b'Sergey Levine'

research

∙ 09/18/2023

Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functions

In this work, we present a scalable reinforcement learning method for tr...

0 Yevgen Chebotar, et al. ∙

research

∙ 09/07/2023

Bootstrapping Adaptive Human-Machine Interfaces with Offline Reinforcement Learning

Adaptive interfaces can help users perform sequential decision-making ta...

0 Jensen Gao, et al. ∙

research

∙ 08/24/2023

BridgeData V2: A Dataset for Robot Learning at Scale

We introduce BridgeData V2, a large and diverse dataset of robotic manip...

0 Homer Walke, et al. ∙

research

∙ 07/28/2023

RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control

We study how vision-language models trained on Internet-scale data can b...

0 Anthony Brohan, et al. ∙

research

∙ 07/24/2023

Contrastive Example-Based Control

While many real-world problems that might benefit from reinforcement lea...

0 Kyle Hatch, et al. ∙

research

∙ 07/24/2023

A Connection between One-Step Regularization and Critic Regularization in Reinforcement Learning

As with any machine learning problem with limited data, effective offlin...

0 Benjamin Eysenbach, et al. ∙

research

∙ 07/22/2023

HIQL: Offline Goal-Conditioned RL with Latent States as Actions

Unsupervised pre-training has recently become the bedrock for computer v...

0 Seohong Park, et al. ∙

research

∙ 07/18/2023

Multi-Stage Cable Routing through Hierarchical Imitation Learning

We study the problem of learning to perform multi-stage robotic manipula...

0 Jianlan Luo, et al. ∙

research

∙ 06/30/2023

Goal Representations for Instruction Following: A Semi-Supervised Language Interface to Control

Our goal is for robots to follow natural language instructions like "put...

0 Vivek Myers, et al. ∙

research

∙ 06/26/2023

ViNT: A Foundation Model for Visual Navigation

General-purpose pre-trained models ("foundation models") have enabled pr...

0 Dhruv Shah, et al. ∙

research

∙ 06/19/2023

Confidence-Based Model Selection: When to Take Shortcuts for Subpopulation Shifts

Effective machine learning models learn both robust features that direct...

0 Annie S. Chen, et al. ∙

research

∙ 06/06/2023

Stabilizing Contrastive RL: Techniques for Offline Goal Reaching

In the same way that the computer vision (CV) and natural language proce...

0 Chongyi Zheng, et al. ∙

research

∙ 06/02/2023

SACSoN: Scalable Autonomous Data Collection for Social Navigation

Machine learning provides a powerful tool for building socially complian...

0 Noriaki Hirose, et al. ∙

research

∙ 05/25/2023

The False Promise of Imitating Proprietary LLMs

An emerging method to cheaply improve a weaker language model is to fine...

0 Arnav Gudibande, et al. ∙

research

∙ 05/22/2023

Training Diffusion Models with Reinforcement Learning

Diffusion models are a class of flexible generative models trained with ...

0 Kevin Black, et al. ∙

research

∙ 05/05/2023

Deep RL at Scale: Sorting Waste in Office Buildings with a Fleet of Mobile Manipulators

We describe a system for deep reinforcement learning of robotic manipula...

0 Alexander Herzog, et al. ∙

research

∙ 04/20/2023

IDQL: Implicit Q-Learning as an Actor-Critic Method with Diffusion Policies

Effective offline RL methods require properly handling out-of-distributi...

0 Philippe Hansen-Estruch, et al. ∙

research

∙ 04/20/2023

Efficient Deep Reinforcement Learning Requires Regulating Overfitting

Deep reinforcement learning algorithms that learn policies by trial-and-...

0 Qiyang Li, et al. ∙

research

∙ 04/19/2023

FastRLAP: A System for Learning High-Speed Driving via Deep RL and Autonomous Practicing

We present a system that enables an autonomous small-scale RC car to dri...

0 Kyle Stachowicz, et al. ∙

research

∙ 04/10/2023

Reinforcement Learning from Passive Data via Latent Intentions

Passive observational data, such as human videos, is abundant and rich i...

0 Dibya Ghosh, et al. ∙

research

∙ 03/20/2023

Neural Constraint Satisfaction: Hierarchical Abstraction for Combinatorial Generalization in Object Rearrangement

Object rearrangement is a challenge for embodied agents because solving ...

0 Michael Chang, et al. ∙

research

∙ 03/10/2023

Ignorance is Bliss: Robust Control via Information Gating

Informational parsimony – i.e., using the minimal information required f...

0 Manan Tomar, et al. ∙

research

∙ 03/09/2023

Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning

A compelling use case of offline reinforcement learning (RL) is to obtai...

0 Mitsuhiko Nakamoto, et al. ∙

research

∙ 03/06/2023

PaLM-E: An Embodied Multimodal Language Model

Large language models excel at a wide range of complex tasks. However, e...

0 Danny Driess, et al. ∙

research

∙ 03/03/2023

Learning to Influence Human Behavior with Offline Reinforcement Learning

In the real world, some of the most complex settings for learned agents ...

0 Joey Hong, et al. ∙

research

∙ 03/01/2023

Grounded Decoding: Guiding Text Generation with Grounded Models for Robot Control

Recent progress in large language models (LLMs) has demonstrated the abi...

0 Wenlong Huang, et al. ∙

research

∙ 02/19/2023

Robust and Versatile Bipedal Jumping Control through Multi-Task Reinforcement Learning

This work aims to push the limits of agility for bipedal robots by enabl...

0 Zhongyu Li, et al. ∙

research

∙ 02/10/2023

Project and Probe: Sample-Efficient Domain Adaptation by Interpolating Orthogonal Features

Conventional approaches to robustness try to learn a model based on caus...

0 Annie S. Chen, et al. ∙

research

∙ 02/08/2023

Predictable MDP Abstraction for Unsupervised Model-Based RL

A key component of model-based reinforcement learning (RL) is a dynamics...

0 Seohong Park, et al. ∙

research

∙ 02/06/2023

Bitrate-Constrained DRO: Beyond Worst Case Robustness To Unknown Group Shifts

Training machine learning models robust to distribution shifts is critic...

0 Amrith Setlur, et al. ∙

research

∙ 12/24/2022

Understanding the Complexity Gains of Single-Task RL with a Curriculum

Reinforcement learning (RL) problems can be challenging without well-sha...

0 Qiyang Li, et al. ∙

research

∙ 12/21/2022

Imitation Is Not Enough: Robustifying Imitation with Reinforcement Learning for Challenging Driving Scenarios

Imitation learning (IL) is a simple and powerful way to use high-quality...

0 Yiren Lu, et al. ∙

research

∙ 12/16/2022

Offline Reinforcement Learning for Visual Navigation

Reinforcement learning can enable robots to navigate to distant goals wh...

0 Dhruv Shah, et al. ∙

research

∙ 12/13/2022

RT-1: Robotics Transformer for Real-World Control at Scale

By transferring knowledge from large, diverse, task-agnostic datasets, m...

0 Anthony Brohan, et al. ∙

research

∙ 12/13/2022

Learning Robotic Navigation from Experience: Principles, Methods, and Recent Results

Navigation is one of the most heavily studied problems in robotics, and ...

0 Sergey Levine, et al. ∙

research

∙ 12/08/2022

Confidence-Conditioned Value Functions for Offline Reinforcement Learning

Offline reinforcement learning (RL) promises the ability to learn effect...

0 Joey Hong, et al. ∙

research

∙ 12/01/2022

Multi-Task Imitation Learning for Linear Dynamical Systems

We study representation learning for efficient imitation learning over l...

0 Thomas T. Zhang, et al. ∙

research

∙ 11/28/2022

Offline Q-Learning on Diverse Multi-Task Data Both Scales And Generalizes

The potential of offline reinforcement learning (RL) is that high-capaci...

0 Aviral Kumar, et al. ∙

research

∙ 11/21/2022

Robotic Skill Acquisition via Instruction Augmentation with Vision-Language Models

In recent years, much progress has been made in learning robotic manipul...

0 Ted Xiao, et al. ∙

research

∙ 11/21/2022

Data-Driven Offline Decision-Making via Invariant Representation Learning

The goal in offline data-driven decision-making is synthesize decisions ...

0 Han Qi, et al. ∙

research

∙ 11/02/2022

Dual Generator Offline Reinforcement Learning

In offline RL, constraining the learned policy to remain close to the da...

0 Quan Vuong, et al. ∙

research

∙ 11/02/2022

Offline RL With Realistic Datasets: Heteroskedasticity and Support Constraints

Offline reinforcement learning (RL) learns policies entirely from static...

0 Anikait Singh, et al. ∙

research

∙ 11/01/2022

Adversarial Policies Beat Professional-Level Go AIs

We attack the state-of-the-art Go-playing AI system, KataGo, by training...

0 Tony Tong Wang, et al. ∙

research

∙ 10/27/2022

Learning on the Job: Self-Rewarding Offline-to-Online Finetuning for Industrial Insertion of Novel Connectors from Vision

Learning-based methods in robotics hold the promise of generalization, b...

0 Ashvin Nair, et al. ∙

research

∙ 10/24/2022

FCM: Forgetful Causal Masking Makes Causal Language Models Better Zero-Shot Learners

Large language models (LLM) trained using the next-token-prediction obje...

0 Hao Liu, et al. ∙

research

∙ 10/18/2022

Unpacking Reward Shaping: Understanding the Benefits of Reward Engineering on Sample Complexity

Reinforcement learning provides an automated framework for learning beha...

0 Abhishek Gupta, et al. ∙

research

∙ 10/17/2022

You Only Live Once: Single-Life Reinforcement Learning

Reinforcement learning algorithms are typically designed to learn a perf...

3 Annie S. Chen, et al. ∙

research

∙ 10/14/2022

ExAug: Robot-Conditioned Navigation Policies via Geometric Experience Augmentation

Machine learning techniques rely on large and diverse datasets for gener...

0 Noriaki Hirose, et al. ∙

research

∙ 10/12/2022

Generalization with Lossy Affordances: Leveraging Broad Offline Data for Learning Visuomotor Tasks

The utilization of broad datasets has proven to be crucial for generaliz...

11 Kuan Fang, et al. ∙

research

∙ 10/11/2022

Pre-Training for Robots: Offline RL Enables Learning New Tasks from a Handful of Trials

Recent progress in deep learning highlights the tremendous potential of ...

21 Aviral Kumar, et al. ∙

Sergey Levine

Featured Co-authors