Sergey Levine

发表

Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning pdf

Ilya Kostrikov, Kumar Krishna Agrawal, Sergey Levine, 2018, ICLR.

Learning compound multi-step controllers under unknown dynamics

Sergey Levine, Weiqiao Han, Pieter Abbeel, 2015, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

PRECOG: PREdiction Conditioned on Goals in Visual Multi-Agent Settings

Sergey Levine, Nicholas Rhinehart, Rowan McAllister, 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction

Sergey Levine, Aviral Kumar, Justin Fu, 2019, NeurIPS.

Path integral guided policy search

Sergey Levine, Stefan Schaal, Yevgen Chebotar, 2016, 2017 IEEE International Conference on Robotics and Automation (ICRA).

Feature Construction for Inverse Reinforcement Learning

Sergey Levine, Vladlen Koltun, Zoran Popovic, 2010, NIPS.

Wasserstein Dependency Measure for Representation Learning

Sergey Levine, Yoshua Bengio, Pierre Sermanet, 2019, NeurIPS.

Learning dexterous manipulation for a soft robotic hand from human demonstrations

Sergey Levine, Pieter Abbeel, Abhishek Gupta, 2016, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

Self-Supervised Deep Reinforcement Learning with Generalized Computation Graphs for Robot Navigation

Sergey Levine, Pieter Abbeel, Gregory Kahn, 2017, 2018 IEEE International Conference on Robotics and Automation (ICRA).

Learning Visual Servoing with Deep Features and Fitted Q-Iteration pdf

Sergey Levine, Pieter Abbeel, Alex X. Lee, 2017, ICLR.

Sim-To-Real via Sim-To-Sim: Data-Efficient Robotic Grasping via Randomized-To-Canonical Adaptation Networks

Sergey Levine, Raia Hadsell, Mrinal Kalakrishnan, 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates

Sergey Levine, Shixiang Gu, Ethan Holly, 2016, 2017 IEEE International Conference on Robotics and Automation (ICRA).

Learning to Identify Object Instances by Touch: Tactile Recognition via Multimodal Matching

Sergey Levine, Roberto Calandra, Justin Lin, 2019, 2019 International Conference on Robotics and Automation (ICRA).

Learning contact-rich manipulation skills with guided policy search

Nolan Wagener, Sergey Levine, Pieter Abbeel, 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

Guiding Policies with Language via Meta-Learning pdf

John DeNero, Sergey Levine, Pieter Abbeel, 2018, ICLR.

Deep reinforcement learning for tensegrity robot locomotion

Sergey Levine, Pieter Abbeel, Vytas SunSpiral, 2016, 2017 IEEE International Conference on Robotics and Automation (ICRA).

Physically plausible simulation for character animation

Sergey Levine, Jovan Popovic, S. Levine, 2012, SCA '12.

Learning Latent Plans from Play

Sergey Levine, Jonathan Tompson, Vikash Kumar, 2019, CoRL.

TRASS: Time Reversal as Self-Supervision

Sergey Levine, Chelsea Finn, Mohammad Babaeizadeh, 2020, 2020 IEEE International Conference on Robotics and Automation (ICRA).

Mint: Matrix-Interleaving for Multi-Task Learning

Sergey Levine, Karol Hausman, Abhishek Gupta, 2019 .

Gesture controllers

Sergey Levine, Sebastian Thrun, Vladlen Koltun, 2010, SIGGRAPH 2010.

Ecological Reinforcement Learning pdf

Sergey Levine, Glen Berseth, John D. Co-Reyes, 2020, ArXiv.

Few-Shot Segmentation Propagation with Guided Networks pdf

Alexei A. Efros, Sergey Levine, Trevor Darrell, 2018, ArXiv.

Recurrent Independent Mechanisms pdf

Sergey Levine, Bernhard Schölkopf, Yoshua Bengio, 2019, ICLR.

One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning pdf

Sergey Levine, Pieter Abbeel, Chelsea Finn, 2018, Robotics: Science and Systems.

Recurrent Network Models for Kinematic Tracking pdf

Jitendra Malik, Sergey Levine, Katerina Fragkiadaki, 2015, ArXiv.

Deep Reinforcement Learning for Industrial Insertion Tasks with Visual Inputs and Natural Rewards pdf

Sergey Levine, Eugen Solowjow, Jianlan Luo, 2019, 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

Uncertainty-Aware Reinforcement Learning for Collision Avoidance pdf

Sergey Levine, Pieter Abbeel, Gregory Kahn, 2017, ArXiv.

Off-Policy Evaluation of Generalization for Deep Q-Learning in BinaryReward Tasks

Sergey Levine, Julian Ibarz, Konstantinos Bousmalis, 2019 .

Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning pdf

Sergey Levine, Aviral Kumar, Xue Bin Peng, 2019, ArXiv.

One-Shot Visual Imitation Learning via Meta-Learning

Sergey Levine, Pieter Abbeel, Chelsea Finn, 2017, CoRL.

EMI: Exploration with Mutual Information Maximizing State and Action Embeddings pdf

Sergey Levine, Hyun Oh Song, Yeonwoo Jeong, 2018, ArXiv.

Time-Contrastive Networks: Self-Supervised Learning from Video

Sergey Levine, Stefan Schaal, Yevgen Chebotar, 2017, 2018 IEEE International Conference on Robotics and Automation (ICRA).

Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization pdf

Sergey Levine, Pieter Abbeel, Chelsea Finn, 2016, ICML.

A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models pdf

Sergey Levine, Pieter Abbeel, Chelsea Finn, 2016, ArXiv.

Leave no Trace: Learning to Reset for Safe and Autonomous Reinforcement Learning pdf

Sergey Levine, Shixiang Gu, Julian Ibarz, 2017, ICLR.

Sim2Real View Invariant Visual Servoing by Recurrent Control

Sergey Levine, Fereshteh Sadeghi, Alexander Toshev, 2017 .

Continuous Deep Q-Learning with Model-based Acceleration pdf

Sergey Levine, Ilya Sutskever, Shixiang Gu, 2016, ICML.

The Feeling of Success: Does Touch Sensing Help Predict Grasp Outcomes?

Andrew Owens, Edward H. Adelson, Sergey Levine, 2017, CoRL.

Diagnosing Bottlenecks in Deep Q-learning Algorithms

Sergey Levine, Aviral Kumar, Justin Fu, 2019, ICML.

Reinforcement Learning with Competitive Ensembles of Information-Constrained Primitives pdf

Sergey Levine, Yoshua Bengio, Jonathan Binas, 2019, ICLR.

Real-time prosody-driven synthesis of body language

Sergey Levine, Vladlen Koltun, Christian Theobalt, 2009, ACM Trans. Graph..

Data-efficient Learning of Morphology and Controller for a Microrobot

Sergey Levine, Grant Wang, Brian Yang, 2019, 2019 International Conference on Robotics and Automation (ICRA).

When to Trust Your Model: Model-Based Policy Optimization

Sergey Levine, Justin Fu, Marvin Zhang, 2019, NeurIPS.

Unsupervised Curricula for Visual Meta-Reinforcement Learning

Allan Jabri, Alexei A. Efros, Sergey Levine, 2019, NeurIPS.

Data-Efficient Hierarchical Reinforcement Learning

Sergey Levine, Honglak Lee, Ofir Nachum, 2018, NeurIPS.

Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection

Sergey Levine, Peter Pastor, Alex Krizhevsky, 2016, Int. J. Robotics Res..

Dynamics-Aware Unsupervised Discovery of Skills pdf

Sergey Levine, Karol Hausman, Vikash Kumar, 2019, ICLR.

Meta-Learning with Implicit Gradients

Sergey Levine, Chelsea Finn, Aravind Rajeswaran, 2019, NeurIPS.

Learning Complex Neural Network Policies with Trajectory Optimization

Sergey Levine, Vladlen Koltun, S. Levine, 2014, ICML.

Universal Planning Networks: Learning Generalizable Representations for Visuomotor Control

Allan Jabri, Sergey Levine, Pieter Abbeel, 2018, ICML.

Variational Policy Search via Trajectory Optimization

Sergey Levine, Vladlen Koltun, S. Levine, 2013, NIPS.

Unsupervised Learning for Physical Interaction through Video Prediction

Sergey Levine, Chelsea Finn, Ian J. Goodfellow, 2016, NIPS.

End-to-End Learning of Semantic Grasping

Sergey Levine, Julian Ibarz, Sudheendra Vijayanarasimhan, 2017, CoRL.

Divide-and-Conquer Reinforcement Learning pdf

Sergey Levine, Vikash Kumar, Aravind Rajeswaran, 2017, ICLR.

InfoBot: Transfer and Exploration via the Information Bottleneck pdf

Sergey Levine, Yoshua Bengio, Hugo Larochelle, 2019, ICLR.

Reinforcement Learning with Deep Energy-Based Policies

Sergey Levine, Pieter Abbeel, Haoran Tang, 2017, ICML.

Self-Consistent Trajectory Autoencoder: Hierarchical Reinforcement Learning with Trajectory Embeddings

Sergey Levine, Pieter Abbeel, Abhishek Gupta, 2018, ICML.

Policy Learning with Continuous Memory States for Partially Observed Robotic Control pdf

Sergey Levine, Pieter Abbeel, Chelsea Finn, 2015, ArXiv.

Automatically Composing Representation Transformations as a Means for Generalization pdf

Thomas L. Griffiths, Sergey Levine, Abhishek Gupta, 2018, ICLR.

Learning force-based manipulation of deformable objects from multiple demonstrations

Sergey Levine, Pieter Abbeel, Abhishek Gupta, 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

Learning Dexterous Manipulation Policies from Experience and Imitation pdf

Sergey Levine, Abhishek Gupta, Vikash Kumar, 2016, ArXiv.

SOLAR: Deep Structured Representations for Model-Based Reinforcement Learning

Sergey Levine, Pieter Abbeel, Matthew J. Johnson, 2018, ICML.

Rewriting History with Inverse RL: Hindsight Inference for Policy Improvement pdf

Sergey Levine, Ruslan Salakhutdinov, Xinyang Geng, 2020, NeurIPS.

Deep visual foresight for planning robot motion

Sergey Levine, Chelsea Finn, S. Levine, 2016, 2017 IEEE International Conference on Robotics and Automation (ICRA).

Generalization through Simulation: Integrating Simulated and Real Data into Deep Reinforcement Learning for Vision-Based Autonomous Flight

Sergey Levine, Pieter Abbeel, Gregory Kahn, 2019, 2019 International Conference on Robotics and Automation (ICRA).

Variational Inverse Control with Events: A General Framework for Data-Driven Reward Definition

Sergey Levine, Justin Fu, Avi Singh, 2018, NeurIPS.

Recasting Gradient-Based Meta-Learning as Hierarchical Bayes pdf

Thomas L. Griffiths, Sergey Levine, Trevor Darrell, 2018, ICLR.

One-shot learning of manipulation skills with online dynamics adaptation and neural network priors

Sergey Levine, Pieter Abbeel, Justin Fu, 2015, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

Improvisation through Physical Understanding: Using Novel Objects as Tools with Visual Foresight pdf

Sergey Levine, Chelsea Finn, Annie Xie, 2019, Robotics: Science and Systems.

Unsupervised Learning via Meta-Learning pdf

Sergey Levine, Chelsea Finn, Kyle Hsu, 2018, ICLR.

Unsupervised Reinforcement Learning

Sergey Levine, 2020, AAMAS.

Search on the Replay Buffer: Bridging Planning and Reinforcement Learning

Sergey Levine, Ruslan Salakhutdinov, Benjamin Eysenbach, 2019, NeurIPS.

Learning Visual Feature Spaces for Robotic Manipulation with Deep Spatial Autoencoders pdf

Sergey Levine, Trevor Darrell, Pieter Abbeel, 2015, ArXiv.

Grasp2Vec: Learning Object Representations from Self-Supervised Grasping

Sergey Levine, Vincent Vanhoucke, Eric Jang, 2018, CoRL.

Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control pdf

Sergey Levine, Chelsea Finn, Alex X. Lee, 2018, ArXiv.

Learning to Walk in the Real World with Minimal Human Effort pdf

Sergey Levine, Sehoon Ha, Peng Xu, 2020, CoRL.

Diversity is All You Need: Learning Skills without a Reward Function pdf

Sergey Levine, Abhishek Gupta, Julian Ibarz, 2018, ICLR.

Learning to Run challenge: Synthesizing physiologically accurate motion using deep reinforcement learning pdf

Sergey Levine, Marcel Salathé, Scott L. Delp, 2018, ArXiv.

Shared Autonomy via Deep Reinforcement Learning pdf

Anca D. Dragan, Sergey Levine, Siddharth Reddy, 2018, Robotics: Science and Systems.

Learning Neural Network Policies with Guided Policy Search under Unknown Dynamics

Sergey Levine, Pieter Abbeel, S. Levine, 2014, NIPS.

Universal Planning Networks pdf

Allan Jabri, Sergey Levine, Pieter Abbeel, 2018, ICML.

Near-Optimal Representation Learning for Hierarchical Reinforcement Learning pdf

Sergey Levine, Honglak Lee, Ofir Nachum, 2018, ICLR.

Visual Reinforcement Learning with Imagined Goals

Sergey Levine, Ashvin Nair, Shikhar Bahl, 2018, NeurIPS.

Unsupervised Perceptual Rewards for Imitation Learning pdf

Sergey Levine, Pierre Sermanet, Kelvin Xu, 2016, Robotics: Science and Systems.

Deep Imitative Models for Flexible Inference, Planning, and Control pdf

Sergey Levine, Nicholas Rhinehart, Rowan McAllister, 2018, ICLR.

Learning a Prior over Intent via Meta-Inverse Reinforcement Learning

Anca D. Dragan, Sergey Levine, Chelsea Finn, 2018, ICML.

Time-Contrastive Networks: Self-Supervised Learning from Multi-view Observation

Sergey Levine, Pierre Sermanet, Corey Lynch, 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

Exploring Deep and Recurrent Architectures for Optimal Control pdf

Sergey Levine, S. Levine, 2013, ArXiv.

Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic pdf

Sergey Levine, Richard E. Turner, Zoubin Ghahramani, 2016, ICLR.

Plan Arithmetic: Compositional Plan Vectors for Multi-Task Control pdf

Sergey Levine, Trevor Darrell, Pieter Abbeel, 2019, ArXiv.

Reset-free guided policy search: Efficient deep reinforcement learning with stochastic initial states

Sergey Levine, Anurag Ajay, Pieter Abbeel, 2016, 2017 IEEE International Conference on Robotics and Automation (ICRA).

InfoBot: Structured Exploration in ReinforcementLearning Using Information Bottleneck

Sergey Levine, Yoshua Bengio, Hugo Larochelle, 2019 .

Model-Based Reinforcement Learning for Atari pdf

Sergey Levine, Dumitru Erhan, Roy H. Campbell, 2019, ICLR.

Optimal control with learned local models: Application to dexterous manipulation

Sergey Levine, Vikash Kumar, Emanuel Todorov, 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

Combining Model-Based and Model-Free Updates for Trajectory-Centric Reinforcement Learning

Gaurav S. Sukhatme, Sergey Levine, Stefan Schaal, 2017, ICML.

Soft Actor-Critic Algorithms and Applications pdf

Henry Zhu, Sergey Levine, Sehoon Ha, 2018, ArXiv.

Introduction to NIPS 2017 Competition Track

Sergio Escalera, Alexander I. Rudnicky, Sergey Levine, 2018 .

If MaxEnt RL is the Answer, What is the Question? pdf

Sergey Levine, Benjamin Eysenbach, S. Levine, 2019, ArXiv.

One-Shot Hierarchical Imitation Learning of Compound Visuomotor Tasks pdf

Sergey Levine, Pieter Abbeel, Chelsea Finn, 2018, ArXiv.

Sim2Real View Invariant Visual Servoing by Recurrent Control

Sergey Levine, Fereshteh Sadeghi, Alexander Toshev, 2017, ArXiv.

Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review pdf

Sergey Levine, S. Levine, 2018, ArXiv.

Time-Agnostic Prediction: Predicting Predictable Video Frames pdf

Alexei A. Efros, Sergey Levine, Dinesh Jayaraman, 2018, ICLR.

Gesture controllers

Sergey Levine, Sebastian Thrun, Vladlen Koltun, 2010, ACM Trans. Graph..

Recurrent Network Models for Human Dynamics

Jitendra Malik, Sergey Levine, Katerina Fragkiadaki, 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

Hierarchical Deep Reinforcement Learning Agent with Counter Self-play on Competitive Games

Sergey Levine, Trevor Darrell, Pieter Abbeel, 2018 .

Learning deep neural network policies with continuous memory states

Sergey Levine, Pieter Abbeel, Chelsea Finn, 2015, 2016 IEEE International Conference on Robotics and Automation (ICRA).

Robustness to Out-of-Distribution Inputs via Task-Aware Generative Uncertainty

Sergey Levine, Rowan McAllister, Jeff Clune, 2018, 2019 International Conference on Robotics and Automation (ICRA).

Hope For The Best But Prepare For The Worst: Cautious Adaptation In RL Agents

Sergey Levine, Chelsea Finn, Dinesh Jayaraman, 2019 .

Learning Flexible and Reusable Locomotion Primitives for a Microrobot

Sergey Levine, Kristofer S. J. Pister, Grant Wang, 2018, IEEE Robotics and Automation Letters.

Unsupervised Exploration with Deep Model-Based Reinforcement Learning

Sergey Levine, Rowan McAllister, Roberto Calandra, 2018 .

EMI: Exploration with Mutual Information

Sergey Levine, Hyun Oh Song, Hyoungseok Kim, 2018, ICML.

Learning from multiple demonstrations using trajectory-aware non-rigid registration with applications to deformable object manipulation

Sergey Levine, Pieter Abbeel, Abhishek Gupta, 2015, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

Low-Level Control of a Quadrotor With Deep Model-Based Reinforcement Learning

Sergey Levine, Kristofer S. J. Pister, Daniel S. Drew, 2019, IEEE Robotics and Automation Letters.

Accelerating Human Learning with Deep Reinforcement Learning

Anca D. Dragan, Sergey Levine, Siddharth Reddy, 2017 .

Residual Reinforcement Learning for Robot Control

Sergey Levine, Matthias Loskyll, Avinash Kumar, 2018, 2019 International Conference on Robotics and Automation (ICRA).

Towards Adapting Deep Visuomotor Representations from Simulated to Real Environments pdf

Sergey Levine, Trevor Darrell, Kate Saenko, 2015, ArXiv.

Policy Search

Sergey Levine, 2017, Encyclopedia of Machine Learning and Data Mining.

Off-Policy Evaluation via Off-Policy Classification

Sergey Levine, Chris Harris, Alex Irpan, 2019, NeurIPS.

REPLAB: A Reproducible Low-Cost Arm Benchmark Platform for Robotic Learning pdf

Sergey Levine, Brian Yang, Dinesh Jayaraman, 2019, ArXiv.

Deep Reinforcement Learning for Vision-Based Robotic Grasping: A Simulated Comparative Evaluation of Off-Policy Methods

Sergey Levine, Chelsea Finn, Ofir Nachum, 2018, 2018 IEEE International Conference on Robotics and Automation (ICRA).

Modular Multitask Reinforcement Learning with Policy Sketches pdf

Dan Klein, Sergey Levine, Jacob Andreas, 2016, ICML.

Dynamical Distance Learning for Semi-Supervised and Unsupervised Skill Discovery

Sergey Levine, Xinyang Geng, Tuomas Haarnoja, 2020, ICLR.

Trust Region Policy Optimization pdf

Sergey Levine, Michael I. Jordan, Pieter Abbeel, 2015, ICML.

Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor

Sergey Levine, Pieter Abbeel, Aurick Zhou, 2018, ICML.

MuProp: Unbiased Backpropagation for Stochastic Neural Networks pdf

Sergey Levine, Ilya Sutskever, Andriy Mnih, 2015, ICLR.

Learning with Latent Language pdf

Dan Klein, Sergey Levine, Jacob Andreas, 2017, NAACL.

Composable Action-Conditioned Predictors: Flexible Off-Policy Learning for Robot Navigation pdf

Sergey Levine, Pieter Abbeel, Gregory Kahn, 2018, CoRL.

QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation pdf

Sergey Levine, Alexander Herzog, Mrinal Kalakrishnan, 2018, CoRL.

End-to-End Training of Deep Visuomotor Policies pdf

Sergey Levine, Trevor Darrell, Pieter Abbeel, 2015, J. Mach. Learn. Res..

Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models pdf

Sergey Levine, Pieter Abbeel, Bradly C. Stadie, 2015, ArXiv.

Skew-Fit: State-Covering Self-Supervised Reinforcement Learning pdf

Sergey Levine, Ashvin Nair, Shikhar Bahl, 2019, ICML.

Backprop KF: Learning Discriminative Deterministic State Estimators

Sergey Levine, Anurag Ajay, Pieter Abbeel, 2016, NIPS.

Regret Minimization for Partially Observable Deep Reinforcement Learning pdf

Kurt Keutzer, Sergey Levine, Peter H. Jin, 2017, ICML.

VideoFlow: A Flow-Based Generative Model for Video

Sergey Levine, Dumitru Erhan, Chelsea Finn, 2019, ArXiv.

Learning to Adapt: Meta-Learning for Model-Based Control pdf

Sergey Levine, Ronald S. Fearing, Pieter Abbeel, 2018, ArXiv.

SQIL: Imitation Learning via Reinforcement Learning with Sparse Rewards

Anca D. Dragan, Sergey Levine, Siddharth Reddy, 2019, ICLR.

Learning Robotic Manipulation of Granular Media

Sergey Levine, Jonathan Tompson, Connor Schenck, 2017, CoRL.

Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flow pdf

Sergey Levine, Pieter Abbeel, Angjoo Kanazawa, 2018, ICLR.

Learning to Walk via Deep Reinforcement Learning pdf

Sergey Levine, Sehoon Ha, Jie Tan, 2018, Robotics: Science and Systems.

Adapting Deep Visuomotor Representations with Weak Pairwise Constraints

Sergey Levine, Trevor Darrell, Kate Saenko, 2015, WAFR.

Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning

Sergey Levine, Gregory Kahn, Anusha Nagabandi, 2017, 2018 IEEE International Conference on Robotics and Automation (ICRA).

Learning from the hindsight plan — Episodic MPC improvement

Sergey Levine, Pieter Abbeel, Tianhao Zhang, 2016, 2017 IEEE International Conference on Robotics and Automation (ICRA).

Unsupervised Meta-Learning for Reinforcement Learning pdf

Sergey Levine, Abhishek Gupta, Chelsea Finn, 2018, ArXiv.

Deep Online Learning via Meta-Learning: Continual Adaptation for Model-Based RL pdf

Sergey Levine, Chelsea Finn, Anusha Nagabandi, 2018, ICLR.

Learning Visual Predictive Models of Physics for Playing Billiards pdf

Jitendra Malik, Sergey Levine, Katerina Fragkiadaki, 2015, ICLR.

The Ingredients of Real-World Robotic Reinforcement Learning pdf

Sergey Levine, Abhishek Gupta, Vikash Kumar, 2020, ICLR.

Real-time prosody-driven synthesis of body language

Sergey Levine, Vladlen Koltun, Christian Theobalt, 2009, SIGGRAPH 2009.

Online Meta-Learning

Sergey Levine, Sham M. Kakade, Chelsea Finn, 2019, ICML.

Deep spatial autoencoders for visuomotor learning

Sergey Levine, Trevor Darrell, Pieter Abbeel, 2015, 2016 IEEE International Conference on Robotics and Automation (ICRA).

Continuous Inverse Optimal Control with Locally Optimal Examples pdf

Sergey Levine, Vladlen Koltun, S. Levine, 2012, ICML.

MELD: Meta-Reinforcement Learning from Images via Latent State Models pdf

Sergey Levine, Chelsea Finn, Anusha Nagabandi, 2020, CoRL.

Manipulation by Feel: Touch-Based Control with Deep Predictive Models

Sergey Levine, Chelsea Finn, Stephen Tian, 2019, 2019 International Conference on Robotics and Automation (ICRA).

The Mirage of Action-Dependent Baselines in Reinforcement Learning pdf

Sergey Levine, Richard E. Turner, Zoubin Ghahramani, 2018, ICML.

Time Reversal as Self-Supervision pdf

Sergey Levine, Chelsea Finn, Vikash Kumar, 2018, ArXiv.

Learning Robust Rewards with Adversarial Inverse Reinforcement Learning pdf

Sergey Levine, Justin Fu, Katie Luo, 2017, ICLR 2017.

Learning Powerful Policies by Using Consistent Dynamics Model pdf

Sergey Levine, Yoshua Bengio, Tristan Deleu, 2019, ArXiv.

(CAD)$^2$RL: Real Single-Image Flight without a Single Real Image pdf

Sergey Levine, Fereshteh Sadeghi, S. Levine, 2016, Robotics: Science and Systems.

Learning Hand-Eye Coordination for Robotic Grasping with Large-Scale Data Collection

Sergey Levine, Peter Pastor, Alex Krizhevsky, 2016, ISER.

Deep Dynamics Models for Learning Dexterous Manipulation pdf

Sergey Levine, Vikash Kumar, Anusha Nagabandi, 2019, CoRL.

ROBEL: Robotics Benchmarks for Learning with Low-Cost Robots

Henry Zhu, Sergey Levine, Abhishek Gupta, 2019, CoRL.

Probabilistic Model-Agnostic Meta-Learning

Sergey Levine, Chelsea Finn, Kelvin Xu, 2018, NeurIPS.

Latent Space Policies for Hierarchical Reinforcement Learning

Sergey Levine, Pieter Abbeel, Tuomas Haarnoja, 2018, ICML.

Learning to Run challenge solutions: Adapting reinforcement learning methods for neuromusculoskeletal environments pdf

Sergey M. Plis, Helge J. Ritter, Sergey Levine, 2018, ArXiv.

Hierarchical Policy Design for Sample-Efficient Learning of Robot Table Tennis Through Self-Play pdf

Risto Miikkulainen, Sergey Levine, Navdeep Jaitly, 2018, ArXiv.

Reinforcement Learning from Imperfect Demonstrations pdf

Yang Gao, Sergey Levine, Trevor Darrell, 2018, ICLR.

Stochastic Adversarial Video Prediction pdf

Sergey Levine, Pieter Abbeel, Chelsea Finn, 2018, ArXiv.

Deep Object-Centric Representations for Generalizable Robot Learning

Sergey Levine, Trevor Darrell, Pieter Abbeel, 2017, 2018 IEEE International Conference on Robotics and Automation (ICRA).

Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models

Sergey Levine, Rowan McAllister, Roberto Calandra, 2018, NeurIPS.

Guided Policy Search

Sergey Levine, Vladlen Koltun, S. Levine, 2013, ICML.

From Language to Goals: Inverse Reinforcement Learning for Vision-Based Instruction Following pdf

Sergey Levine, Sergio Guadarrama, Justin Fu, 2019, ICLR.

High-Dimensional Continuous Control Using Generalized Advantage Estimation pdf

Sergey Levine, Michael I. Jordan, Pieter Abbeel, 2015, ICLR.

Contextual Imagined Goals for Self-Supervised Robotic Learning

Sergey Levine, Glen Berseth, Ashvin Nair, 2019, CoRL.

Planning with Goal-Conditioned Policies

Sergey Levine, Vitchyr Pong, Vitchyr H. Pong, 2019, NeurIPS.

MCP: Learning Composable Hierarchical Control with Multiplicative Compositional Policies

Sergey Levine, Pieter Abbeel, Xue Bin Peng, 2019, NeurIPS.

DeepMimic

Sergey Levine, Pieter Abbeel, Michiel van de Panne, 2018, ACM Trans. Graph..

Goal-Conditioned Video Prediction

Sergey Levine, Chelsea Finn, Oleh Rybkin, 2019 .

Model-based reinforcement learning with parametrized physical models and optimism-driven exploration

Sergey Levine, Pieter Abbeel, Sachin Patil, 2015, 2016 IEEE International Conference on Robotics and Automation (ICRA).

Vision-Based Multi-Task Manipulation for Inexpensive Robots Using End-to-End Learning from Demonstration

Rouhollah Rahmatizadeh, Ladislau Bölöni, Sergey Levine, 2017, 2018 IEEE International Conference on Robotics and Automation (ICRA).

SOLAR: Deep Structured Latent Representations for Model-Based Reinforcement Learning pdf

Sergey Levine, Pieter Abbeel, Matthew J. Johnson, 2018, ArXiv.

Deep Reinforcement Learning for Robotic Manipulation pdf

Sergey Levine, Shixiang Gu, Ethan Holly, 2016, ArXiv.

Watch, Try, Learn: Meta-Learning from Demonstrations and Reward pdf

Sergey Levine, Chelsea Finn, Daniel Kappler, 2019, ICLR.

Compositional Plan Vectors

Sergey Levine, Trevor Darrell, Pieter Abbeel, 2019, NeurIPS.

Bayes Net

Dan Klein, Sergey Levine, Pieter Abbeel, 2017, Encyclopedia of Machine Learning and Data Mining.

Scaled Autonomy: Enabling Human Operators to Control Robot Fleets

Anca D. Dragan, Sergey Levine, Gokul Swamy, 2020, 2020 IEEE International Conference on Robotics and Automation (ICRA).

Parrot: Data-Driven Behavioral Priors for Reinforcement Learning pdf

Sergey Levine, Nicholas Rhinehart, Avi Singh, 2020, ICLR.

Space-time planning with parameterized locomotion controllers

Sergey Levine, Vladlen Koltun, Zoran Popovic, 2011, TOGS.

Guided Policy Search via Approximate Mirror Descent

Sergey Levine, William H. Montgomery, S. Levine, 2016, NIPS.

Dexterous Manipulation with Deep Reinforcement Learning: Efficient, General, and Low-Cost

Henry Zhu, Sergey Levine, Abhishek Gupta, 2018, 2019 International Conference on Robotics and Automation (ICRA).

Composable Deep Reinforcement Learning for Robotic Manipulation

Sergey Levine, Pieter Abbeel, Aurick Zhou, 2018, 2018 IEEE International Conference on Robotics and Automation (ICRA).

GPLAC: Generalizing Vision-Based Robotic Skills Using Weakly Labeled Images

Sergey Levine, Avi Singh, Larry Yang, 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

Self-Supervised Visual Planning with Temporal Skip Connections

Sergey Levine, Chelsea Finn, Alex X. Lee, 2017, CoRL.

Meta-Reinforcement Learning of Structured Exploration Strategies

Sergey Levine, Pieter Abbeel, Abhishek Gupta, 2018, NeurIPS.

Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations pdf

Sergey Levine, Aravind Rajeswaran, Emanuel Todorov, 2017, Robotics: Science and Systems.

Meta-Learning to Guide Segmentation

Alexei A. Efros, Sergey Levine, Trevor Darrell, 2018 .

Learning deep control policies for autonomous aerial vehicles with MPC-guided policy search

Sergey Levine, Pieter Abbeel, Tianhao Zhang, 2015, 2016 IEEE International Conference on Robotics and Automation (ICRA).

Learning to Poke by Poking: Experiential Learning of Intuitive Physics pdf

Jitendra Malik, Sergey Levine, Pieter Abbeel, 2016, NIPS.

MBMF: Model-Based Priors for Model-Free Reinforcement Learning pdf

Sergey Levine, Claire J. Tomlin, Somil Bansal, 2017, ArXiv.

Combining Model-Based and Model-Free Updates for Deep Reinforcement Learning

Gaurav S. Sukhatme, Sergey Levine, Stefan Schaal, 2017 .

Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translation

Sergey Levine, Pieter Abbeel, Abhishek Gupta, 2017, 2018 IEEE International Conference on Robotics and Automation (ICRA).

Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks

Sergey Levine, Pieter Abbeel, Chelsea Finn, 2017, ICML.

Learning Invariant Feature Spaces to Transfer Skills with Reinforcement Learning pdf

Sergey Levine, Pieter Abbeel, Abhishek Gupta, 2017, ICLR.

Learning Image-Conditioned Dynamics Models for Control of Underactuated Legged Millirobots

Sergey Levine, Ronald S. Fearing, Ravi Pandya, 2017, 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables pdf

Sergey Levine, Chelsea Finn, Aurick Zhou, 2019, ICML.

Reasoning About Physical Interactions with Object-Oriented Prediction and Planning pdf

Sergey Levine, Jiajun Wu, Joshua B. Tenenbaum, 2018, ICLR.

Nonlinear Inverse Reinforcement Learning with Gaussian Processes

Sergey Levine, Vladlen Koltun, Zoran Popovic, 2011, NIPS.

End-to-End Robotic Reinforcement Learning without Reward Engineering pdf

Sergey Levine, Chelsea Finn, Avi Singh, 2019, Robotics: Science and Systems.

Combining self-supervised learning and imitation for vision-based rope manipulation

Jitendra Malik, Sergey Levine, Pieter Abbeel, 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA).

SFV

Jitendra Malik, Sergey Levine, Pieter Abbeel, 2018, ACM Trans. Graph..

Continuous character control with low-dimensional embeddings

Sergey Levine, Vladlen Koltun, Zoran Popovic, 2012, ACM Trans. Graph..

ViNG: Learning Open-World Navigation with Visual Goals pdf

Sergey Levine, Nicholas Rhinehart, Gregory Kahn, 2020, 2021 IEEE International Conference on Robotics and Automation (ICRA).

Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning

Sergey Levine, Karol Hausman, Zhanpeng He, 2019, CoRL.

Goal-driven dynamics learning via Bayesian optimization

Sergey Levine, Claire J. Tomlin, Somil Bansal, 2017, 2017 IEEE 56th Annual Conference on Decision and Control (CDC).

Model-Based Value Estimation for Efficient Model-Free Reinforcement Learning pdf

Sergey Levine, Michael I. Jordan, Ion Stoica, 2018, ArXiv.

Learning to Manipulate Granular Media with a Robot

Sergey Levine, Jonathan Tompson, Connor Schenck, 2017 .

PLATO: Policy learning using adaptive trajectory optimization

Sergey Levine, Pieter Abbeel, Tianhao Zhang, 2016, 2017 IEEE International Conference on Robotics and Automation (ICRA).

Efficient Exploration via State Marginal Matching pdf

Sergey Levine, Eric Xing, Ruslan Salakhutdinov, 2019, ArXiv.

Stochastic Variational Video Prediction pdf

Sergey Levine, Dumitru Erhan, Roy H. Campbell, 2017, ICLR.

Few-Shot Intent Inference via Meta-Inverse Reinforcement Learning

Anca D. Dragan, Sergey Levine, Chelsea Finn, 2018 .

Extending Deep Model Predictive Control with Safety Augmented Value Estimation from Demonstrations pdf

Sergey Levine, Francesco Borrelli, Brijen Thananjeyan, 2019, ArXiv.

Learning modular neural network policies for multi-task and multi-robot transfer

Sergey Levine, Trevor Darrell, Pieter Abbeel, 2016, 2017 IEEE International Conference on Robotics and Automation (ICRA).

Learning to Adapt in Dynamic, Real-World Environments through Meta-Reinforcement Learning

Sergey Levine, Pieter Abbeel, Chelsea Finn, 2018, ICLR.

Unifying Map and Landmark Based Representations for Visual Navigation pdf

Jitendra Malik, Sergey Levine, Saurabh Gupta, 2017, ArXiv.

Conditional Networks for Few-Shot Semantic Segmentation

Alexei A. Efros, Sergey Levine, Trevor Darrell, 2018, ICLR.

Recall Traces: Backtracking Models for Efficient Reinforcement Learning pdf

Sergey Levine, Yoshua Bengio, Hugo Larochelle, 2018, ICLR.

SQIL: Imitation Learning via Regularized Behavioral Cloning pdf

Anca D. Dragan, Sergey Levine, Siddharth Reddy, 2019, ArXiv.

Meta-Learning and Universality: Deep Representations and Gradient Descent can Approximate any Learning Algorithm pdf

Sergey Levine, Chelsea Finn, S. Levine, 2017, ICLR.

Generalizing Skills with Semi-Supervised Reinforcement Learning pdf

Sergey Levine, Pieter Abbeel, Chelsea Finn, 2016, ICLR.

More Than a Feeling: Learning to Grasp and Regrasp Using Vision and Touch

Jitendra Malik, Andrew Owens, Edward H. Adelson, 2018, IEEE Robotics and Automation Letters.

Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model pdf

Sergey Levine, Pieter Abbeel, Alex X. Lee, 2019, NeurIPS.

Few-Shot Goal Inference for Visuomotor Learning and Planning

Sergey Levine, Chelsea Finn, Avi Singh, 2018, CoRL.

Neural Network Dynamics Models for Control of Under-actuated Legged Millirobots pdf

Sergey Levine, Ronald S. Fearing, Gregory Kahn, 2017, ArXiv.

Optimism-driven exploration for nonlinear systems

Sergey Levine, Michael I. Jordan, Pieter Abbeel, 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

Causal Confusion in Imitation Learning

Sergey Levine, Dinesh Jayaraman, Pim de Haan, 2019, NeurIPS.

Collective robot reinforcement learning with distributed asynchronous guided policy search

Sergey Levine, Yevgen Chebotar, Mrinal Kalakrishnan, 2016, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

Why Does Hierarchy (Sometimes) Work So Well in Reinforcement Learning? pdf

Sergey Levine, Honglak Lee, Ofir Nachum, 2019, ArXiv.

Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning

Sergey Levine, Karol Hausman, Corey Lynch, 2019, CoRL.

Learning Instance Segmentation by Interaction

Jitendra Malik, Sergey Levine, Trevor Darrell, 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

Learning Actionable Representations with Goal-Conditioned Policies pdf

Sergey Levine, Abhishek Gupta, Dibya Ghosh, 2018, ICLR.

OmniTact: A Multi-Directional High-Resolution Touch Sensor

Sergey Levine, Chelsea Finn, Stephen Tian, 2020, 2020 IEEE International Conference on Robotics and Automation (ICRA).

Dynamical Distance Learning for Unsupervised and Semi-Supervised Skill Discovery pdf

Sergey Levine, Xinyang Geng, Tuomas Haarnoja, 2019, ArXiv.

Visual Memory for Robust Path Following

Jitendra Malik, Sergey Levine, Saurabh Gupta, 2018, NeurIPS.

Where Do You Think You're Going?: Inferring Beliefs about Dynamics from Behavior

Anca D. Dragan, Sergey Levine, Siddharth Reddy, 2018, NeurIPS.

Offline policy evaluation across representations with applications to educational games

Sergey Levine, Zoran Popovic, Yun-En Liu, 2014, AAMAS.

Deep Reinforcement Learning for Industrial Insertion Tasks with Visual Inputs and Natural Reward Signals

Sergey Levine, Eugen Solowjow, Jianlan Luo, 2019 .

Adversarial Policies: Attacking Deep Reinforcement Learning pdf

Sergey Levine, Stuart J. Russell, Neel Kant, 2019, ICLR.

Temporal Difference Models: Model-Free Deep RL for Model-Based Control pdf

Sergey Levine, Shixiang Gu, Vitchyr Pong, 2018, ICLR.

REPLAB: A Reproducible Low-Cost Arm Benchmark for Robotic Learning

Sergey Levine, Brian Yang, Dinesh Jayaraman, 2019, 2019 International Conference on Robotics and Automation (ICRA).

Using Simulation and Domain Adaptation to Improve Efficiency of Deep Robotic Grasping

Sergey Levine, Kurt Konolige, Mrinal Kalakrishnan, 2018, 2018 IEEE International Conference on Robotics and Automation (ICRA).

Robustness via Retrying: Closed-Loop Robotic Manipulation with Self-Supervised Learning

Sergey Levine, Chelsea Finn, Alex X. Lee, 2018, CoRL.

Guided Meta-Policy Search

Sergey Levine, Pieter Abbeel, Abhishek Gupta, 2019, NeurIPS.

Conservative Safety Critics for Exploration pdf

Sergey Levine, Nicholas Rhinehart, Animesh Garg, 2021, ICLR.

Robust Predictable Control pdf

Sergey Levine, Ruslan Salakhutdinov, Benjamin Eysenbach, 2021, NeurIPS.

X2T: Training an X-to-Text Typing Interface with Online Learning from User Feedback

Sergey Levine, Siddharth Reddy, Karunesh Ganguly, 2022, ICLR.

Autonomous Reinforcement Learning: Formalism and Benchmarking pdf

Sergey Levine, Karol Hausman, Chelsea Finn, 2021, ArXiv.

Persistent Reinforcement Learning via Subgoal Curricula pdf

Sergey Levine, Karol Hausman, Chelsea Finn, 2021, ArXiv.

FitVid: Overfitting in Pixel-Level Video Prediction pdf

Sergey Levine, Dumitru Erhan, Chelsea Finn, 2021, ArXiv.

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

Sergey Levine, C. Karen Liu, Yunfei Bai, 2021, 2021 IEEE International Conference on Robotics and Automation (ICRA).

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

Sergey Levine, Pieter Abbeel, Angjoo Kanazawa, 2021, ACM Trans. Graph..

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

Sergey Levine, Ryan P. Adams, Aviral Kumar, 2021, NeurIPS.

Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills pdf

Sergey Levine, Yevgen Chebotar, Karol Hausman, 2021, ICML.

Modularity in Reinforcement Learning via Algorithmic Independence in Credit Assignment

Thomas L. Griffiths, Sergey Levine, Michael Chang, 2021, ICML.

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

Sergey Levine, Ruslan Salakhutdinov, Benjamin Eysenbach, 2021, NeurIPS.

Contingencies from Observations: Tractable Contingency Planning with Learned Behavior Models

Sergey Levine, Joseph E. Gonzalez, Nicholas Rhinehart, 2021, 2021 IEEE International Conference on Robotics and Automation (ICRA).

Variational Empowerment as Representation Learning for Goal-Conditioned Reinforcement Learning

Sergey Levine, Jongwook Choi, Shixiang Shane Gu, 2021, ICML.

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

Sergey Levine, Chelsea Finn, Daniel Kappler, 2022, CoRL.

Reset-Free Reinforcement Learning via Multi-Task Learning: Learning Dexterous Manipulation Behaviors without Human Intervention

Sergey Levine, Kelvin Xu, Abhishek Gupta, 2021, 2021 IEEE International Conference on Robotics and Automation (ICRA).

Variational Empowerment as Representation Learning for Goal-Based Reinforcement Learning pdf

Sergey Levine, Jongwook Choi, Shixiang Shane Gu, 2021, ArXiv.

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

Sergey Levine, Chelsea Finn, Georgios Georgakis, 2021, Robotics: Science and Systems XVIII.

Hybrid Imitative Planning with Geometric and Predictive Costs in Off-road Environments pdf

Sergey Levine, Nicholas Rhinehart, Dhruv Shah, 2021, ArXiv.

Learning to Reach Goals via Iterated Supervised Learning

Sergey Levine, Justin Fu, Coline Devin, 2019, ICLR.

Outcome-Driven Reinforcement Learning via Variational Inference pdf

Sergey Levine, Rowan McAllister, Yarin Gal, 2021, NeurIPS.

Data-Driven Offline Optimization For Architecting Hardware Accelerators pdf

Sergey Levine, Aviral Kumar, Kevin Swersky, 2021, ArXiv.

Fully Autonomous Real-World Reinforcement Learning with Applications to Mobile Manipulation

Sergey Levine, Glen Berseth, Brian Yang, 2021, CoRL.

Offline Reinforcement Learning as One Big Sequence Modeling Problem pdf

Sergey Levine, Qiyang Li, Michael Janner, 2021, NeurIPS.

Hierarchically Integrated Models: Learning to Navigate from Heterogeneous Robots

Sergey Levine, Gregory Kahn, Katie Kang, 2021, CoRL.

Explore and Control with Adversarial Surprise pdf

Sergey Levine, Natasha Jaques, Stuart J. Russell, 2021, ArXiv.

Conservative Data Sharing for Multi-Task Offline Reinforcement Learning pdf

Sergey Levine, Yevgen Chebotar, Karol Hausman, 2021, NeurIPS.

Amortized Conditional Normalized Maximum Likelihood: Reliable Out of Distribution Uncertainty Estimation

Sergey Levine, Aurick Zhou, S. Levine, 2020, ICML.

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

Sergey Levine, Glen Berseth, Brian Yang, 2021, ArXiv.

A Workflow for Offline Model-Free Robotic Reinforcement Learning

Sergey Levine, Chelsea Finn, Aviral Kumar, 2021, CoRL.

Recurrent Independent Mechanisms pdf

Bernhard Schölkopf, Sergey Levine, Yoshua Bengio, 2021, ICLR.

DR3: Value-Based Deep Reinforcement Learning Requires Explicit Regularization pdf

Sergey Levine, Aaron C. Courville, Rishabh Agarwal, 2021, ICLR.

How to train your robot with deep reinforcement learning: lessons we have learned

Sergey Levine, Chelsea Finn, Mrinal Kalakrishnan, 2021, Int. J. Robotics Res..

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

Sergey Levine, Kate Rakelly, Carlos Florensa, 2021, NeurIPS.

C-Planning: An Automatic Curriculum for Learning Goal-Reaching Tasks pdf

Sergey Levine, Ruslan Salakhutdinov, Tianjun Zhang, 2021, ICLR.

TRAIL: Near-Optimal Imitation Learning with Suboptimal Data pdf

Sergey Levine, Ofir Nachum, Mengjiao Yang, 2021, ICLR.

MEMO: Test Time Robustness via Adaptation and Augmentation pdf

Sergey Levine, Chelsea Finn, Marvin Zhang, 2021, ArXiv.

Factorizing Declarative and Procedural Knowledge in Structured, Dynamical Environments

Sergey Levine, Alex Lamb, Anirudh Goyal, 2021, ICLR.

C-Learning: Learning to Achieve Goals via Recursive Classification pdf

Sergey Levine, Ruslan Salakhutdinov, Benjamin Eysenbach, 2020, ICLR.

CoMPS: Continual Meta Policy Search pdf

Sergey Levine, Chelsea Finn, Glen Berseth, 2021, ICLR.

Pragmatic Image Compression for Human-in-the-Loop Decision-Making pdf

Anca D. Dragan, Sergey Levine, Siddharth Reddy, 2021, NeurIPS.

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

Jure Leskovec, Sergey Levine, Chelsea Finn, 2021, ICML.

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

Sergey Levine, Ashvin Nair, Alexander Khazatsky, 2021, 2021 IEEE International Conference on Robotics and Automation (ICRA).

Benchmarks for Deep Off-Policy Evaluation pdf

Sergey Levine, Mohammad Norouzi, Justin Fu, 2021, ICLR.

Legged Robots that Keep on Learning: Fine-Tuning Locomotion Policies in the Real World pdf

Sergey Levine, Sehoon Ha, J. Chase Kew, 2021, 2022 International Conference on Robotics and Automation (ICRA).

Offline Model-Based Optimization via Normalized Maximum Likelihood Estimation pdf

Sergey Levine, Justin Fu, S. Levine, 2021, ICLR.

Offline Meta-Reinforcement Learning with Online Self-Supervision pdf

Sergey Levine, Ashvin Nair, Laura Smith, 2021, ArXiv.

Simple and Effective VAE Training with Calibrated Decoders

Sergey Levine, Kostas Daniilidis, Oleh Rybkin, 2020, ICML.

COMBO: Conservative Offline Model-Based Policy Optimization pdf

Sergey Levine, Chelsea Finn, Aravind Rajeswaran, 2021, NeurIPS.

Mismatched No More: Joint Model-Policy Optimization for Model-Based RL pdf

Sergey Levine, Ruslan Salakhutdinov, Benjamin Eysenbach, 2021, ArXiv.

Extending the WILDS Benchmark for Unsupervised Adaptation pdf

Jure Leskovec, Sergey Levine, Chelsea Finn, 2021, ArXiv.

Reinforcement Learning for Robust Parameterized Locomotion Control of Bipedal Robots

Koushil Sreenath, Sergey Levine, Pieter Abbeel, 2021, 2021 IEEE International Conference on Robotics and Automation (ICRA).

Training on Test Data with Bayesian Adaptation for Covariate Shift pdf

Sergey Levine, Aurick Zhou, S. Levine, 2021, ArXiv.

Implicit Under-Parameterization Inhibits Data-Efficient Deep Reinforcement Learning pdf

Sergey Levine, Rishabh Agarwal, Aviral Kumar, 2020, ICLR.

Information is Power: Intrinsic Control via Information Capture pdf

Sergey Levine, Chelsea Finn, Glen Berseth, 2021, NeurIPS.

Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoning pdf

Sergey Levine, Brian Ichter, Alexander Toshev, 2021, ArXiv.

Understanding the World Through Action

Sergey Levine, S. Levine, 2021, CoRL.

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

Sergey Levine, Nicholas Rhinehart, Gregory Kahn, 2021, CoRL.

Multi-Robot Deep Reinforcement Learning for Mobile Navigation pdf

Sergey Levine, Gregory Kahn, Katie Kang, 2021, ArXiv.

OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning pdf

Sergey Levine, Ofir Nachum, Pulkit Agrawal, 2021, ICLR.

Model-Based Reinforcement Learning via Latent-Space Collocation pdf

Sergey Levine, Oleh Rybkin, Igor Mordatch, 2021, ICML.

Maximum Entropy RL (Provably) Solves Some Robust RL Problems pdf

Sergey Levine, Benjamin Eysenbach, 2021, ArXiv.

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

Sergey Levine, Yutaka Matsuo, Tatsuya Matsushima, 2021, ICML.

AW-Opt: Learning Robotic Skills with Imitation and Reinforcement at Scale pdf

Sergey Levine, Yevgen Chebotar, Karol Hausman, 2021, CoRL.

The Information Geometry of Unsupervised Reinforcement Learning pdf

Sergey Levine, Ruslan Salakhutdinov, Benjamin Eysenbach, 2021, ICLR.

Conservative Objective Models for Effective Offline Model-Based Optimization

Sergey Levine, Aviral Kumar, Brandon Trabucco, 2021, ICML.

Offline Meta-Reinforcement Learning for Industrial Insertion pdf

Oleg O. Sushkov, Sergey Levine, Stefan Schaal, 2021, ArXiv.

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

Sergey Levine, Glen Berseth, Ashvin Nair, 2021, 2021 IEEE International Conference on Robotics and Automation (ICRA).

Autonomous Reinforcement Learning via Subgoal Curricula

Sergey Levine, Karol Hausman, Chelsea Finn, 2021, NeurIPS.

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

Sergey Levine, Natasha Jaques, Gregory Farquhar, 2021, ICML.

RvS: What is Essential for Offline RL via Supervised Learning? pdf

Sergey Levine, Benjamin Eysenbach, Scott Emmons, 2021, ArXiv.

Offline Reinforcement Learning with Implicit Q-Learning pdf

Sergey Levine, Ashvin Nair, Ilya Kostrikov, 2021, ICLR.

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

Sergey Levine, Yevgen Chebotar, Karol Hausman, 2021, ArXiv.

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

Sergey Levine, Aurick Zhou, Ashwin Reddy, 2021, ICML.

Offline Meta-Reinforcement Learning with Advantage Weighting

Sergey Levine, Chelsea Finn, Eric Mitchell, 2020, ICML.

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

Sergey Levine, Chelsea Finn, Marvin Zhang, 2020, ArXiv.

Learned Tactile Dynamics Candidate actions Sequence Prediction Compute Costs Choose Best Action Model Predictive Control

Sergey Levine, Chelsea Finn, Stephen Tian, 2019 .

Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning pdf

Sergey Levine, Karol Hausman, Zhanpeng He, 2019, CoRL.

D4RL: Datasets for Deep Data-Driven Reinforcement Learning pdf

Sergey Levine, Justin Fu, George Tucker, 2020, ArXiv.

Combining Model-based and Model-free RL via Multi-step Control Variates

Sergey Levine, Yoshua Bengio, Yuchen Lu, 2018 .

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

Sergey Levine, Pieter Abbeel, Marvin Zhang, 2020, Robotics: Science and Systems.

Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design pdf

Sergey Levine, Natasha Jaques, Stuart Russell, 2020, NeurIPS.