---
title: "John Schulman — all works — Elamur Research"
description: "All 52 works of John Schulman in the Elamur Research library, the most cited first: our summaries where we have them, else the original."
canonical: "https://research.elamur.ai/free/en/authors/john-schulman/works/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/john-schulman/works/)

[home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / [John Schulman](https://md.research.elamur.ai/free/en/authors/john-schulman/) / all works

# John Schulman — all works

52 works · [← John Schulman](https://md.research.elamur.ai/free/en/authors/john-schulman/)

1. [**Training language models to follow instructions with human feedback arXiv:2203.02155**Long Ouyang, Jeff Wu, Xu Jiang, et al.*2022 · 10,224 citations*](https://md.research.elamur.ai/free/en/papers/ouyang-2022-training-language-models-follow-instructions/)
2. [**Training Verifiers to Solve Math Word Problems arXiv:2110.14168**Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, et al.*2021 · 3,796 citations*](https://md.research.elamur.ai/free/en/papers/cobbe-2021-training-verifiers-solve-math-word/)
3. **[Trust Region Policy Optimization ↗](https://arxiv.org/abs/1502.05477) arXiv:1502.05477 · no summary yet**John Schulman et al.*2015 · 3,015 citations*
4. **[High-Dimensional Continuous Control Using Generalized Advantage Estimation ↗](https://arxiv.org/abs/1506.02438) arXiv:1506.02438 · no summary yet**John Schulman et al.*2015 · 1,867 citations*
5. [**Let's Verify Step by Step arXiv:2305.20050**Hunter Lightman, Vineet Kosaraju, Yura Burda, et al.*2023 · 1,412 citations*](https://md.research.elamur.ai/free/en/papers/lightman-2023-let-s-verify-step-step/)
6. **[InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets ↗](https://arxiv.org/abs/1606.03657) arXiv (Cornell University) · no summary yet**Chen, Xi et al.*2016 · 1,285 citations*
7. **[Benchmarking Deep Reinforcement Learning for Continuous Control ↗](https://arxiv.org/abs/1604.06778) arXiv:1604.06778 · no summary yet**Yan Duan et al.*2016 · 967 citations*
8. **[Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations ↗](https://arxiv.org/abs/1709.10087) arXiv:1709.10087 · no summary yet**Aravind Rajeswaran et al.*2017 · 838 citations*
9. **[OpenAI Gym ↗](https://arxiv.org/abs/1606.01540) arXiv:1606.01540 · no summary yet**Greg Brockman et al.*2016 · 829 citations*
10. **[On First-Order Meta-Learning Algorithms ↗](https://arxiv.org/abs/1803.02999) arXiv:1803.02999 · no summary yet**Alex Nichol, Joshua Achiam, John Schulman*2018 · 606 citations*
11. [**RL²: Fast Reinforcement Learning via Slow Reinforcement Learning arXiv:1611.02779**Yan Duan, John Schulman, Xi Chen, et al.*2016 · 524 citations*](https://md.research.elamur.ai/free/en/papers/duan-2016-rl-2-fast-reinforcement-learning/)
12. **[VIME: Variational Information Maximizing Exploration ↗](https://arxiv.org/abs/1605.09674) arXiv:1605.09674 · no summary yet**Rein Houthooft et al.*2016 · 518 citations*
13. **[Finding Locally Optimal, Collision-Free Trajectories with Sequential Convex Optimization ↗](https://doi.org/10.15607/rss.2013.ix.031) no summary yet**John Schulman et al.*2013 · 437 citations*
14. **[Teacher-Student Curriculum Learning ↗](https://arxiv.org/abs/1707.00183) arXiv:1707.00183 · no summary yet**Tambet Matiisen et al.*2017 · 350 citations*
15. **[#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning ↗](https://arxiv.org/abs/1611.04717) arXiv (Cornell University) · no summary yet**Haoran Tang et al.*2016 · 327 citations*
16. [**Scaling Laws for Reward Model Overoptimization arXiv:2210.10760**Leo Gao, John Schulman, Jacob Hilton*2022 · 323 citations*](https://md.research.elamur.ai/free/en/papers/gao-2022-scaling-laws-reward-model-overoptimization/)
17. **[Variational Lossy Autoencoder ↗](https://arxiv.org/abs/1611.02731) arXiv (Cornell University) · no summary yet**Xi Chen et al.*2016 · 285 citations*
18. [**Concrete Problems in AI Safety arXiv:1606.06565**Dario Amodei, Chris Olah, Jacob Steinhardt, et al.*2016 · 232 citations*](https://md.research.elamur.ai/free/en/papers/amodei-2016-concrete-problems-ai-safety/)
19. **[Quantifying Generalization in Reinforcement Learning ↗](https://arxiv.org/abs/1812.02341) arXiv (Cornell University) · no summary yet**Karl Cobbe et al.*2018 · 222 citations*
20. **[Gradient Estimation Using Stochastic Computation Graphs ↗](https://arxiv.org/abs/1506.05254) arXiv (Cornell University) · no summary yet**John Schulman et al.*2015 · 216 citations*
21. **[Leveraging Procedural Generation to Benchmark Reinforcement Learning ↗](https://arxiv.org/abs/1912.01588) arXiv (Cornell University) · no summary yet**Karl Cobbe et al.*2019 · 214 citations*
22. **[Equivalence Between Policy Gradients and Soft Q-Learning ↗](https://arxiv.org/abs/1704.06440) arXiv (Cornell University) · no summary yet**John Schulman, Chen, Xi, Pieter Abbeel*2017 · 196 citations*
23. **[Tracking deformable objects with point clouds ↗](https://doi.org/10.1109/icra.2013.6630714) Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · no summary yet**John Schulman et al.*2013 · 170 citations*
24. [**Measuring short-form factuality in large language models arXiv:2411.04368**Jason Wei, Nguyen Karina, Hyung Won Chung, et al.*2024 · 160 citations*](https://md.research.elamur.ai/free/en/papers/wei-2024-measuring-short-form-factuality-large/)
25. **[Unsolved Problems in ML Safety ↗](https://arxiv.org/abs/2109.13916) arXiv:2109.13916 · no summary yet**Dan Hendrycks et al.*2021 · 151 citations*
26. [**Efficient Training of Language Models to Fill in the Middle arXiv:2207.14255**Mohammad Bavarian, Heewoo Jun, Nikolas Tezak, et al.*2022 · 144 citations*](https://md.research.elamur.ai/free/en/papers/bavarian-2022-efficient-training-language-models-fill/)
27. **[Learning from Demonstrations Through the Use of Non-rigid Registration ↗](https://doi.org/10.1007/978-3-319-28872-7_20) Springer tracts in advanced robotics · no summary yet**John Schulman et al.*2016 · 130 citations*
28. **[Meta Learning Shared Hierarchies ↗](https://arxiv.org/abs/1710.09767) arXiv (Cornell University) · no summary yet**Kevin Frans et al.*2017 · 116 citations*
29. **[Model-Based Reinforcement Learning via Meta-Policy Optimization ↗](https://arxiv.org/abs/1809.05214) arXiv (Cornell University) · no summary yet**Ignasi Clavera et al.*2018 · 112 citations*
30. **[Reasoning Models Don't Always Say What They Think ↗](https://arxiv.org/abs/2505.05410) arXiv:2505.05410 · no summary yet**Yanda Chen et al.*2025 · 106 citations*
31. **[Gotta Learn Fast: A New Benchmark for Generalization in RL ↗](https://arxiv.org/abs/1804.03720) arXiv (Cornell University) · no summary yet**Alex Nichol et al.*2018 · 93 citations*
32. **[A case study of trajectory transfer through non-rigid registration for a simplified suturing scenario ↗](https://doi.org/10.1109/iros.2013.6696945) IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · no summary yet**John Schulman et al.*2013 · 85 citations*
33. **[UCB Exploration via Q-Ensembles ↗](https://arxiv.org/abs/1706.01502) arXiv (Cornell University) · no summary yet**Richard Y. Chen et al.*2017 · 75 citations*
34. **[Scaling up Gaussian Belief Space Planning Through Covariance-Free Trajectory Optimization and Automatic Differentiation ↗](https://doi.org/10.1007/978-3-319-16595-0_30) Springer tracts in advanced robotics · no summary yet**Sachin Patil et al.*2015 · 74 citations*
35. **[Phasic Policy Gradient ↗](https://arxiv.org/abs/2009.04416) arXiv (Cornell University) · no summary yet**Karl Cobbe et al.*2020 · 56 citations*
36. **[Rule Based Rewards for Language Model Safety ↗](https://doi.org/10.52202/079017-3457) neural information processing systems · no summary yet**Tong Mu et al.*2024 · 49 citations*
37. **[Sigma hulls for Gaussian belief space planning for imprecise articulated robots amid obstacles ↗](https://doi.org/10.1109/iros.2013.6697176) IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · no summary yet**Alex Lee et al.*2013 · 42 citations*
38. **[Distribution Augmentation for Generative Modeling ↗](https://openalex.org/W3114951884) International Conference on Machine Learning · no summary yet**Heewoo Jun et al.*2020 · 30 citations*
39. **[Gaussian belief space planning with discontinuities in sensing domains ↗](https://doi.org/10.1109/icra.2014.6907816) Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · no summary yet**Sachin Patil et al.*2014 · 23 citations*
40. **[Grasping and Fixturing as Submodular Coverage Problems ↗](https://doi.org/10.1007/978-3-319-29363-9_32) Springer tracts in advanced robotics · no summary yet**John Schulman, Ken Y. Goldberg, Pieter Abbeel*2016 · 21 citations*
41. **[Scaling laws for single-agent reinforcement learning ↗](https://arxiv.org/abs/2301.13442) arXiv (Cornell University) · no summary yet**Jacob K. Hilton, Jie Tang, John Schulman*2023 · 19 citations*
42. **[Planning locally optimal, curvature-constrained trajectories in 3D using sequential convex optimization ↗](https://doi.org/10.1109/icra.2014.6907726) Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · no summary yet**Yan Duan et al.*2014 · 19 citations*
43. **[Semi-Supervised Learning by Label Gradient Alignment ↗](https://arxiv.org/abs/1902.02336) arXiv (Cornell University) · no summary yet**Jackson, Jacob, John Schulman*2019 · 16 citations*
44. **[Policy Gradient Search: Online Planning and Expert Iteration without Search Trees ↗](https://arxiv.org/abs/1904.03646) arXiv (Cornell University) · no summary yet**Anthony, Thomas et al.*2019 · 15 citations*
45. **[Batch Size-Invariance for Policy Optimization ↗](https://doi.org/10.52202/068431-1243) neural information processing systems · no summary yet**Jacob Hilton, Karl Cobbe, John Schulman*2022 · 9 citations*
46. **[Measuring Sample Efficiency and Generalization in Reinforcement Learning Benchmarks: NeurIPS 2020 Procgen Benchmark ↗](https://arxiv.org/abs/2103.15332) arXiv (Cornell University) · no summary yet**Sharada P. Mohanty et al.*2021 · 8 citations*
47. **[Stress-Testing Model Specs Reveals Character Differences among Language Models ↗](https://arxiv.org/abs/2510.07686) arXiv (Cornell University) · no summary yet**Zhang, Jifan et al.*2025 · 4 citations*
48. **[Quantifying Elicitation of Latent Capabilities in Language Models ↗](https://doi.org/10.52202/085713-5029) neural information processing systems · no summary yet**Elizabeth Donoway et al.*2025 · 1 citation*
49. **[Detecting Adversarial Fine-tuning with Auditing Agents ↗](https://arxiv.org/abs/2510.16255) arXiv (Cornell University) · no summary yet**Sarah Egler, John Schulman, Nicholas Carlini*2025 · 1 citation*
50. **[Spike sorting for large dense arrays ↗](https://doi.org/10.3389/conf.fninf.2013.08.00011) Frontiers in Neuroinformatics · no summary yet**Shabnam Kadir et al.*2013 · 1 citation*
51. **[Chunky Post-Training: Data Driven Failures of Generalization ↗](https://arxiv.org/abs/2602.05910) arXiv (Cornell University) · no summary yet**Seoirse Murray et al.*2026*
52. **[Conditional Augmentation for Generative Modeling ↗](https://openalex.org/W3035610106) International Conference on Machine Learning · no summary yet**Heewoo Jun et al.*2020*