S. Gu

发表

Categorical Reparameterization with Gumbel-Softmax pdf

Ben Poole, Shixiang Gu, Eric Jang, 2016, ICLR.

Dynamics-Aware Unsupervised Discovery of Skills pdf

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

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

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

Continuous Deep Q-Learning with Model-based Acceleration pdf

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

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).

Data-Efficient Hierarchical Reinforcement Learning

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

Deep Reinforcement Learning for Robotic Manipulation pdf

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

Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog pdf

Natasha Jaques, Rosalind W. Picard, Shixiang Gu, 2019, ArXiv.

Neural Adaptive Sequential Monte Carlo

Richard E. Turner, Zoubin Ghahramani, Shixiang Gu, 2015, NIPS.

Language as an Abstraction for Hierarchical Deep Reinforcement Learning

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

Sequence Tutor: Conservative Fine-Tuning of Sequence Generation Models with KL-control

Richard E. Turner, Natasha Jaques, José Miguel Hernández-Lobato, 2016, ICML.

Tuning Recurrent Neural Networks with Reinforcement Learning pdf

Douglas Eck, Richard E. Turner, Natasha Jaques, 2016, ICLR.

OFFLINE HINDSIGHT INFORMATION MATCHING

S. Gu, Hiroki Furuta, Yutaka Matsuo, 2022 .

Way Off-Policy Batch Deep Reinforcement Learning of Human Preferences in Dialog

Natasha Jaques, Àgata Lapedriza, Rosalind W. Picard, 2019 .

Categorical Reparametrization with Gumble-Softmax

Ben Poole, Shixiang Gu, Eric Jang, 2017, ICLR 2017.

C ATEGORICAL R EPARAMETERIZATION WITH G UMBEL -S OFTMAX

Eric Jang, S. Gu, 2017 .

Large Language Models are Zero-Shot Reasoners

S. Gu, Yusuke Iwasawa, Yutaka Matsuo, 2022, 2205.11916.

ING VIA MODEL-BASED OFFLINE OPTIMIZATION

S. Gu, Ofir Nachum, Hiroki Furuta, 2021 .

Why Should I Trust You, Bellman? The Bellman Error is a Poor Replacement for Value Error

S. Gu, Doina Precup, Ofir Nachum, 2022, ICML.

Large Language Models are Zero-Shot Reasoners

S. Gu, Yusuke Iwasawa, Yutaka Matsuo, 2022, ArXiv.

Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models

Gerard de Melo, Andrew M. Dai, Christopher D. Manning, 2022, ArXiv.

Can Wikipedia Help Offline Reinforcement Learning?

S. Gu, Yutaro Yamada, Machel Reid, 2022, ArXiv.

World robot challenge 2020 – partner robot: a data-driven approach for room tidying with mobile manipulator

S. Gu, Yusuke Iwasawa, Yutaka Matsuo, 2022, Adv. Robotics.

Domain Prompt Learning for Efficiently Adapting CLIP to Unseen Domains

S. Gu, Yusuke Iwasawa, Yutaka Matsuo, 2021, Transactions of the Japanese Society for Artificial Intelligence.

Large Language Models are Zero-Shot Reasoners

S. Gu, Yusuke Iwasawa, Yutaka Matsuo, 2022, ArXiv.

Mind's Eye: Grounded Language Model Reasoning through Simulation

Andrew M. Dai, S. Gu, Denny Zhou, 2022, ICLR.

TRL: Discriminative Hints for Scalable Reverse Curriculum Learning

Chen Wang, Cewu Lu, Jialu Wang, 2018 .

Scaling Instruction-Finetuned Language Models

Andrew M. Dai, Hyung Won Chung, J. Dean, 2022, ArXiv.

Large Language Models Can Self-Improve

S. Gu, Yuexin Wu, Jiawei Han, 2022, 2210.11610.

Scaling Instruction-Finetuned Language Models

Andrew M. Dai, Hyung Won Chung, J. Dean, 2022, ArXiv.

Large Language Models Can Self-Improve

S. Gu, Xuezhi Wang, Hongkun Yu, 2022, EMNLP.

Scaling Instruction-Finetuned Language Models

Andrew M. Dai, Hyung Won Chung, J. Dean, 2022, ArXiv.

A System for Morphology-Task Generalization via Unified Representation and Behavior Distillation

S. Gu, Yusuke Iwasawa, Hiroki Furuta, 2022, ArXiv.

Collective Intelligence for Object Manipulation with Mobile Robots

S. Gu, Yutaka Matsuo, T. Matsushima, 2022, ArXiv.

Deployment-Efficient Reinforcement Learning via Model-Based Offline Optimization pdf

Yutaka Matsuo, Tatsuya Matsushima, Ofir Nachum, 2020, ICLR.

A Divergence Minimization Perspective on Imitation Learning Methods

Richard Zemel, Seyed Kamyar Seyed Ghasemipour, Shixiang Gu, 2019, CoRL.

Large Language Models are Zero-Shot Reasoners

S. Gu, Yusuke Iwasawa, Yutaka Matsuo, 2022, NeurIPS.

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

S. Levine, S. Gu, Honglak Lee, 2019, ArXiv.

A Minimalist Approach to Offline Reinforcement Learning pdf

Scott Fujimoto, Shixiang Shane Gu, S. Gu, 2021, NeurIPS.

EMaQ: Expected-Max Q-Learning Operator for Simple Yet Effective Offline and Online RL pdf

Seyed Kamyar Seyed Ghasemipour, Dale Schuurmans, Shixiang Shane Gu, 2020, ICML.

Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning

Tatsuya Matsushima, Tadashi Kozuno, Shixiang Shane Gu, 2021, NeurIPS.

Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning pdf

Yutaka Matsuo, Tatsuya Matsushima, Tadashi Kozuno, 2021, NeurIPS.

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

Karol Hausman, Sergey Levine, Vikash Kumar, 2020, Robotics: Science and Systems.

Variational Empowerment as Representation Learning for Goal-Conditioned Reinforcement Learning

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

A System for Morphology-Task Generalization via Unified Representation and Behavior Distillation

S. Gu, Yusuke Iwasawa, Hiroki Furuta, 2022, ICLR.

Near-Optimal Representation Learning for Hierarchical Reinforcement Learning pdf

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

Aligning Text-to-Image Models using Human Feedback

P. Abbeel, S. Gu, M. Ghavamzadeh, 2023, ArXiv.

Bi-Manual Block Assembly via Sim-to-Real Reinforcement Learning

Seyed Kamyar Seyed Ghasemipour, S. Gu, Igor Mordatch, 2023, ArXiv.

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

S. Levine, S. Gu, Ofir Nachum, 2021, ICML.

Towards Deep Neural Network Architectures Robust to Adversarial Examples pdf

Luca Rigazio, Shixiang Gu, S. Gu, 2014, ICLR.

MuProp: Unbiased Backpropagation for Stochastic Neural Networks pdf

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

Amortized Prompt: Guide CLIP to Domain Transfer Learning

S. Gu, Yusuke Iwasawa, Yutaka Matsuo, 2022 .

SMILe: Scalable Meta Inverse Reinforcement Learning through Context-Conditional Policies

Richard S. Zemel, Seyed Kamyar Seyed Ghasemipour, Shixiang Gu, 2019, NeurIPS.

Doubly Reparameterized Gradient Estimators for Monte Carlo Objectives pdf

George Tucker, Chris J. Maddison, Shixiang Gu, 2019, ICLR.

Generalized Decision Transformer for Offline Hindsight Information Matching

S. Gu, Y. Matsuo, Hiroki Furuta, 2021, ICLR.

Generating Music by Fine-Tuning Recurrent Neural Networks with Reinforcement Learning

Douglas Eck, Richard E. Turner, Natasha Jaques, 2016 .

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

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

Learning a Universal Human Prior for Dexterous Manipulation from Human Preference

Allen Z. Ren, S. Gu, Chi Jin, 2023, ArXiv.

Human-centric Dialog Training via Offline Reinforcement Learning pdf

Natasha Jaques, Craig Ferguson, Rosalind Picard, 2020, EMNLP.

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

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

Multi-Agent Manipulation via Locomotion using Hierarchical Sim2Real pdf

Vikash Kumar, Ofir Nachum, Hugo Ponte, 2019, CoRL.

Weakly-Supervised Reinforcement Learning for Controllable Behavior pdf

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

Multimodal Web Navigation with Instruction-Finetuned Foundation Models

S. Gu, Ofir Nachum, Izzeddin Gur, 2023, ArXiv.

Braxlines: Fast and Interactive Toolkit for RL-driven Behavior Engineering beyond Reward Maximization pdf

Olivier Bachem, Seyed Kamyar Seyed Ghasemipour, Erwin Coumans, 2021, ArXiv.

Blocks Assemble! Learning to Assemble with Large-Scale Structured Reinforcement Learning

Seyed Kamyar Seyed Ghasemipour, S. Gu, Igor Mordatch, 2022, ICML.

Why So Pessimistic? Estimating Uncertainties for Offline RL through Ensembles, and Why Their Independence Matters

Seyed Kamyar Seyed Ghasemipour, S. Gu, Ofir Nachum, 2022, NeurIPS.

Interpolated Policy Gradient: Merging On-Policy and Off-Policy Gradient Estimation for Deep Reinforcement Learning

Richard E. Turner, Zoubin Ghahramani, Bernhard Scholkopf, 2017, NIPS.

INSTRUCTION-FINETUNED FOUNDATION MODELS FOR MULTIMODAL WEB NAVIGATION

S. Gu, Ofir Nachum, Hiroki Furuta, 2023 .

Realtime HDR (High Dynamic Range) video for eyetap wearable computers, FPGA-based seeing aids, and glasseyes (EyeTaps)

Steve Mann, Kalin Ovtcharov, Shixiang Gu, 2012, 2012 25th IEEE Canadian Conference on Electrical and Computer Engineering (CCECE).

The Mirage of Action-Dependent Baselines in Reinforcement Learning pdf

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

DreamSparse: Escaping from Plato's Cave with 2D Frozen Diffusion Model Given Sparse Views

S. Gu, Paul Yoo, Jiaxian Guo, 2023, NeurIPS.

Doubly Reparameterized Gradient Estimators for Monte Carlo Objectives

Chris J. Maddison, S. Gu, G. Tucker, 2018, ArXiv.

Immersive Real World through Deep Billboards

S. Gu, Yoichi Ochiai, Yutaka Matsuo, 2022, Special Interest Group on Computer Graphics and Interactive Techniques Conference Immersive Pavilion.

Amortized Prompt: Lightweight Fine-Tuning for CLIP in Domain Generalization

Yutaka Matsuo, Yusuke Iwasawa, Shixiang Shane Gu, 2021, ArXiv.

Dynamics-Aware Unsupervised Skill Discovery

Karol Hausman, Sergey Levine, Vikash Kumar, 2020, ICLR 2020.

Sample-efficient deep reinforcement learning for continuous control

Shixiang Gu, S. Gu, 2019 .

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

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

Tool as Embodiment for Recursive Manipulation pdf

Tatsuya Matsushima, Shixiang Shane Gu, Yutaka Matsuo, 2021, ArXiv.

Learning a Universal Human Prior for Dexterous Manipulation from Human Preference

Allen Z. Ren, S. Gu, Chi Jin, 2023, ArXiv.

Collective Intelligence for 2D Push Manipulations With Mobile Robots

S. Gu, Hiroki Furuta, Yutaka Matsuo, 2022, IEEE Robotics and Automation Letters.

For SALE: State-Action Representation Learning for Deep Reinforcement Learning

S. Gu, Doina Precup, D. Meger, 2023, ArXiv.

Scaling Instruction-Finetuned Language Models

Andrew M. Dai, Adams Wei Yu, Hyung Won Chung, 2022, ArXiv.

EMaQ: Expected-Max Q-Learning Operator for Simple Yet Effective Offline and Online RL

Seyed Kamyar Seyed Ghasemipour, Dale Schuurmans, Shixiang Shane Gu, 2020, ICML.

Multimodal Web Navigation with Instruction-Finetuned Foundation Models

S. Gu, Ofir Nachum, Izzeddin Gur, 2023, ICLR.

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

S. Levine, S. Gu, Benjamin Eysenbach, 2017, ICLR.

World robot challenge 2020 – partner robot: a data-driven approach for room tidying with mobile manipulator

S. Gu, Yusuke Iwasawa, Yutaka Matsuo, 2022, Adv. Robotics.