2.6k citations · 3.3k across the 23 of their papers we have counts for
16 papers · 1 filter
WANDR: A Benchmark for Wide and Deep Research
Vitaliy Polshkov, Marcin Pitera, Jeremy Yang +7
WANDR (Wide ANd Deep Research) is a benchmark of 500 realistic, challenging data-collection tasks for research agents. Each task requires a system to discover a large set of entiti…
DRACO: a Cross-Domain Benchmark for Deep Research Accuracy, Completeness, and Objectivity
Joey Zhong, Hao Zhang, Clare Southern +7
We present DRACO (Deep Research Accuracy, Completeness, and Objectivity), a benchmark of complex deep research tasks. These tasks, which span 10 domains and draw on information sou…
The Adoption and Usage of AI Agents: Early Evidence from Perplexity
Jeremy Yang, Noah Yonack, Kate Zyskowski +3
This paper presents the first large-scale field study of the adoption, usage intensity, and use cases of general-purpose AI agents operating in open-world web environments. Our ana…
BrowseSafe: Understanding and Preventing Prompt Injection Within AI Browser Agents
Kaiyuan Zhang, Mark Tenenholtz, Kyle Polley +3
The integration of artificial intelligence (AI) agents into web browsers introduces security challenges that go beyond traditional web application threat models. Prior work has ide…
CIC: Contrastive Intrinsic Control for Unsupervised Skill Discovery
Michael Laskin, Hao Liu, Xue Bin Peng +3
We introduce Contrastive Intrinsic Control (CIC), an algorithm for unsupervised skill discovery that maximizes the mutual information between state-transitions and latent skill vec…
Don't Change the Algorithm, Change the Data: Exploratory Data for Offline Reinforcement Learning
Denis Yarats, David Brandfonbrener, Hao Liu +4
Recent progress in deep learning has relied on access to large and diverse datasets. Such data-driven progress has been less evident in offline reinforcement learning (RL), because…
URLB: Unsupervised Reinforcement Learning Benchmark
Michael Laskin, Denis Yarats, Hao Liu +6
Deep Reinforcement Learning (RL) has emerged as a powerful paradigm to solve a range of complex yet specific control tasks. Yet training generalist agents that can quickly adapt to…
Reinforcement Learning with Prototypical Representations
Denis Yarats, Rob Fergus, Alessandro Lazaric +1
Learning effective representations in image-based environments is crucial for sample efficient Reinforcement Learning (RL). Unfortunately, in RL, representation learning is confoun…
On the model-based stochastic value gradient for continuous reinforcement learning
Brandon Amos, Samuel Stanton, Denis Yarats +1
For over a decade, model-based reinforcement learning has been seen as a way to leverage control-based domain knowledge to improve the sample-efficiency of reinforcement learning a…
Automatic Data Augmentation for Generalization in Deep Reinforcement Learning
Roberta Raileanu, Max Goldstein, Denis Yarats +2
Deep reinforcement learning (RL) agents often fail to generalize to unseen scenarios, even when they are trained on many instances of semantically similar environments. Data augmen…
Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels
Ilya Kostrikov, Denis Yarats, Rob Fergus
We propose a simple data augmentation technique that can be applied to standard model-free reinforcement learning algorithms, enabling robust learning directly from pixels without…
Generalized Inner Loop Meta-Learning
Edward Grefenstette, Brandon Amos, Denis Yarats +6
Many (but not all) approaches self-qualifying as "meta-learning" in deep learning and reinforcement learning fit a common pattern of approximating the solution to a nested optimiza…
On the adequacy of untuned warmup for adaptive optimization
Jerry Ma, Denis Yarats
Adaptive optimization algorithms such as Adam are widely used in deep learning. The stability of such algorithms is often improved with a warmup schedule for the learning rate. Mot…
Improving Sample Efficiency in Model-Free Reinforcement Learning from Images
Denis Yarats, Amy Zhang, Ilya Kostrikov +3
Training an agent to solve control tasks directly from high-dimensional images with model-free reinforcement learning (RL) has proven difficult. A promising approach is to learn a…
The Differentiable Cross-Entropy Method
Brandon Amos, Denis Yarats
We study the cross-entropy method (CEM) for the non-convex optimization of a continuous and parameterized objective function and introduce a differentiable variant that enables us…
Quasi-hyperbolic momentum and Adam for deep learning
Jerry Ma, Denis Yarats
Momentum-based acceleration of stochastic gradient descent (SGD) is widely used in deep learning. We propose the quasi-hyperbolic momentum algorithm (QHM) as an extremely simple al…