b'Chelsea Finn'

research

∙ 06/13/2022

Memory-Based Model Editing at Scale

Even the largest neural networks make errors, and once-correct predictio...

Eric Mitchell, et al. ∙

research

∙ 05/30/2022

Play it by Ear: Learning Skills amidst Occlusion through Audio-Visual Imitation Learning

Humans are capable of completing a range of challenging manipulation tas...

Maximilian Du, et al. ∙

research

∙ 05/11/2022

A State-Distribution Matching Approach to Non-Episodic Reinforcement Learning

While reinforcement learning (RL) provides a framework for learning thro...

Archit Sharma, et al. ∙

research

∙ 04/18/2022

Training and Evaluation of Deep Policies using Reinforcement Learning and Generative Models

We present a data-efficient framework for solving sequential decision-ma...

Ali Ghadirzadeh, et al. ∙

research

∙ 04/04/2022

Do As I Can, Not As I Say: Grounding Language in Robotic Affordances

Large language models can encode a wealth of semantic knowledge about th...

Michael Ahn, et al. ∙

research

∙ 03/15/2022

Vision-Based Manipulators Need to Also See from Their Hands

We study how the choice of visual perspective affects learning and gener...

Kyle Hsu, et al. ∙

research

∙ 03/03/2022

Correct-N-Contrast: A Contrastive Approach for Improving Robustness to Spurious Correlations

Spurious correlations pose a major challenge for robust machine learning...

Michael Zhang, et al. ∙

research

∙ 02/14/2022

Robust Policy Learning over Multiple Uncertainty Sets

Reinforcement learning (RL) agents need to be robust to variations in sa...

Annie Xie, et al. ∙

research

∙ 02/07/2022

Diversify and Disambiguate: Learning From Underspecified Data

Many datasets are underspecified, which means there are several equally ...

Yoonho Lee, et al. ∙

research

∙ 02/04/2022

BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning

In this paper, we study the problem of enabling a vision-based robotic m...

Eric Jang, et al. ∙

research

∙ 02/03/2022

How to Leverage Unlabeled Data in Offline Reinforcement Learning

Offline reinforcement learning (RL) can learn control policies from stat...

Tianhe Yu, et al. ∙

research

∙ 01/02/2022

Improving Out-of-Distribution Robustness via Selective Augmentation

Machine learning algorithms typically assume that training and test exam...

Huaxiu Yao, et al. ∙

research

∙ 12/17/2021

Autonomous Reinforcement Learning: Formalism and Benchmarking

Reinforcement learning (RL) provides a naturalistic framing for learning...

Archit Sharma, et al. ∙

research

∙ 12/09/2021

Extending the WILDS Benchmark for Unsupervised Adaptation

Machine learning systems deployed in the wild are often trained on a sou...

Shiori Sagawa, et al. ∙

research

∙ 12/08/2021

CoMPS: Continual Meta Policy Search

We develop a new continual meta-learning method to address challenges in...

Glen Berseth, et al. ∙

research

∙ 12/07/2021

Information is Power: Intrinsic Control via Information Capture

Humans and animals explore their environment and acquire useful skills e...

Nicholas Rhinehart, et al. ∙

research

∙ 12/07/2021

MESA: Offline Meta-RL for Safe Adaptation and Fault Tolerance

Safe exploration is critical for using reinforcement learning (RL) in ri...

Michael Luo, et al. ∙

research

∙ 12/06/2021

Noether Networks: Meta-Learning Useful Conserved Quantities

Progress in machine learning (ML) stems from a combination of data avail...

Ferran Alet, et al. ∙

research

∙ 10/26/2021

Meta-learning with an Adaptive Task Scheduler

To benefit the learning of a new task, meta-learning has been proposed t...

Huaxiu Yao, et al. ∙

research

∙ 10/21/2021

Fast Model Editing at Scale

While large pre-trained models have enabled impressive results on a vari...

Eric Mitchell, et al. ∙

research

∙ 10/18/2021

MEMO: Test Time Robustness via Adaptation and Augmentation

While deep neural networks can attain good accuracy on in-distribution t...

Marvin Zhang, et al. ∙

research

∙ 09/27/2021

Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasets

Robot learning holds the promise of learning policies that generalize br...

Frederik Ebert, et al. ∙

research

∙ 09/22/2021

A Workflow for Offline Model-Free Robotic Reinforcement Learning

Offline reinforcement learning (RL) enables learning control policies by...

Aviral Kumar, et al. ∙

research

∙ 09/21/2021

Example-Driven Model-Based Reinforcement Learning for Solving Long-Horizon Visuomotor Tasks

In this paper, we study the problem of learning a repertoire of low-leve...

Bohan Wu, et al. ∙

research

∙ 09/19/2021

Lifelong Robotic Reinforcement Learning by Retaining Experiences

Multi-task learning ideally allows robots to acquire a diverse repertoir...

Annie Xie, et al. ∙

research

∙ 09/16/2021

Conservative Data Sharing for Multi-Task Offline Reinforcement Learning

Offline reinforcement learning (RL) algorithms have shown promising resu...

Tianhe Yu, et al. ∙

research

∙ 09/10/2021

Efficiently Identifying Task Groupings for Multi-Task Learning

Multi-task learning can leverage information learned by one task to bene...

Christopher Fifty, et al. ∙

research

∙ 09/02/2021

Learning Language-Conditioned Robot Behavior from Offline Data and Crowd-Sourced Annotation

We study the problem of learning a range of vision-based manipulation ta...

Suraj Nair, et al. ∙

research

∙ 07/29/2021

Bayesian Embeddings for Few-Shot Open World Recognition

As autonomous decision-making agents move from narrow operating environm...

John Willes, et al. ∙

research

∙ 07/27/2021

Persistent Reinforcement Learning via Subgoal Curricula

Reinforcement learning (RL) promises to enable autonomous acquisition of...

Archit Sharma, et al. ∙

research

∙ 07/23/2021

ProtoTransformer: A Meta-Learning Approach to Providing Student Feedback

High-quality computer science education is limited by the difficulty of ...

Mike Wu, et al. ∙

research

∙ 07/21/2021

Differentiable Annealed Importance Sampling and the Perils of Gradient Noise

Annealed importance sampling (AIS) and related algorithms are highly eff...

Guodong Zhang, et al. ∙

research

∙ 07/19/2021

Just Train Twice: Improving Group Robustness without Training Group Information

Standard training via empirical risk minimization (ERM) can produce mode...

Evan Zheran Liu, et al. ∙

research

∙ 07/16/2021

Visual Adversarial Imitation Learning using Variational Models

Reward function specification, which requires considerable human effort ...

Rafael Rafailov, et al. ∙

research

∙ 06/24/2021

FitVid: Overfitting in Pixel-Level Video Prediction

An agent that is capable of predicting what happens next can perform a v...

Mohammad Babaeizadeh, et al. ∙

research

∙ 06/04/2021

Meta-Learning with Fewer Tasks through Task Interpolation

Meta-learning enables algorithms to quickly learn a newly encountered ta...

Huaxiu Yao, et al. ∙

research

∙ 04/16/2021

MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale

General-purpose robotic systems must master a large repertoire of divers...

Dmitry Kalashnikov, et al. ∙

research

∙ 04/15/2021

Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills

We consider the problem of learning useful robotic skills from previousl...

Yevgen Chebotar, et al. ∙

research

∙ 03/31/2021

Learning Generalizable Robotic Reward Functions from "In-The-Wild" Human Videos

We are motivated by the goal of generalist robots that can complete a wi...

Annie S. Chen, et al. ∙

research

∙ 03/24/2021

Discriminator Augmented Model-Based Reinforcement Learning

By planning through a learned dynamics model, model-based reinforcement ...

Behzad Haghgoo, et al. ∙

research

∙ 03/06/2021

Greedy Hierarchical Variational Autoencoders for Large-Scale Video Prediction

A video prediction model that generalizes to diverse scenes would enable...

Bohan Wu, et al. ∙

research

∙ 03/05/2021

Bayesian Meta-Learning for Few-Shot Policy Adaptation Across Robotic Platforms

Reinforcement learning methods can achieve significant performance but r...

Ali Ghadirzadeh, et al. ∙

research

∙ 02/16/2021

COMBO: Conservative Offline Model-Based Policy Optimization

Model-based algorithms, which learn a dynamics model from logged experie...

Tianhe Yu, et al. ∙

research

∙ 02/04/2021

How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned

Deep reinforcement learning (RL) has emerged as a promising approach for...

Julian Ibarz, et al. ∙

research

∙ 12/30/2020

Model-Based Visual Planning with Self-Supervised Functional Distances

A generalist robot must be able to complete a variety of tasks in its en...

Stephen Tian, et al. ∙

research

∙ 12/21/2020

Offline Reinforcement Learning from Images with Latent Space Models

Offline reinforcement learning (RL) refers to the problem of learning po...

Rafael Rafailov, et al. ∙

research

∙ 12/14/2020

Variable-Shot Adaptation for Online Meta-Learning

Few-shot meta-learning methods consider the problem of learning new task...

Tianhe Yu, et al. ∙

research

∙ 12/14/2020

WILDS: A Benchmark of in-the-Wild Distribution Shifts

Distribution shifts can cause significant degradation in a broad range o...

Pang Wei Koh, et al. ∙

research

∙ 12/08/2020

Models, Pixels, and Rewards: Evaluating Design Trade-offs in Visual Model-Based Reinforcement Learning

Model-based reinforcement learning (MBRL) methods have shown strong samp...

Mohammad Babaeizadeh, et al. ∙

research

∙ 11/12/2020

Learning Latent Representations to Influence Multi-Agent Interaction

Seamlessly interacting with humans or robots is hard because these agent...

Annie Xie, et al. ∙

Chelsea Finn

Featured Co-authors