b'Sergey Levine'

ReLMM: Practical RL for Learning Mobile Manipulation Skills Using Only Onboard Sensors

In this paper, we study how robots can autonomously learn skills that re...
07/28/2021 ∙ by Charles Sun, et al. ∙ 0 ∙ share

read it
Persistent Reinforcement Learning via Subgoal Curricula

Reinforcement learning (RL) promises to enable autonomous acquisition of...
07/27/2021 ∙ by Archit Sharma, et al. ∙ 2 ∙ share

read it
MURAL: Meta-Learning Uncertainty-Aware Rewards for Outcome-Driven Reinforcement Learning

Exploration in reinforcement learning is a challenging problem: in the w...
07/15/2021 ∙ by Kevin Li, et al. ∙ 12 ∙ share

read it
Conservative Objective Models for Effective Offline Model-Based Optimization

Computational design problems arise in a number of settings, from synthe...
07/14/2021 ∙ by Brandon Trabucco, et al. ∙ 0 ∙ share

read it
Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability

Generalization is a central challenge for the deployment of reinforcemen...
07/13/2021 ∙ by Dibya Ghosh, et al. ∙ 5 ∙ share

read it
Explore and Control with Adversarial Surprise

Reinforcement learning (RL) provides a framework for learning goal-direc...
07/12/2021 ∙ by Arnaud Fickinger, et al. ∙ 4 ∙ share

read it
Offline Meta-Reinforcement Learning with Online Self-Supervision

Meta-reinforcement learning (RL) can meta-train policies that adapt to n...
07/08/2021 ∙ by Vitchyr H. Pong, et al. ∙ 0 ∙ share

read it
Modularity in Reinforcement Learning via Algorithmic Independence in Credit Assignment

Many transfer problems require re-using previously optimal decisions for...
06/28/2021 ∙ by Michael Chang, et al. ∙ 0 ∙ share

read it
Multi-Robot Deep Reinforcement Learning for Mobile Navigation

Deep reinforcement learning algorithms require large and diverse dataset...
06/24/2021 ∙ by Katie Kang, et al. ∙ 0 ∙ share

read it
Model-Based Reinforcement Learning via Latent-Space Collocation

The ability to plan into the future while utilizing only raw high-dimens...
06/24/2021 ∙ by Oleh Rybkin, et al. ∙ 9 ∙ share

read it
FitVid: Overfitting in Pixel-Level Video Prediction

An agent that is capable of predicting what happens next can perform a v...
06/24/2021 ∙ by Mohammad Babaeizadeh, et al. ∙ 6 ∙ share

read it
Which Mutual-Information Representation Learning Objectives are Sufficient for Control?

Mutual information maximization provides an appealing formalism for lear...
06/14/2021 ∙ by Kate Rakelly, et al. ∙ 0 ∙ share

read it
Reinforcement Learning as One Big Sequence Modeling Problem

Reinforcement learning (RL) is typically concerned with estimating singl...
06/03/2021 ∙ by Michael Janner, et al. ∙ 0 ∙ share

read it
Variational Empowerment as Representation Learning for Goal-Based Reinforcement Learning

Learning to reach goal states and learning diverse skills through mutual...
06/02/2021 ∙ by Jongwook Choi, et al. ∙ 9 ∙ share

read it
What Can I Do Here? Learning New Skills by Imagining Visual Affordances

A generalist robot equipped with learned skills must be able to perform ...
06/01/2021 ∙ by Alexander Khazatsky, et al. ∙ 0 ∙ share

read it
DisCo RL: Distribution-Conditioned Reinforcement Learning for General-Purpose Policies

Can we use reinforcement learning to learn general-purpose policies that...
04/23/2021 ∙ by Soroush Nasiriany, et al. ∙ 14 ∙ share

read it
Contingencies from Observations: Tractable Contingency Planning with Learned Behavior Models

Humans have a remarkable ability to make decisions by accurately reasoni...
04/21/2021 ∙ by Nicholas Rhinehart, et al. ∙ 0 ∙ share

read it
Outcome-Driven Reinforcement Learning via Variational Inference

While reinforcement learning algorithms provide automated acquisition of...
04/20/2021 ∙ by Tim G. J. Rudner, et al. ∙ 0 ∙ share

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

General-purpose robotic systems must master a large repertoire of divers...
04/16/2021 ∙ by Dmitry Kalashnikov, et al. ∙ 10 ∙ share

read it
Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills

We consider the problem of learning useful robotic skills from previousl...
04/15/2021 ∙ by Yevgen Chebotar, et al. ∙ 11 ∙ share

read it
RECON: Rapid Exploration for Open-World Navigation with Latent Goal Models

We describe a robotic learning system for autonomous navigation in diver...
04/12/2021 ∙ by Dhruv Shah, et al. ∙ 4 ∙ share

read it
AMP: Adversarial Motion Priors for Stylized Physics-Based Character Control

Synthesizing graceful and life-like behaviors for physically simulated c...
04/05/2021 ∙ by Xue Bin Peng, et al. ∙ 2 ∙ share

read it
Benchmarks for Deep Off-Policy Evaluation

Off-policy evaluation (OPE) holds the promise of being able to leverage ...
03/30/2021 ∙ by Justin Fu, et al. ∙ 13 ∙ share

read it
Reinforcement Learning for Robust Parameterized Locomotion Control of Bipedal Robots

Developing robust walking controllers for bipedal robots is a challengin...
03/26/2021 ∙ by Zhongyu Li, et al. ∙ 0 ∙ share

read it
Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning

Progress in deep reinforcement learning (RL) research is largely enabled...
03/23/2021 ∙ by Hiroki Furuta, et al. ∙ 13 ∙ share

read it
Replacing Rewards with Examples: Example-Based Policy Search via Recursive Classification

In the standard Markov decision process formalism, users specify tasks b...
03/23/2021 ∙ by Benjamin Eysenbach, et al. ∙ 0 ∙ share

read it
Maximum Entropy RL (Provably) Solves Some Robust RL Problems

Many potential applications of reinforcement learning (RL) require guara...
03/10/2021 ∙ by Benjamin Eysenbach, et al. ∙ 0 ∙ share

read it
PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning

We study reinforcement learning (RL) with no-reward demonstrations, a se...
02/24/2021 ∙ by Angelos Filos, et al. ∙ 16 ∙ share

read it
COMBO: Conservative Offline Model-Based Policy Optimization

Model-based algorithms, which learn a dynamics model from logged experie...
02/16/2021 ∙ by Tianhe Yu, et al. ∙ 0 ∙ share

read it
Offline Model-Based Optimization via Normalized Maximum Likelihood Estimation

In this work we consider data-driven optimization problems where one mus...
02/16/2021 ∙ by Justin Fu, et al. ∙ 9 ∙ share

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

Deep reinforcement learning (RL) has emerged as a promising approach for...
02/04/2021 ∙ by Julian Ibarz, et al. ∙ 48 ∙ share

read it
SimGAN: Hybrid Simulator Identification for Domain Adaptation via Adversarial Reinforcement Learning

As learning-based approaches progress towards automating robot controlle...
01/15/2021 ∙ by Yifeng Jiang, et al. ∙ 0 ∙ share

read it
Evolving Reinforcement Learning Algorithms

We propose a method for meta-learning reinforcement learning algorithms ...
01/08/2021 ∙ by John D. Co-Reyes, et al. ∙ 28 ∙ share

read it
Model-Based Visual Planning with Self-Supervised Functional Distances

A generalist robot must be able to complete a variety of tasks in its en...
12/30/2020 ∙ by Stephen Tian, et al. ∙ 13 ∙ share

read it
ViNG: Learning Open-World Navigation with Visual Goals

We propose a learning-based navigation system for reaching visually indi...
12/17/2020 ∙ by Dhruv Shah, et al. ∙ 15 ∙ share

read it
Variable-Shot Adaptation for Online Meta-Learning

Few-shot meta-learning methods consider the problem of learning new task...
12/14/2020 ∙ by Tianhe Yu, et al. ∙ 5 ∙ share

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

Distribution shifts can cause significant degradation in a broad range o...
12/14/2020 ∙ by Pang Wei Koh, et al. ∙ 11 ∙ share

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

Model-based reinforcement learning (MBRL) methods have shown strong samp...
12/08/2020 ∙ by Mohammad Babaeizadeh, et al. ∙ 7 ∙ share

read it
Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design

A wide range of reinforcement learning (RL) problems - including robustn...
12/03/2020 ∙ by Michael Dennis, et al. ∙ 0 ∙ share

read it
Parrot: Data-Driven Behavioral Priors for Reinforcement Learning

Reinforcement learning provides a general framework for flexible decisio...
11/19/2020 ∙ by Avi Singh, et al. ∙ 18 ∙ share

read it
C-Learning: Learning to Achieve Goals via Recursive Classification

We study the problem of predicting and controlling the future state dist...
11/17/2020 ∙ by Benjamin Eysenbach, et al. ∙ 12 ∙ share

read it
Reinforcement Learning with Videos: Combining Offline Observations with Interaction

Reinforcement learning is a powerful framework for robots to acquire ski...
11/12/2020 ∙ by Karl Schmeckpeper, et al. ∙ 15 ∙ share

read it
Continual Learning of Control Primitives: Skill Discovery via Reset-Games

Reinforcement learning has the potential to automate the acquisition of ...
11/10/2020 ∙ by Kelvin Xu, et al. ∙ 0 ∙ share

read it
Amortized Conditional Normalized Maximum Likelihood

While deep neural networks provide good performance for a range of chall...
11/05/2020 ∙ by Aurick Zhou, et al. ∙ 0 ∙ share

read it
Rearrangement: A Challenge for Embodied AI

We describe a framework for research and evaluation in Embodied AI. Our ...
11/03/2020 ∙ by Dhruv Batra, et al. ∙ 2 ∙ share

read it
COG: Connecting New Skills to Past Experience with Offline Reinforcement Learning

Reinforcement learning has been applied to a wide variety of robotics pr...
10/27/2020 ∙ by Avi Singh, et al. ∙ 0 ∙ share

read it
Implicit Under-Parameterization Inhibits Data-Efficient Deep Reinforcement Learning

We identify an implicit under-parameterization phenomenon in value-based...
10/27/2020 ∙ by Aviral Kumar, et al. ∙ 0 ∙ share

read it
Conservative Safety Critics for Exploration

Safe exploration presents a major challenge in reinforcement learning (R...
10/27/2020 ∙ by Homanga Bharadhwaj, et al. ∙ 0 ∙ share

read it
γ-Models: Generative Temporal Difference Learning for Infinite-Horizon Prediction

We introduce the γ-model, a predictive model of environment dynamics wit...
10/27/2020 ∙ by Michael Janner, et al. ∙ 15 ∙ share

read it
One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RL

While reinforcement learning algorithms can learn effective policies for...
10/27/2020 ∙ by Saurabh Kumar, et al. ∙ 4 ∙ share

read it

Sergey Levine

Featured Co-authors