Chelsea Finn

发表

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

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

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

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

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

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

Deep visual foresight for planning robot motion

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

Meta-Learning with Implicit Gradients

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

Unsupervised Learning for Physical Interaction through Video Prediction

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

Universal Planning Networks: Learning Generalizable Representations for Visuomotor Control

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

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

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

End-to-End Training of Deep Visuomotor Policies pdf

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

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

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

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

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

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

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

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

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

Stochastic Adversarial Video Prediction pdf

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

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

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

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

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

Deep spatial autoencoders for visuomotor learning

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

Recasting Gradient-Based Meta-Learning as Hierarchical Bayes pdf

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

Learning a Prior over Intent via Meta-Inverse Reinforcement Learning

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

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

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

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

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

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).

Stochastic Variational Video Prediction pdf

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

Adapting Deep Visuomotor Representations with Weak Pairwise Constraints

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

Model-Based Reinforcement Learning for Atari pdf

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

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).

Gradient Surgery for Multi-Task Learning pdf

Karol Hausman, Abhishek Gupta, Chelsea Finn, 2020, NeurIPS.

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

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

Unsupervised Meta-Learning for Reinforcement Learning pdf

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

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

Harini Kannan, Dumitru Erhan, Sergey Levine, 2020, ArXiv.

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

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

Language as an Abstraction for Hierarchical Deep Reinforcement Learning

Chelsea Finn, Kevin Murphy, Yiding Jiang, 2019, NeurIPS.

Variable-Shot Adaptation for Online Meta-Learning pdf

Sergey Levine, Chelsea Finn, Tianhe Yu, 2020, ArXiv.

MOPO: Model-based Offline Policy Optimization pdf

Lantao Yu, Stefano Ermon, Tengyu Ma, 2020, NeurIPS.

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

Jure Leskovec, Sergey Levine, Chelsea Finn, 2020, ArXiv.

Entity Abstraction in Visual Model-Based Reinforcement Learning pdf

Jiajun Wu, Joshua B. Tenenbaum, Chelsea Finn, 2019, CoRL.

SMiRL: Surprise Minimizing Reinforcement Learning in Unstable Environments

Sergey Levine, Chelsea Finn, Nicholas Rhinehart, 2021, ICLR.

Meta-Learning

Sergey Levine, Sham M. Kakade, Chelsea Finn, 2019, Automated Machine Learning.

Generalizing Skills with Semi-Supervised Reinforcement Learning pdf

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

Reasoning About Physical Interactions with Object-Centric Models

S. Levine, J. Tenenbaum, W. Freeman, 2018 .

Exact (Then Approximate) Dynamic Programming for Deep Reinforcement Learning

Chelsea Finn, H. Marklund, Suraj Nair, 2020 .

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

Chelsea Finn, Ali Ghadirzadeh, D. Kragic, 2022, J. Mach. Learn. Res..

Multi-Task Offline Reinforcement Learning with Conservative Data Sharing

S. Levine, Karol Hausman, Chelsea Finn, 2021 .

Example-Based Ofﬂine Reinforcement Learning without Rewards

Chelsea Finn, Tianhe Yu, Kyle Hatch, 2021 .

Goal-Aware Prediction: Learning to Model What Matters

S. Savarese, Chelsea Finn, Suraj Nair, 2020, ICML.

Gradient Surgery for Multi-Task Learning

S. Levine, Saurabh Kumar, Abhishek Gupta, 2020, NeurIPS.

Reinforcement Learning with Videos: Combining Offline Observations with Interaction

S. Levine, Kostas Daniilidis, Chelsea Finn, 2020, CoRL.

Guided Meta-Policy Search

S. Levine, P. Abbeel, Abhishek Gupta, 2019, NeurIPS.

Universal Planning Networks-Long Version + Supplementary

S. Levine, P. Abbeel, A. Srinivas, 2018 .

Rapidly Adaptable Legged Robots via Evolutionary Meta-Learning

Chelsea Finn, Jie Tan, K. Choromanski, 2020, 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

Extending the WILDS Benchmark for Unsupervised Adaptation

Tatsunori B. Hashimoto, Pang Wei Koh, Sang Michael Xie, 2021, ICLR.

SMiRL: Surprise Minimizing Reinforcement Learning in Dynamic Environments

S. Levine, Chelsea Finn, Nicholas Rhinehart, 2019 .

S Tochastic V Ariational V Ideo P Rediction

S. Levine, D. Erhan, R. Campbell, 2018 .

Predict futures using video prediction model Training Time Test Time Collect Kinesthetic Demonstrations Autonomous Random Data

S. Levine, F. Ebert, Chelsea Finn, 2022 .

R3M: A Universal Visual Representation for Robot Manipulation

Vikash Kumar, Chelsea Finn, A. Rajeswaran, 2022, ArXiv.

Adaptive Risk Minimization: Learning to Adapt to Domain Shift

S. Levine, Abhishek Gupta, Chelsea Finn, 2020, NeurIPS.

V ARIATIONAL M ODEL -B ASED I MITATION L EARNING IN H IGH -D IMENSIONAL O BSERVATION S PACES

Chelsea Finn, A. Rajeswaran, Tianhe Yu, 2021 .

Decoupling Exploration and Exploitation for Meta-Reinforcement Learning without Sacrifices

Percy Liang, Chelsea Finn, E. Liu, 2020, ICML.

Guided Meta-Policy Search

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

Decoupled Meta-Learning with Structured Latents

S. Levine, Chelsea Finn, Russell Mendonca, 2019 .

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).

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

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

FitVid: Overfitting in Pixel-Level Video Prediction pdf

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

CoMPS: Continual Meta Policy Search pdf

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

Continuous Meta-Learning without Tasks pdf

Marco Pavone, Chelsea Finn, Apoorva Sharma, 2019, NeurIPS.

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

Sergey Levine, Chelsea Finn, Stephen Tian, 2019 .

Persistent Reinforcement Learning via Subgoal Curricula pdf

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

Extended Abstract: Concept Acquisition Through Meta-Learning

Joshua T. Abbott, Joshua C. Peterson, S. Levine, 2017 .

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

S. Levine, Deirdre Quillen, Karol Hausman, 2019, CoRL.

VideoFlow: A Conditional Flow-Based Model for Stochastic Video Generation

S. Levine, D. Erhan, Chelsea Finn, 2019, ICLR.

Structure & Priors in Reinforcement Learning (SPiRL)

Thomas L. Griffiths, Junhyuk Oh, Abhishek Gupta, 2019, ICLR 2019.

SMiRL: Surprise Minimizing RL in Entropic Environments

Sergey Levine, Chelsea Finn, Glen Berseth, 2019 .

Meta-Learning without Memorization

S. Levine, G. Tucker, Chelsea Finn, 2019, ICLR.

F AST M ODEL E DITING AT S CALE

Christopher D. Manning, Chelsea Finn, Eric Mitchell, 2021 .

A UTONOMOUS R EINFORCEMENT L EARNING : F ORMALISM AND B ENCHMARKING

S. Levine, Archit Sharma, Karol Hausman, 2022 .

Consistent Meta-Reinforcement Learning via Model Identification and Experience Relabeling

Sergey Levine, Chelsea Finn, Xinyang Geng, 2019 .

Fast Model Editing at Scale

Christopher D. Manning, A. Bosselut, Chelsea Finn, 2021, ICLR.

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

Archit Sharma, Chelsea Finn, Rehaan Ahmad, 2022, ICML.

Mint: Matrix-Interleaving for Multi-Task Learning

Sergey Levine, Karol Hausman, Abhishek Gupta, 2019 .

Offline Reinforcement Learning at Multiple Frequencies

Karol Hausman, Chelsea Finn, Tianhe Yu, 2022, CoRL.

Goal-Conditioned Video Prediction

Sergey Levine, Chelsea Finn, Oleh Rybkin, 2019 .

Memory-Based Model Editing at Scale

Christopher D. Manning, Chelsea Finn, Eric Mitchell, 2022, ICML.

Self-Supervised Learning of Object Motion Through Adversarial Video Prediction

Pieter Abbeel, Chelsea Finn, Richard Zhang, 2018 .

Autonomous Reinforcement Learning: Formalism and Benchmarking

S. Levine, Archit Sharma, Karol Hausman, 2021, ICLR.

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

S. Levine, Pierre Sermanet, Vincent Vanhoucke, 2022, CoRL.

Latent-Variable Advantage-Weighted Policy Optimization for Offline Reinforcement Learning

X. Chen, Chelsea Finn, Tianhe Yu, 2022 .

RoboNet: Large-Scale Multi-Robot Learning

S. Levine, F. Ebert, Chelsea Finn, 2019, CoRL.

Diversify and Disambiguate: Learning From Underspecified Data

Chelsea Finn, Yoonho Lee, Huaxiu Yao, 2022, ArXiv.

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

Li Fei-Fei, Chelsea Finn, Suraj Nair, 2021, CoRL.

Bayesian Embeddings for Few-Shot Open World Recognition

Steven L. Waslander, Chelsea Finn, M. Pavone, 2021, IEEE transactions on pattern analysis and machine intelligence.

You Only Live Once: Single-Life Reinforcement Learning

Annie S. Chen, S. Levine, Archit Sharma, 2022, NeurIPS.

MEMO: Test Time Robustness via Adaptation and Augmentation

S. Levine, Chelsea Finn, Marvin Zhang, 2021, NeurIPS.

Meta-Inverse Reinforcement Learning with Probabilistic Context Variables

Chelsea Finn, S. Ermon, Tianhe Yu, 2019, NeurIPS.

Learning to Reason With Relational Abstractions

James L. McClelland, Chelsea Finn, Mengye Ren, 2022, ArXiv.

C-Mixup: Improving Generalization in Regression

James Y. Zou, Chelsea Finn, Linjun Zhang, 2022, NeurIPS.

Surgical Fine-Tuning Improves Adaptation to Distribution Shifts

Annie S. Chen, Percy Liang, Ananya Kumar, 2022, International Conference on Learning Representations.

Enhancing Self-Consistency and Performance of Pre-Trained Language Models through Natural Language Inference

Christopher D. Manning, Chelsea Finn, Eric Mitchell, 2022, EMNLP.

Self-Destructing Models: Increasing the Costs of Harmful Dual Uses in Foundation Models

Christopher D. Manning, Chelsea Finn, Dan Jurafsky, 2022, ArXiv.

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

S. Levine, F. Ebert, Chelsea Finn, 2022, ArXiv.

Wild-Time: A Benchmark of in-the-Wild Distribution Shift over Time

Pang Wei Koh, Chelsea Finn, Yoonho Lee, 2022, NeurIPS.

What Makes Representation Learning from Videos Hard for Control?

T. Kollar, Percy Liang, Chelsea Finn, 2022 .

Improving Out-of-Distribution Robustness via Selective Augmentation

James Y. Zou, Chelsea Finn, Weixin Liang, 2022, ICML.

Train Offline, Test Online: A Real Robot Learning Benchmark

P. Abbeel, Chelsea Finn, A. Rajeswaran, 2023, 2023 IEEE International Conference on Robotics and Automation (ICRA).

RoboNet: Large-Scale Multi-Robot Learning

S. Levine, F. Ebert, Chelsea Finn, 2019, Conference on Robot Learning.

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

S. Levine, Vincent Vanhoucke, M. Ryoo, 2022, Robotics: Science and Systems.

Learning Options via Compression

Chelsea Finn, Benjamin Eysenbach, E. Liu, 2022, NeurIPS.

R3M: A Universal Visual Representation for Robot Manipulation

Vikash Kumar, Chelsea Finn, A. Rajeswaran, 2022, CoRL.

Learning to Reason With Relational Abstractions

James L. McClelland, Chelsea Finn, Mengye Ren, 2022, ArXiv.

Few-Shot Intent Inference via Meta-Inverse Reinforcement Learning

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

When to Ask for Help: Proactive Interventions in Autonomous Reinforcement Learning

Archit Sharma, Chelsea Finn, A. Xie, 2022, NeurIPS.

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

Chelsea Finn, Suraj Nair, Stanford, 2022, Robotics: Science and Systems.

Multi-Domain Long-Tailed Learning by Augmenting Disentangled Representations

Chelsea Finn, Allan Zhou, Xinyu Yang, 2022, ArXiv.

V ISION -B ASED M ANIPULATORS N EED TO A LSO S EE FROM T HEIR H ANDS

Chelsea Finn, Jiajun Wu, Rafael Rafailov, 2022 .

Visual Adversarial Imitation Learning using Variational Models

Chelsea Finn, A. Rajeswaran, Tianhe Yu, 2021, NeurIPS.

A Survey of Meta-Reinforcement Learning

Chelsea Finn, E. Liu, Zheng Xiong, 2023, ArXiv.

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

Sergey Levine, Chelsea Finn, Dinesh Jayaraman, 2019 .

Learning to Interactively Learn and Assist pdf

Karol Hausman, Chelsea Finn, Mark Woodward, 2019, AAAI.

Unsupervised Curricula for Visual Meta-Reinforcement Learning

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

Beyond lowest-warping cost action selection in trajectory transfer

Dylan Hadfield-Menell, Sandy H. Huang, Pieter Abbeel, 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

Efficiently Identifying Task Groupings for Multi-Task Learning

Christopher Fifty, Chelsea Finn, Tianhe Yu, 2021, NeurIPS.

Measuring and Harnessing Transference in Multi-Task Learning

Christopher Fifty, Chelsea Finn, Tianhe Yu, 2020, ArXiv.

Challenges of Acquiring Compositional Inductive Biases via Meta-Learning

Christopher D. Manning, Chelsea Finn, Eric Mitchell, 2021, MetaDL@AAAI.

On the Opportunities and Risks of Foundation Models

Michael S. Bernstein, Juan Carlos Niebles, Christopher D. Manning, 2021, ArXiv.

Self-Supervised Visual Planning with Temporal Skip Connections

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

Information is Power: Intrinsic Control via Information Capture pdf

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

Intrinsic Control of Variational Beliefs in Dynamic Partially-Observed Visual Environments

John D. Co-Reyes, S. Levine, Chelsea Finn, 2021 .

SMiRL: Surprise Minimizing RL in Dynamic Environments pdf

Sergey Levine, Chelsea Finn, Glen Berseth, 2019, ArXiv.

Unsupervised Learning via Meta-Learning pdf

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

Learning Predictive Models From Observation and Interaction

Sergey Levine, Chelsea Finn, Kostas Daniilidis, 2019, ECCV.

Greedy Hierarchical Variational Autoencoders for Large-Scale Video Prediction

Li Fei-Fei, Chelsea Finn, Suraj Nair, 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

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

Pang Wei Koh, Sang Michael Xie, Berton A. Earnshaw, 2020, ICML.

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

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

Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills pdf

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

Universal Planning Networks pdf

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

Recovery RL: Safe Reinforcement Learning With Learned Recovery Zones

Brijen Thananjeyan, Ashwin Balakrishna, Minho Hwang, 2020, IEEE Robotics and Automation Letters.

Learning to be Safe: Deep RL with a Safety Critic pdf

Sehoon Ha, Chelsea Finn, Krishnan Srinivasan, 2020, ArXiv.

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

Chelsea Finn, Suraj Nair, Annie S. Chen, 2021, Robotics: Science and Systems.

Do Deep Networks Transfer Invariances Across Classes?

George J. Pappas, Chelsea Finn, Hamed Hassani, 2022, ICLR.

Probabilistic Model-Agnostic Meta-Learning

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

Towards Adapting Deep Visuomotor Representations from Simulated to Real Environments pdf

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

DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature

Christopher D. Manning, Chelsea Finn, Yoonho Lee, 2023, ArXiv.

2022 Source Labeled Unlabeled Belgium France Norway Validation China Target United States Canada UK Japan Mexico Extra

Pang Wei Koh, Sang Michael Xie, Ananya Kumar, 2022 .

Model-Based Visual Planning with Self-Supervised Functional Distances pdf

Chelsea Finn, Stephen Tian, Suraj Nair, 2020, ICLR.

A Workflow for Offline Model-Free Robotic Reinforcement Learning

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

One-Shot Visual Imitation Learning via Meta-Learning

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

COMBO: Conservative Offline Model-Based Policy Optimization pdf

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

How to Leverage Unlabeled Data in Offline Reinforcement Learning

S. Levine, Karol Hausman, Chelsea Finn, 2022, ICML.

Conservative Data Sharing for Multi-Task Offline Reinforcement Learning pdf

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

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

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

Vision-Based Manipulators Need to Also See from Their Hands

Chelsea Finn, Jiajun Wu, Rafael Rafailov, 2022, ICLR.

Language-Driven Representation Learning for Robotics

T. Kollar, Annie S. Chen, Percy Liang, 2023, Robotics: Science and Systems.

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

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

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

Sergey Levine, Chelsea Finn, Xinyang Geng, 2020, ArXiv.

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

Sergey Levine, Chelsea Finn, Kelvin Xu, 2020, NeurIPS.

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

Amrith Rajagopal Setlur, Annie S. Chen, S. Levine, 2023, ArXiv.

Decoupling Exploration and Exploitation for Meta-Reinforcement Learning without Sacrifices

Chelsea Finn, Aditi Raghunathan, Percy Liang, 2020, ICML.

Deep Reinforcement Learning amidst Continual Structured Non-Stationarity

Chelsea Finn, Annie Xie, James Harrison, 2021, ICML.

Learning Latent Representations to Influence Multi-Agent Interaction pdf

Chelsea Finn, Dorsa Sadigh, Dylan P. Losey, 2020, CoRL.

Explore then Execute: Adapting without Rewards via Factorized Meta-Reinforcement Learning pdf

Chelsea Finn, Aditi Raghunathan, Percy Liang, 2020, ArXiv.

Deep Reinforcement Learning amidst Lifelong Non-Stationarity pdf

Chelsea Finn, Annie Xie, James Harrison, 2020, ArXiv.

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

S. Levine, F. Ebert, Chelsea Finn, 2022, Robotics: Science and Systems.

Offline Reinforcement Learning from Images with Latent Space Models pdf

Chelsea Finn, Aravind Rajeswaran, Tianhe Yu, 2020, L4DC.

Offline Meta-Reinforcement Learning with Advantage Weighting

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

Few-Shot Goal Inference for Visuomotor Learning and Planning

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

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

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

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

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

Lifelong Robotic Reinforcement Learning by Retaining Experiences

Chelsea Finn, A. Xie, 2021, CoLLAs.

Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors pdf

Chelsea Finn, Oleh Rybkin, Karl Pertsch, 2020, NeurIPS.

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

S. Savarese, Chelsea Finn, Suraj Nair, 2021, CoRL.

Surgical Fine-Tuning Improves Adaptation to Distribution Shifts

Annie S. Chen, Percy Liang, Ananya Kumar, 2022, ArXiv.

Cautious Adaptation For Reinforcement Learning in Safety-Critical Settings pdf

Chelsea Finn, Dinesh Jayaraman, Sergey Levine, 2020, ICML.

Behavior Retrieval: Few-Shot Imitation Learning by Querying Unlabeled Datasets

Chelsea Finn, Suraj Nair, Dorsa Sadigh, 2023, ArXiv.

Just Train Twice: Improving Group Robustness without Training Group Information

Chelsea Finn, Aditi Raghunathan, Percy Liang, 2021, ICML.

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

Sergey Levine, Chelsea Finn, Aviral Kumar, 2020, NeurIPS.

Diversify and Disambiguate: Learning From Underspecified Data

Chelsea Finn, Yoonho Lee, Huaxiu Yao, 2022, ArXiv.

Scalable Multi-Task Imitation Learning with Autonomous Improvement

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

Meta-Learning Symmetries by Reparameterization pdf

Chelsea Finn, Allan Zhou, Tom Knowles, 2020, ICLR.

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

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

Learning to Learn with Gradients

Chelsea Finn, Chelsea Finn, 2018 .

Meta-Learning with Fewer Tasks through Task Interpolation

Chelsea Finn, Linjun Zhang, Huaxiu Yao, 2021, ICLR.

ProtoTransformer: A Meta-Learning Approach to Providing Student Feedback pdf

Mike Wu, Chelsea Finn, Noah D. Goodman, 2021, ArXiv.

Open-World Object Manipulation using Pre-trained Vision-Language Models

Karol Hausman, Chelsea Finn, Paul Wohlhart, 2023, ArXiv.

Entity Abstraction in Visual Model-Based Reinforcement Learning

John D. Co-Reyes, S. Levine, J. Tenenbaum, 2019, CoRL.

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

Michael Zhang, Chelsea Finn, N. Sohoni, 2022, ICML.

Latent-Variable Advantage-Weighted Policy Optimization for Offline RL

Xi Chen, Chelsea Finn, Tianhe Yu, 2022, ArXiv.

Hierarchical Foresight: Self-Supervised Learning of Long-Horizon Tasks via Visual Subgoal Generation pdf

Chelsea Finn, Suraj Nair, Chelsea Finn, 2019, ICLR.

Permutation Equivariant Neural Functionals

J. Z. Kolter, Chelsea Finn, Yiding Jiang, 2023, ArXiv.

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

S. Levine, Chelsea Finn, Aviral Kumar, 2023, arXiv.org.

Self-Improving Robots: End-to-End Autonomous Visuomotor Reinforcement Learning

Ahmed M. Ahmed, Archit Sharma, Chelsea Finn, 2023, arXiv.org.

Autonomous Reinforcement Learning via Subgoal Curricula

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

OmniTact: A Multi-Directional High-Resolution Touch Sensor

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

Active One-shot Learning pdf

Chelsea Finn, Mark Woodward, Mark P. Woodward, 2017, ArXiv.

NeRF in the Palm of Your Hand: Corrective Augmentation for Robotics via Novel-View Synthesis

Peter R. Florence, Chelsea Finn, Allan Zhou, 2023, 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

VideoFlow: A Flow-Based Generative Model for Video

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

Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware

S. Levine, Vikash Kumar, Chelsea Finn, 2023, Robotics: Science and Systems.

Weakly-Supervised Reinforcement Learning for Controllable Behavior pdf

Ruslan Salakhutdinov, Chelsea Finn, Shixiang Gu, 2020, NeurIPS.

One-Shot Hierarchical Imitation Learning of Compound Visuomotor Tasks pdf

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

Bridging text spotting and SLAM with junction features

John J. Leonard, Seth J. Teller, Liam Paull, 2015, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

Knowledge-Driven New Drug Recommendation

David M. Liebovitz, James Y. Zou, Chelsea Finn, 2022, ArXiv.

Efficient Adaptation for End-to-End Vision-Based Robotic Manipulation pdf

Gaurav S. Sukhatme, Karol Hausman, Ryan Julian, 2020, RSS 2020.

Multi-Domain Long-Tailed Learning by Augmenting Disentangled Representations

Chelsea Finn, Allan Zhou, Xinyu Yang, 2022, ArXiv.

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

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

Surgical Fine-Tuning Improves Adaptation to Distribution Shifts

Annie S. Chen, Percy Liang, Ananya Kumar, 2022, ICLR.

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

Amrith Rajagopal Setlur, Annie S. Chen, S. Levine, 2023, ArXiv.

Direct Preference Optimization: Your Language Model is Secretly a Reward Model

Christopher D. Manning, Archit Sharma, Chelsea Finn, 2023, NeurIPS.

Policy Architectures for Compositional Generalization in Control

Vikash Kumar, Chelsea Finn, A. Rajeswaran, 2022, ArXiv.

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

Amrith Rajagopal Setlur, S. Levine, Chelsea Finn, 2023, ICLR.

Meta-Learning Online Adaptation of Language Models

Christopher D. Manning, Chelsea Finn, Nathan J. Hu, 2023, ArXiv.

NoRML: No-Reward Meta Learning pdf

Atil Iscen, Jie Tan, Chelsea Finn, 2019, AAMAS.

Noether Networks: Meta-Learning Useful Conserved Quantities pdf

Chelsea Finn, Ferran Alet, Joshua Tenenbaum, 2021, NeurIPS.

A Control-Centric Benchmark for Video Prediction

Chelsea Finn, Jiajun Wu, Stephen Tian, 2023, ICLR.

Discriminator Augmented Model-Based Reinforcement Learning pdf

Chelsea Finn, Behzad Haghgoo, Archit Sharma, 2021, ArXiv.

Never Stop Learning: The Effectiveness of Fine-Tuning in Robotic Reinforcement Learning

S. Levine, Karol Hausman, Chelsea Finn, 2020, CoRL.

DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature

Christopher D. Manning, Chelsea Finn, Yoonho Lee, 2023, ICML.

Meta-learning with an Adaptive Task Scheduler pdf

Yu Wang, Chelsea Finn, Mehrdad Mahdavi, 2021, NeurIPS.

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

S. Levine, F. Ebert, Chelsea Finn, 2021, Robotics: Science and Systems.

Supervised Pretraining Can Learn In-Context Reinforcement Learning

Ofir Nachum, Chelsea Finn, A. Xie, 2023, arXiv.org.

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

S. Levine, Chelsea Finn, Aviral Kumar, 2023, ArXiv.

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

Amrith Rajagopal Setlur, Annie S. Chen, S. Levine, 2023, ArXiv.

Neural Functional Transformers

J. Z. Kolter, Chelsea Finn, Allan Zhou, 2023, ArXiv.

A C ONTROL -C ENTRIC B ENCHMARK FOR V IDEO P REDICTION

Chelsea Finn, Jiajun Wu, Stephen Tian, 2022 .

Leveraging Domain Relations for Domain Generalization

Pang Wei Koh, Chelsea Finn, Shengchao Liu, 2023, ArXiv.

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

S. Levine, Vincent Vanhoucke, M. Ryoo, 2022, Robotics: Science and Systems.

Simple Embodied Language Learning as a Byproduct of Meta-Reinforcement Learning

Chelsea Finn, S. Suri, E. Liu, 2023, ICML.

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

Danica Kragic, Chelsea Finn, Mårten Björkman, 2021, 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

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

Ion Stoica, Brijen Thananjeyan, Ashwin Balakrishna, 2021, ArXiv.

Robust Policy Learning over Multiple Uncertainty Sets

Joelle Pineau, Chelsea Finn, A. Xie, 2022, ICML.

Self-Destructing Models: Increasing the Costs of Harmful Dual Uses of Foundation Models

Christopher D. Manning, Chelsea Finn, Dan Jurafsky, 2022, Proceedings of the 2023 AAAI/ACM Conference on AI, Ethics, and Society.

Waypoint-Based Imitation Learning for Robotic Manipulation

Archit Sharma, Chelsea Finn, Tony Zhao, 2023, 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).

Behavior Retrieval: Few-Shot Imitation Learning by Querying Unlabeled Datasets

Chelsea Finn, Suraj Nair, Dorsa Sadigh, 2023, Robotics: Science and Systems.

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

Peter R. Florence, Montse Gonzalez Arenas, S. Levine, 2023, ArXiv.

Decomposing the Generalization Gap in Imitation Learning for Visual Robotic Manipulation

Chelsea Finn, A. Xie, Ted Xiao, 2023, ArXiv.

Polybot: Training One Policy Across Robots While Embracing Variability

Chelsea Finn, Dorsa Sadigh, Jonathan Yang, 2023, ArXiv.

Disentanglement via Latent Quantization

James C. R. Whittington, Chelsea Finn, Jiajun Wu, 2023, ArXiv.

Conservative Prediction via Data-Driven Confidence Minimization

Ananya Kumar, Chelsea Finn, Yoonho Lee, 2023, arXiv.org.

Disentanglement via Latent Quantization

James C. R. Whittington, Chelsea Finn, Jiajun Wu, 2023, ArXiv.

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

S. Levine, Chelsea Finn, Aviral Kumar, 2023, ArXiv.

Contrastive Example-Based Control

S. Levine, R. Salakhutdinov, Chelsea Finn, 2023, L4DC.

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

S. Levine, F. Ebert, Chelsea Finn, 2022, Robotics: Science and Systems.

Batch Exploration With Examples for Scalable Robotic Reinforcement Learning pdf

Chelsea Finn, Suraj Nair, Annie S. Chen, 2020, IEEE Robotics and Automation Letters.

Open X-Embodiment: Robotic Learning Datasets and RT-X Models

Pannag R. Sanketi, Norman Di Palo, Lawrence Yunliang Chen, 2023, ArXiv.

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

S. Levine, Karol Hausman, Ofir Nachum, 2023, ArXiv.

Open-World Object Manipulation using Pre-trained Vision-Language Models

Karol Hausman, Chelsea Finn, Paul Wohlhart, 2023, ArXiv.

Diversify and Disambiguate: Out-of-Distribution Robustness via Disagreement

Chelsea Finn, Yoonho Lee, Huaxiu Yao, 2023, ICLR.

Offline Retraining for Online RL: Decoupled Policy Learning to Mitigate Exploration Bias

Archit Sharma, Chelsea Finn, Rafael Rafailov, 2023, 2310.08558.

MOPO: Model-based Offline Policy Optimization

James Y. Zou, S. Levine, Chelsea Finn, 2020, NeurIPS.

Meta-Learning Online Adaptation of Language Models

Christopher D. Manning, Chelsea Finn, Nathan J. Hu, 2023, EMNLP.

TRASS: Time Reversal as Self-Supervision

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

Permutation Equivariant Neural Functionals

J. Z. Kolter, Chelsea Finn, Yiding Jiang, 2023, ArXiv.

VideoFlow: A Conditional Flow-Based Model for Stochastic Video Generation

S. Levine, D. Erhan, Chelsea Finn, 2019, ICLR.

Disentanglement via Latent Quantization

James C. R. Whittington, Chelsea Finn, Jiajun Wu, 2023, ArXiv.

Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback

Christopher D. Manning, Archit Sharma, Chelsea Finn, 2023, EMNLP.

Fast Model Editing at Scale

Christopher D. Manning, Chelsea Finn, Antoine Bosselut, 2021, ICLR.

Giving Robots a Hand: Learning Generalizable Manipulation with Eye-in-Hand Human Video Demonstrations

Chelsea Finn, Jiajun Wu, Moo Jin Kim, 2023, ArXiv.