🧑‍🔬 Sergey Levine — all works

69 works · ← Sergey Levine

1. Model-Agnostic Meta-Learning for Fast Adaptation of Deep NetworksarXiv:1703.03400Chelsea Finn, Pieter Abbeel, Sergey Levine2017 · 6,549 citations
2. Trust Region Policy Optimization ↗arXiv:1502.05477 · no summary yetJohn Schulman et al.2015 · 3,015 citations
3. High-Dimensional Continuous Control Using Generalized Advantage Estimation ↗arXiv:1506.02438 · no summary yetJohn Schulman et al.2015 · 1,867 citations
4. End-to-End Training of Deep Visuomotor Policies ↗arXiv:1504.00702 · no summary yetSergey Levine et al.2015 · 1,463 citations
5. Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations ↗arXiv:1709.10087 · no summary yetAravind Rajeswaran et al.2017 · 838 citations
6. PaLM-E: An Embodied Multimodal Language Model ↗arXiv:2303.03378 · no summary yetDanny Driess et al.2023 · 700 citations
7. Cognitive Mapping and Planning for Visual Navigation ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetSaurabh Gupta et al.2017 · 544 citations
8. Value Iteration Networks ↗arXiv:1602.02867 · Advances in Neural Information Processing Systems 29 pages 2154–2162, 2016 · no summary yetAviv Tamar et al.2016 · 489 citations
9. Deep Spatial Autoencoders for Visuomotor Learning ↗arXiv:1509.06113 · no summary yetChelsea Finn et al.2015 · 461 citations
10. Model-Based Reinforcement Learning for Atari ↗arXiv (Cornell University) · no summary yetŁukasz Kaiser et al.2019 · 429 citations
11. Sim-To-Real via Sim-To-Sim: Data-Efficient Robotic Grasping via Randomized-To-Canonical Adaptation Networks ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetStephen James et al.2019 · 414 citations
12. WILDS: A Benchmark of in-the-Wild Distribution Shifts ↗CaltechAUTHORS (California Institute of Technology) · no summary yetPang Wei Koh et al.2020 · 405 citations
13. PRECOG: PREdiction Conditioned on Goals in Visual Multi-Agent Settings ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetNicholas Rhinehart et al.2019 · 355 citations
14. Learning modular neural network policies for multi-task and multi-robot transfer ↗Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · no summary yetColine Devin et al.2017 · 328 citations
15. Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models ↗arXiv:1507.00814 · no summary yetBradly C. Stadie, Sergey Levine, Pieter Abbeel2015 · 313 citations
16. MOPO: Model-based Offline Policy Optimization ↗arXiv (Cornell University) · no summary yetTianhe Yu et al.2020 · 260 citations
17. OpenVLA: An Open-Source Vision-Language-Action Model ↗arXiv:2406.09246 · no summary yetMoo Jin Kim et al.2024 · 254 citations
18. Modular Multitask Reinforcement Learning with Policy Sketches ↗arXiv (Cornell University) · no summary yetJacob Andreas, Dan Klein, Sergey Levine2016 · 238 citations
19. Gradient Surgery for Multi-Task LearningarXiv:2001.06782Tianhe Yu, Saurabh Kumar, Abhishek Gupta, et al.2020 · 233 citations
20. Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning ↗arXiv:1910.00177 · no summary yetXue Bin Peng et al.2019 · 223 citations
21. Open X-Embodiment: Robotic Learning Datasets and RT-X Models ↗arXiv:2310.08864 · no summary yetEmbodiment Collaboration et al.2023 · 204 citations
22. The False Promise of Imitating Proprietary LLMsarXiv:2305.15717Arnav Gudibande, Eric Wallace, Charlie Snell, et al.2023 · 182 citations
23. Recasting Gradient-Based Meta-Learning as Hierarchical Bayes ↗arXiv (Cornell University) · no summary yetErin Grant et al.2018 · 165 citations
24. Model-Based Value Estimation for Efficient Model-Free Reinforcement Learning ↗arXiv (Cornell University) · no summary yetVladimir Feinberg et al.2018 · 162 citations
25. SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-trainingarXiv:2501.17161Tianzhe Chu, Yuexiang Zhai, Jihan Yang, et al.2025 · 160 citations
26. Conditional Networks for Few-Shot Semantic Segmentation ↗International Conference on Learning Representations · no summary yetKate Rakelly et al.2018 · 159 citations
27. Learning to poke by poking: experiential learning of intuitive physics ↗neural information processing systems · no summary yetPulkit Agrawal et al.2016 · 155 citations
28. Diversity is All You Need: Learning Skills without a Reward Function ↗arXiv:1802.06070 · no summary yetBenjamin Eysenbach et al.2018 · 145 citations
29. Adapting Deep Visuomotor Representations with Weak Pairwise Constraints ↗Springer proceedings in advanced robotics · no summary yetEric Tzeng et al.2015 · 124 citations
30. FAST: Efficient Action Tokenization for Vision-Language-Action ModelsarXiv:2501.09747Karl Pertsch, Kyle Stachowicz, Brian Ichter, et al.2025 · 123 citations
31. Learning with Latent Language ↗Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · no summary yetJacob Andreas, Dan Klein, Sergey Levine2018 · 121 citations
32. Backprop KF: learning discriminative deterministic state estimators ↗neural information processing systems · no summary yetTuomas Haarnoja et al.2016 · 102 citations
33. Reinforcement Learning from Imperfect Demonstrations ↗arXiv (Cornell University) · no summary yetYang Gao et al.2018 · 97 citations
34. Efficient Exploration via State Marginal Matching ↗arXiv (Cornell University) · no summary yetLisa Lee et al.2019 · 96 citations
35. Deep Object-Centric Representations for Generalizable Robot Learning ↗Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · no summary yetColine Devin et al.2018 · 95 citations
36. Few-Shot Segmentation Propagation with Guided Networks ↗arXiv (Cornell University) · no summary yetKate Rakelly et al.2018 · 95 citations
37. Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning ↗neural information processing systems · no summary yetYuexiang Zhai et al.2024 · 65 citations
38. Search on the Replay Buffer: Bridging Planning and Reinforcement Learning ↗arXiv (Cornell University) · no summary yetBenjamin Eysenbach, Ruslan Salakhutdinov, Sergey Levine2019 · 55 citations
39. ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL ↗arXiv:2402.19446 · no summary yetYifei Zhou et al.2024 · 54 citations
40. Autonomous Evaluation and Refinement of Digital Agents ↗arXiv:2404.06474 · no summary yetJiayi Pan; Yichi Zhang; Nicholas Tomlin; Yifei Zhou; Sergey Levine;, Alane Suhr2024 · 53 citations
41. Unfamiliar Finetuning Examples Control How Language Models HallucinateConference of the North American Chapter of the Association for Computational Linguistics (NAACL)Katie Kang, Eric Wallace, Claire Tomlin, et al.2025 · 47 citations
42. Learning to Reason without External Rewards ↗arXiv:2505.19590 · no summary yetXuandong Zhao et al.2025 · 44 citations
43. Learning Instance Segmentation by Interaction ↗IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · no summary yetDeepak Pathak et al.2018 · 41 citations
44. Rewriting History with Inverse RL: Hindsight Inference for Policy Improvement ↗arXiv (Cornell University) · no summary yetBenjamin Eysenbach et al.2020 · 38 citations
45. Scaling Test-Time Compute Without Verification or RL is Suboptimal ↗arXiv:2502.12118 · no summary yetAmrith Setlur et al.2025 · 26 citations
46. C-Learning: Learning to Achieve Goals via Recursive Classification ↗arXiv (Cornell University) · no summary yetBenjamin Eysenbach, Ruslan Salakhutdinov, Sergey Levine2020 · 24 citations
47. Evolving Reinforcement Learning Algorithms ↗arXiv (Cornell University) · no summary yetJohn D. Co-Reyes et al.2021 · 22 citations
48. PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs ↗arXiv (Cornell University) · no summary yetSoroush Nasiriany et al.2024 · 21 citations
49. Extending the WILDS Benchmark for Unsupervised Adaptation ↗arXiv (Cornell University) · no summary yetShiori Sagawa et al.2021 · 18 citations
50. Zero-Shot Goal-Directed Dialogue via RL on Imagined Conversations ↗arXiv:2311.05584 · no summary yetJoey Hong, Sergey Levine, Anca Dragan2023 · 15 citations
51. Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers ↗arXiv (Cornell University) · no summary yetBenjamin Eysenbach et al.2020 · 12 citations
52. Robust Predictable Control ↗arXiv (Cornell University) · no summary yetBenjamin Eysenbach, Ruslan Salakhutdinov, Sergey Levine2021 · 11 citations
53. Predicting Emergent Capabilities by Finetuning ↗arXiv (Cornell University) · no summary yetCharlie Snell et al.2024 · 8 citations
54. C-Planning: An Automatic Curriculum for Learning Goal-Reaching Tasks ↗arXiv (Cornell University) · no summary yetTianjun Zhang et al.2021 · 7 citations
55. Compositional Plan Vectors ↗neural information processing systems · no summary yetColine Devin et al.2019 · 7 citations
56. RoboReward: General-Purpose Vision-Language Reward Models for Robotics ↗arXiv (Cornell University) · no summary yetTony Lee et al.2026 · 6 citations
57. Replacing Rewards with Examples: Example-Based Policy Search via Recursive Classification ↗arXiv (Cornell University) · no summary yetBenjamin Eysenbach, Sergey Levine, Ruslan Salakhutdinov2021 · 6 citations
58. What Do Learning Dynamics Reveal About Generalization in LLM Reasoning? ↗arXiv (Cornell University) · no summary yetKatie Kang et al.2024 · 4 citations
59. Stabilizing Contrastive RL: Techniques for Robotic Goal Reaching from Offline Data ↗arXiv (Cornell University) · no summary yetChongyi Zheng et al.2023 · 4 citations
60. Hierarchical Deep Reinforcement Learning Agent with Counter Self-play on Competitive Games ↗no summary yetHuazhe Xu et al.2018 · 4 citations
61. Inference via Interpolation: Contrastive Representations Provably Enable Planning and Inference ↗neural information processing systems · no summary yetBenjamin Eysenbach et al.2024 · 3 citations
62. Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objective ↗arXiv (Cornell University) · no summary yetRaj Ghugare et al.2022 · 3 citations
63. Meta-Learning to Guide Segmentation ↗no summary yetKate Rakelly et al.2018 · 3 citations
64. The Information Geometry of Unsupervised Reinforcement Learning ↗arXiv (Cornell University) · no summary yetBenjamin Eysenbach, Ruslan Salakhutdinov, Sergey Levine2021 · 2 citations
65. A Connection between One-Step Regularization and Critic Regularization in Reinforcement Learning ↗arXiv (Cornell University) · no summary yetBenjamin Eysenbach et al.2023 · 1 citation
66. Plan Arithmetic: Compositional Plan Vectors for Multi-Task Control ↗arXiv (Cornell University) · no summary yetColine Devin et al.2019 · 1 citation
67. One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL ↗arXiv (Cornell University) · no summary yetSu Yu et al.2026
68. Contrastive Example-Based Control ↗arXiv (Cornell University) · no summary yetKyle Hatch et al.2023
69. End-toend training of deep visuomotor policies. arXiv preprint arXiv:1504.00702 ↗no summary yetSergey Levine et al.2015

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/sergey-levine/works/