2.3k citations · 6.3k across the 61 of their papers we have counts for
16 papers · 1 filter
Straightening Out the Straight-Through Estimator: Overcoming Optimization Challenges in Vector Quantized Networks
Minyoung Huh, Brian Cheung, Pulkit Agrawal +1
This work examines the challenges of training neural networks using vector quantization using straight-through estimation. We find that a primary cause of training instability is t…
Optimal Goal-Reaching Reinforcement Learning via Quasimetric Learning
Tongzhou Wang, Antonio Torralba, Phillip Isola +1
In goal-reaching reinforcement learning (RL), the optimal value function has a particular geometry, called quasimetric structure. This paper introduces Quasimetric Reinforcement Le…
Improved Representation of Asymmetrical Distances with Interval Quasimetric Embeddings
Tongzhou Wang, Phillip Isola
Asymmetrical distance structures (quasimetrics) are ubiquitous in our lives and are gaining more attention in machine learning applications. Imposing such quasimetric structures in…
On the Learning and Learnability of Quasimetrics
Tongzhou Wang, Phillip Isola
Our world is full of asymmetries. Gravity and wind can make reaching a place easier than coming back. Social artifacts such as genealogy charts and citation graphs are inherently d…
Denoised MDPs: Learning World Models Better Than the World Itself
Tongzhou Wang, Simon S. Du, Antonio Torralba +3
The ability to separate signal from noise, and reason with clean abstractions, is critical to intelligence. With this ability, humans can efficiently perform real world tasks witho…
Learning to Ground Multi-Agent Communication with Autoencoders
Toru Lin, Minyoung Huh, Chris Stauffer +2
Communication requires having a common language, a lingua franca, between agents. This language could emerge via a consensus process, but it may require many generations of trial a…
The Neural MMO Platform for Massively Multiagent Research
Joseph Suarez, Yilun Du, Clare Zhu +2
Neural MMO is a computationally accessible research platform that combines large agent populations, long time horizons, open-ended tasks, and modular game systems. Existing environ…
Adaptable Agent Populations via a Generative Model of Policies
Kenneth Derek, Phillip Isola
In the natural world, life has found innumerable ways to survive and often thrive. Between and even within species, each individual is in some manner unique, and this diversity len…
The Low-Rank Simplicity Bias in Deep Networks
Minyoung Huh, Hossein Mobahi, Richard Zhang +3
Modern deep neural networks are highly over-parameterized compared to the data on which they are trained, yet they often generalize remarkably well. A flurry of recent work has ask…
Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere
Tongzhou Wang, Phillip Isola
Contrastive representation learning has been outstandingly successful in practice. In this work, we identify two key properties related to the contrastive loss: (1) alignment (clos…
Supervised Contrastive Learning
Prannay Khosla, Piotr Teterwak, Chen Wang +6
Contrastive learning applied to self-supervised representation learning has seen a resurgence in recent years, leading to state of the art performance in the unsupervised training…
Neural MMO v1.3: A Massively Multiagent Game Environment for Training and Evaluating Neural Networks
Joseph Suarez, Yilun Du, Igor Mordatch +1
Progress in multiagent intelligence research is fundamentally limited by the number and quality of environments available for study. In recent years, simulated games have become a…
Contrastive Representation Distillation
Yonglong Tian, Dilip Krishnan, Phillip Isola
Often we wish to transfer representational knowledge from one neural network to another. Examples include distilling a large network into a smaller one, transferring knowledge from…
Learning to Control Self-Assembling Morphologies: A Study of Generalization via Modularity
Deepak Pathak, Chris Lu, Trevor Darrell +2
Contemporary sensorimotor learning approaches typically start with an existing complex agent (e.g., a robotic arm), which they learn to control. In contrast, this paper investigate…
Evolved Policy Gradients
Rein Houthooft, Richard Y. Chen, Phillip Isola +4
We propose a metalearning approach for learning gradient-based reinforcement learning (RL) algorithms. The idea is to evolve a differentiable loss function, such that an agent, whi…
Learning visual groups from co-occurrences in space and time
Phillip Isola, Daniel Zoran, Dilip Krishnan +1
We propose a self-supervised framework that learns to group visual entities based on their rate of co-occurrence in space and time. To model statistical dependencies between the en…