Sergey Levine

LaND: Learning to Navigate from Disengagements

Consistently testing autonomous mobile robots in real world scenarios is...
10/09/2020 ∙ by Gregory Kahn, et al. ∙ 1 ∙ share

read it
Multi-agent Social Reinforcement Learning Improves Generalization

Social learning is a key component of human and animal intelligence. By ...
10/01/2020 ∙ by Kamal Ndousse, et al. ∙ 35 ∙ share

read it
Cautious Adaptation For Reinforcement Learning in Safety-Critical Settings

Reinforcement learning (RL) in real-world safety-critical target setting...
08/15/2020 ∙ by Jesse Zhang, et al. ∙ 7 ∙ share

read it
Offline Meta-Reinforcement Learning with Advantage Weighting

Massive datasets have proven critical to successfully applying deep lear...
08/13/2020 ∙ by Eric Mitchell, et al. ∙ 31 ∙ share

read it
Assisted Perception: Optimizing Observations to Communicate State

We aim to help users estimate the state of the world in tasks like robot...
08/06/2020 ∙ by Siddharth Reddy, et al. ∙ 6 ∙ share

read it
Adaptive Risk Minimization: A Meta-Learning Approach for Tackling Group Shift

A fundamental assumption of most machine learning algorithms is that the...
07/06/2020 ∙ by Marvin Zhang, et al. ∙ 5 ∙ share

read it
Decentralized Reinforcement Learning: Global Decision-Making via Local Economic Transactions

This paper seeks to establish a framework for directing a society of sim...
07/05/2020 ∙ by Michael Chang, et al. ∙ 0 ∙ share

read it
Object Files and Schemata: Factorizing Declarative and Procedural Knowledge in Dynamical Systems

Modeling a structured, dynamic environment like a video game requires ke...
06/29/2020 ∙ by Anirudh Goyal, et al. ∙ 0 ∙ share

read it
Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?

Out-of-training-distribution (OOD) scenarios are a common challenge of l...
06/26/2020 ∙ by Angelos Filos, et al. ∙ 14 ∙ share

read it
Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers

We propose a simple, practical, and intuitive approach for domain adapta...
06/24/2020 ∙ by Benjamin Eysenbach, et al. ∙ 15 ∙ share

read it
Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors

The ability to predict and plan into the future is fundamental for agent...
06/23/2020 ∙ by Karl Pertsch, et al. ∙ 8 ∙ share

read it
Simple and Effective VAE Training with Calibrated Decoders

Variational autoencoders (VAEs) provide an effective and simple method f...
06/23/2020 ∙ by Oleh Rybkin, et al. ∙ 22 ∙ share

read it
Ecological Reinforcement Learning

Much of the current work on reinforcement learning studies episodic sett...
06/22/2020 ∙ by John D. Co-Reyes, et al. ∙ 50 ∙ share

read it
Learning Invariant Representations for Reinforcement Learning without Reconstruction

We study how representation learning can accelerate reinforcement learni...
06/18/2020 ∙ by Amy Zhang, et al. ∙ 9 ∙ share

read it
Accelerating Online Reinforcement Learning with Offline Datasets

Reinforcement learning provides an appealing formalism for learning cont...
06/16/2020 ∙ by Ashvin Nair, et al. ∙ 0 ∙ share

read it
RL-CycleGAN: Reinforcement Learning Aware Simulation-To-Real

Deep neural network based reinforcement learning (RL) can learn appropri...
06/16/2020 ∙ by Kanishka Rao, et al. ∙ 10 ∙ share

read it
Meta-Reinforcement Learning Robust to Distributional Shift via Model Identification and Experience Relabeling

Reinforcement learning algorithms can acquire policies for complex tasks...
06/12/2020 ∙ by Russell Mendonca, et al. ∙ 41 ∙ share

read it
Conservative Q-Learning for Offline Reinforcement Learning

Effectively leveraging large, previously collected datasets in reinforce...
06/08/2020 ∙ by Aviral Kumar, et al. ∙ 0 ∙ share

read it
MOPO: Model-based Offline Policy Optimization

Offline reinforcement learning (RL) refers to the problem of learning po...
05/27/2020 ∙ by Tianhe Yu, et al. ∙ 15 ∙ share

read it
Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems

In this tutorial article, we aim to provide the reader with the conceptu...
05/04/2020 ∙ by Sergey Levine, et al. ∙ 28 ∙ share

read it
Meta-Reinforcement Learning for Robotic Industrial Insertion Tasks

Robotic insertion tasks are characterized by contact and friction mechan...
04/29/2020 ∙ by Gerrit Schoettler, et al. ∙ 0 ∙ share

read it
Emergent Real-World Robotic Skills via Unsupervised Off-Policy Reinforcement Learning

Reinforcement learning provides a general framework for learning robotic...
04/27/2020 ∙ by Archit Sharma, et al. ∙ 0 ∙ share

read it
The Ingredients of Real-World Robotic Reinforcement Learning

The success of reinforcement learning for real world robotics has been, ...
04/27/2020 ∙ by Henry Zhu, et al. ∙ 14 ∙ share

read it
The Variational Bandwidth Bottleneck: Stochastic Evaluation on an Information Budget

In many applications, it is desirable to extract only the relevant infor...
04/24/2020 ∙ by Anirudh Goyal, et al. ∙ 0 ∙ share

read it
Model-Based Meta-Reinforcement Learning for Flight with Suspended Payloads

Transporting suspended payloads is challenging for autonomous aerial veh...
04/23/2020 ∙ by Suneel Belkhale, et al. ∙ 1 ∙ share

read it
Efficient Adaptation for End-to-End Vision-Based Robotic Manipulation

One of the great promises of robot learning systems is that they will be...
04/21/2020 ∙ by Ryan Julian, et al. ∙ 29 ∙ share

read it
D4RL: Datasets for Deep Data-Driven Reinforcement Learning

The offline reinforcement learning (RL) problem, also referred to as bat...
04/15/2020 ∙ by Justin Fu, et al. ∙ 41 ∙ share

read it
Datasets for Data-Driven Reinforcement Learning

The offline reinforcement learning (RL) problem, also referred to as bat...
04/15/2020 ∙ by Justin Fu, et al. ∙ 6 ∙ share

read it
Thinking While Moving: Deep Reinforcement Learning with Concurrent Control

We study reinforcement learning in settings where sampling an action fro...
04/13/2020 ∙ by Ted Xiao, et al. ∙ 17 ∙ share

read it
Learning Agile Robotic Locomotion Skills by Imitating Animals

Reproducing the diverse and agile locomotion skills of animals has been ...
04/02/2020 ∙ by Xue Bin Peng, et al. ∙ 0 ∙ share

read it
Sequential Forecasting of 100,000 Points

Predicting the future is a crucial first step to effective control, sinc...
03/18/2020 ∙ by Xinshuo Weng, et al. ∙ 4 ∙ share

read it
Unsupervised Sequence Forecasting of 100,000 Points for Unsupervised Trajectory Forecasting

Predicting the future is a crucial first step to effective control, sinc...
03/18/2020 ∙ by Xinshuo Weng, et al. ∙ 0 ∙ share

read it
DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction

Deep reinforcement learning can learn effective policies for a wide rang...
03/16/2020 ∙ by Aviral Kumar, et al. ∙ 9 ∙ share

read it
OmniTact: A Multi-Directional High Resolution Touch Sensor

Incorporating touch as a sensing modality for robots can enable finer an...
03/16/2020 ∙ by Akhil Padmanabha, et al. ∙ 2 ∙ share

read it
Scalable Multi-Task Imitation Learning with Autonomous Improvement

While robot learning has demonstrated promising results for enabling rob...
02/25/2020 ∙ by Avi Singh, et al. ∙ 0 ∙ share

read it
Rewriting History with Inverse RL: Hindsight Inference for Policy Improvement

Multi-task reinforcement learning (RL) aims to simultaneously learn poli...
02/25/2020 ∙ by Benjamin Eysenbach, et al. ∙ 11 ∙ share

read it
Learning to Walk in the Real World with Minimal Human Effort

Reliable and stable locomotion has been one of the most fundamental chal...
02/20/2020 ∙ by Sehoon Ha, et al. ∙ 27 ∙ share

read it
BADGR: An Autonomous Self-Supervised Learning-Based Navigation System

Mobile robot navigation is typically regarded as a geometric problem, in...
02/13/2020 ∙ by Gregory Kahn, et al. ∙ 56 ∙ share

read it
Gradient Surgery for Multi-Task Learning

While deep learning and deep reinforcement learning (RL) systems have de...
01/19/2020 ∙ by Tianhe Yu, et al. ∙ 19 ∙ share

read it
Reward-Conditioned Policies

Reinforcement learning offers the promise of automating the acquisition ...
12/31/2019 ∙ by Aviral Kumar, et al. ∙ 0 ∙ share

read it
Model Inversion Networks for Model-Based Optimization

In this work, we aim to solve data-driven optimization problems, where t...
12/31/2019 ∙ by Aviral Kumar, et al. ∙ 3 ∙ share

read it
Morphology-Agnostic Visual Robotic Control

Existing approaches for visuomotor robotic control typically require cha...
12/31/2019 ∙ by Brian Yang, et al. ∙ 16 ∙ share

read it
Learning Predictive Models From Observation and Interaction

Learning predictive models from interaction with the world allows an age...
12/30/2019 ∙ by Karl Schmeckpeper, et al. ∙ 12 ∙ share

read it
Learning To Reach Goals Without Reinforcement Learning

Imitation learning algorithms provide a simple and straightforward appro...
12/12/2019 ∙ by Dibya Ghosh, et al. ∙ 0 ∙ share

read it
SMiRL: Surprise Minimizing RL in Dynamic Environments

All living organisms struggle against the forces of nature to carve out ...
12/11/2019 ∙ by Glen Berseth, et al. ∙ 8 ∙ share

read it
AVID: Learning Multi-Stage Tasks via Pixel-Level Translation of Human Videos

Robotic reinforcement learning (RL) holds the promise of enabling robots...
12/10/2019 ∙ by Laura Smith, et al. ∙ 11 ∙ share

read it
Unsupervised Curricula for Visual Meta-Reinforcement Learning

In principle, meta-reinforcement learning algorithms leverage experience...
12/09/2019 ∙ by Allan Jabri, et al. ∙ 7 ∙ share

read it
Meta-Learning without Memorization

The ability to learn new concepts with small amounts of data is a critic...
12/09/2019 ∙ by Mingzhang Yin, et al. ∙ 19 ∙ share

read it
Learning Human Objectives by Evaluating Hypothetical Behavior

We seek to align agent behavior with a user's objectives in a reinforcem...
12/05/2019 ∙ by Siddharth Reddy, et al. ∙ 20 ∙ share

read it
Planning with Goal-Conditioned Policies

Planning methods can solve temporally extended sequential decision makin...
11/19/2019 ∙ by Soroush Nasiriany, et al. ∙ 14 ∙ share

read it

Sergey Levine

Featured Co-authors