297 citations · 859 across the 24 of their papers we have counts for
25 papers
The Bias is in the Details: An Assessment of Cognitive Bias in LLMs
R. Alexander Knipper, Charles S. Knipper, Kaiqi Zhang +3
As Large Language Models (LLMs) are increasingly embedded in real-world decision-making processes, it becomes crucial to examine the extent to which they exhibit cognitive biases.…
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
Gemini Team, Petko Georgiev, Ving Ian Lei +1132
In this report, we introduce the Gemini 1.5 family of models, representing the next generation of highly compute-efficient multimodal models capable of recalling and reasoning over…
Reinforced Self-Training (ReST) for Language Modeling
Caglar Gulcehre, Tom Le Paine, Srivatsan Srinivasan +11
Reinforcement learning from human feedback (RLHF) can improve the quality of large language model's (LLM) outputs by aligning them with human preferences. We propose a simple algor…
AlphaStar Unplugged: Large-Scale Offline Reinforcement Learning
Michaël Mathieu, Sherjil Ozair, Srivatsan Srinivasan +21
StarCraft II is one of the most challenging simulated reinforcement learning environments; it is partially observable, stochastic, multi-agent, and mastering StarCraft II requires…
: Policy Representations with Successor Features
Gianluca Scarpellini, Ksenia Konyushkova, Claudio Fantacci +3
This paper describes , a method for representing behaviors of black box policies as feature vectors. The policy representations capture how the statistics of founda…
Active Offline Policy Selection
Ksenia Konyushkova, Yutian Chen, Tom Le Paine +5
This paper addresses the problem of policy selection in domains with abundant logged data, but with a restricted interaction budget. Solving this problem would enable safe evaluati…
On Instrumental Variable Regression for Deep Offline Policy Evaluation
Yutian Chen, Liyuan Xu, Caglar Gulcehre +4
We show that the popular reinforcement learning (RL) strategy of estimating the state-action value (Q-function) by minimizing the mean squared Bellman error leads to a regression p…
Autoregressive Dynamics Models for Offline Policy Evaluation and Optimization
Michael R. Zhang, Tom Le Paine, Ofir Nachum +4
Standard dynamics models for continuous control make use of feedforward computation to predict the conditional distribution of next state and reward given current state and action…
Benchmarks for Deep Off-Policy Evaluation
Justin Fu, Mohammad Norouzi, Ofir Nachum +10
Off-policy evaluation (OPE) holds the promise of being able to leverage large, offline datasets for both evaluating and selecting complex policies for decision making. The ability…
Regularized Behavior Value Estimation
Caglar Gulcehre, Sergio Gómez Colmenarejo, Ziyu Wang +7
Offline reinforcement learning restricts the learning process to rely only on logged-data without access to an environment. While this enables real-world applications, it also pose…
Hyperparameter Selection for Offline Reinforcement Learning
Tom Le Paine, Cosmin Paduraru, Andrea Michi +5
Offline reinforcement learning (RL purely from logged data) is an important avenue for deploying RL techniques in real-world scenarios. However, existing hyperparameter selection m…
RL Unplugged: A Suite of Benchmarks for Offline Reinforcement Learning
Caglar Gulcehre, Ziyu Wang, Alexander Novikov +15
Offline methods for reinforcement learning have a potential to help bridge the gap between reinforcement learning research and real-world applications. They make it possible to lea…
Improving the Gating Mechanism of Recurrent Neural Networks
Albert Gu, Caglar Gulcehre, Tom Le Paine +2
Gating mechanisms are widely used in neural network models, where they allow gradients to backpropagate more easily through depth or time. However, their saturation property introd…
Making Efficient Use of Demonstrations to Solve Hard Exploration Problems
Tom Le Paine, Caglar Gulcehre, Bobak Shahriari +11
This paper introduces R2D3, an agent that makes efficient use of demonstrations to solve hard exploration problems in partially observable environments with highly variable initial…
One-Shot High-Fidelity Imitation: Training Large-Scale Deep Nets with RL
Tom Le Paine, Sergio Gómez Colmenarejo, Ziyu Wang +8
Humans are experts at high-fidelity imitation -- closely mimicking a demonstration, often in one attempt. Humans use this ability to quickly solve a task instance, and to bootstrap…
Large-Scale Visual Speech Recognition
Brendan Shillingford, Yannis Assael, Matthew W. Hoffman +12
This work presents a scalable solution to open-vocabulary visual speech recognition. To achieve this, we constructed the largest existing visual speech recognition dataset, consist…
Playing hard exploration games by watching YouTube
Yusuf Aytar, Tobias Pfaff, David Budden +3
Deep reinforcement learning methods traditionally struggle with tasks where environment rewards are particularly sparse. One successful method of guiding exploration in these domai…
Few-shot Autoregressive Density Estimation: Towards Learning to Learn Distributions
Scott Reed, Yutian Chen, Thomas Paine +5
Deep autoregressive models have shown state-of-the-art performance in density estimation for natural images on large-scale datasets such as ImageNet. However, such models require m…
Fast Generation for Convolutional Autoregressive Models
Prajit Ramachandran, Tom Le Paine, Pooya Khorrami +6
Convolutional autoregressive models have recently demonstrated state-of-the-art performance on a number of generation tasks. While fast, parallel training methods have been crucial…
Fast Wavenet Generation Algorithm
Tom Le Paine, Pooya Khorrami, Shiyu Chang +4
This paper presents an efficient implementation of the Wavenet generation process called Fast Wavenet. Compared to a naive implementation that has complexity O(2^L) (L denotes the…
Seq-NMS for Video Object Detection
Wei Han, Pooya Khorrami, Tom Le Paine +6
Video object detection is challenging because objects that are easily detected in one frame may be difficult to detect in another frame within the same clip. Recently, there have b…
How Deep Neural Networks Can Improve Emotion Recognition on Video Data
Pooya Khorrami, Tom Le Paine, Kevin Brady +2
We consider the task of dimensional emotion recognition on video data using deep learning. While several previous methods have shown the benefits of training temporal neural networ…
Do Deep Neural Networks Learn Facial Action Units When Doing Expression Recognition?
Pooya Khorrami, Tom Le Paine, Thomas S. Huang
Despite being the appearance-based classifier of choice in recent years, relatively few works have examined how much convolutional neural networks (CNNs) can improve performance on…
An Analysis of Unsupervised Pre-training in Light of Recent Advances
Tom Le Paine, Pooya Khorrami, Wei Han +1
Convolutional neural networks perform well on object recognition because of a number of recent advances: rectified linear units (ReLUs), data augmentation, dropout, and large label…