
In machine learning, an agent needs to estimate uncertainty to efficiently explore and adapt and to make effective decisions.
Evaluating High-Order Predictive Distributions in Deep Learning
Previous work has developed methods for assessing low-order predictive distributions with inputs sampled i. i. d.
The Neural Testbed: Evaluating Joint Predictions
Predictive distributions quantify uncertainties ignored by point estimates.
Evaluating Predictive Distributions: Does Bayesian Deep Learning Work?
This paper introduces \textit{The Neural Testbed}, which provides tools for the systematic evaluation of agents that generate such predictions.
From Predictions to Decisions: The Importance of Joint Predictive Distributions
A fundamental challenge for any intelligent system is prediction: given some inputs, can you predict corresponding outcomes?
Epistemic Neural Networks
We introduce the epinet: an architecture that can supplement any conventional neural network, including large pretrained models, and can be trained with modest incremental computation to estimate uncertainty.
Reinforcement Learning, Bit by Bit
To illustrate concepts, we design simple agents that build on them and present computational results that highlight data efficiency.
Hypermodels for Exploration
This generalizes and extends the use of ensembles to approximate Thompson sampling.
Langevin DQN
Algorithms that tackle deep exploration -- an important challenge in reinforcement learning -- have relied on epistemic uncertainty representation through ensembles or other hypermodels, exploration bonuses, or visitation count distributions.
Motion-based Object Segmentation based on Dense RGB-D Scene Flow
Our model jointly estimates (i) the segmentation of the scene into an unknown but finite number of objects, (ii) the motion trajectories of these objects and (iii) the object scene flow.
