Sergey Levine
UC Berkeley professor and co-founder of Physical Intelligence (Pi); one of the most prolific deep-RL and robot-learning researchers.
- Role
- professor
- Currently at
- University of California, Berkeley
- twitter.com/svlevine
- Scholar
- scholar.google.com/citations
- Papers
- 57
Cite
Notes
Only stored in your browser.
Authored papers
57Q-learning with Adjoint Matching
arXiv 2026
Offline Materials Optimization with CliqueFlowmer
arXiv 2026
Diffusion Guidance Is a Controllable Policy Improvement Operator
arXiv 2025
Learning to Reason without External Rewards
arXiv 2025
Beyond Sight: Finetuning Generalist Robot Policies with Heterogeneous Sensors via Language Grounding
arXiv 2025
Digi-Q: Learning Q-Value Functions for Training Device-Control Agents
arXiv 2025
Decoupled Q-Chunking
arXiv 2025
SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks
arXiv 2025
Steering Your Generalists: Improving Robotic Foundation Models via Value Guidance
arXiv 2024
Training Diffusion Models with Reinforcement Learning
arXiv 2023
One Step Diffusion via Shortcut Models
arXiv 2024
SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning
arXiv 2024
Scaling Cross-Embodied Learning: One Policy for Manipulation, Navigation, Locomotion and Aviation
arXiv 2024
Autonomous Evaluation and Refinement of Digital Agents
arXiv 2024
Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline Data
arXiv 2024
Inference via Interpolation: Contrastive Representations Provably Enable Planning and Inference
arXiv 2024
Derivative-Free Guidance in Continuous and Discrete Diffusion Models with Soft Value-Based Decoding
arXiv 2024
Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration
arXiv 2024
Video Occupancy Models
arXiv 2024
Octo: An Open-Source Generalist Robot Policy
arXiv 2024
Evaluating Real-World Robot Manipulation Policies in Simulation
arXiv 2024
ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL
arXiv 2024
Foundation Policies with Hilbert Representations
arXiv 2024
Unsupervised Zero-Shot Reinforcement Learning via Functional Reward Encodings
arXiv 2024
Learning to Assist Humans without Inferring Rewards
arXiv 2024
Unfamiliar Finetuning Examples Control How Language Models Hallucinate
arXiv 2024
Adding Conditional Control to Diffusion Models with Reinforcement Learning
arXiv 2024
Efficient Online Reinforcement Learning with Offline Data
arXiv 2023
BridgeData V2: A Dataset for Robot Learning at Scale
arXiv 2023
LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models
arXiv 2023
Reinforcement Learning from Passive Data via Latent Intentions
arXiv 2023
Predictable MDP Abstraction for Unsupervised Model-Based RL
arXiv 2023
Accelerating Exploration with Unlabeled Prior Data
accelerating-exploration-with-unlabeled-prior
Deep Neural Networks Tend To Extrapolate Predictably
arXiv 2023
Open X-Embodiment: Robotic Learning Datasets and RT-X Models
arXiv 2023
Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Models
arXiv 2023
METRA: Scalable Unsupervised RL with Metric-Aware Abstraction
arXiv 2023
Stabilizing Contrastive RL: Techniques for Robotic Goal Reaching from Offline Data
arXiv 2023
Contrastive Example-Based Control
arXiv 2023
RT-1: Robotics Transformer for Real-World Control at Scale
arXiv 2022
Planning with Diffusion for Flexible Behavior Synthesis
arXiv 2022
LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action
arXiv 2022
Adversarial Policies Beat Superhuman Go AIs
arXiv 2022
GNM: A General Navigation Model to Drive Any Robot
arXiv 2022
Offline Reinforcement Learning as One Big Sequence Modeling Problem
NeurIPS 2021 12
Evolving Reinforcement Learning Algorithms
evolving-reinforcement-learning-algorithms
D4RL: Datasets for Deep Data-Driven Reinforcement Learning
arXiv 2020
WILDS: A Benchmark of in-the-Wild Distribution Shifts
arXiv 2020
Gradient Surgery for Multi-Task Learning
NeurIPS 2020 12
Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning
arXiv 2019
Learning Latent Plans from Play
arXiv 2019
Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
soft-actor-critic-off-policy-maximum-entropy-1
Soft Actor-Critic Algorithms and Applications
arXiv 2018
Visual Reinforcement Learning with Imagined Goals
visual-reinforcement-learning-with-imagined-1
Grasp2Vec: Learning Object Representations from Self-Supervised Grasping
arXiv 2018
Self-supervised Deep Reinforcement Learning with Generalized Computation Graphs for Robot Navigation
arXiv 2017
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
model-agnostic-meta-learning-for-fast-1
Affiliations
Frequent co-authors
10from 57 papers