default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDBibTeX records: John Schulman
@inproceedings{DBLP:conf/iclr/LightmanKBEBLLS24,
author = {Hunter Lightman and
Vineet Kosaraju and
Yuri Burda and
Harrison Edwards and
Bowen Baker and
Teddy Lee and
Jan Leike and
John Schulman and
Ilya Sutskever and
Karl Cobbe},
title = {Let's Verify Step by Step},
booktitle = {The Twelfth International Conference on Learning Representations,
{ICLR} 2024, Vienna, Austria, May 7-11, 2024},
publisher = {OpenReview.net},
year = {2024},
url = {https://openreview.net/forum?id=v8L0pN6EOi},
timestamp = {Wed, 07 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iclr/LightmanKBEBLLS24.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/GaoSH23,
author = {Leo Gao and
John Schulman and
Jacob Hilton},
editor = {Andreas Krause and
Emma Brunskill and
Kyunghyun Cho and
Barbara Engelhardt and
Sivan Sabato and
Jonathan Scarlett},
title = {Scaling Laws for Reward Model Overoptimization},
booktitle = {International Conference on Machine Learning, {ICML} 2023, 23-29 July
2023, Honolulu, Hawaii, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {202},
pages = {10835--10866},
publisher = {{PMLR}},
year = {2023},
url = {https://proceedings.mlr.press/v202/gao23h.html},
timestamp = {Mon, 28 Aug 2023 17:23:08 +0200},
biburl = {https://dblp.org/rec/conf/icml/GaoSH23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2301-13442,
author = {Jacob Hilton and
Jie Tang and
John Schulman},
title = {Scaling laws for single-agent reinforcement learning},
journal = {CoRR},
volume = {abs/2301.13442},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2301.13442},
doi = {10.48550/ARXIV.2301.13442},
eprinttype = {arXiv},
eprint = {2301.13442},
timestamp = {Thu, 02 Feb 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2301-13442.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2305-20050,
author = {Hunter Lightman and
Vineet Kosaraju and
Yura Burda and
Harri Edwards and
Bowen Baker and
Teddy Lee and
Jan Leike and
John Schulman and
Ilya Sutskever and
Karl Cobbe},
title = {Let's Verify Step by Step},
journal = {CoRR},
volume = {abs/2305.20050},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2305.20050},
doi = {10.48550/ARXIV.2305.20050},
eprinttype = {arXiv},
eprint = {2305.20050},
timestamp = {Tue, 20 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2305-20050.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/HiltonCS22,
author = {Jacob Hilton and
Karl Cobbe and
John Schulman},
editor = {Sanmi Koyejo and
S. Mohamed and
A. Agarwal and
Danielle Belgrave and
K. Cho and
A. Oh},
title = {Batch size-invariance for policy optimization},
booktitle = {Advances in Neural Information Processing Systems 35: Annual Conference
on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans,
LA, USA, November 28 - December 9, 2022},
year = {2022},
url = {http://papers.nips.cc/paper\_files/paper/2022/hash/6ceb6c2150bbf46fd75528a6cd6be793-Abstract-Conference.html},
timestamp = {Mon, 08 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/HiltonCS22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/Ouyang0JAWMZASR22,
author = {Long Ouyang and
Jeffrey Wu and
Xu Jiang and
Diogo Almeida and
Carroll L. Wainwright and
Pamela Mishkin and
Chong Zhang and
Sandhini Agarwal and
Katarina Slama and
Alex Ray and
John Schulman and
Jacob Hilton and
Fraser Kelton and
Luke Miller and
Maddie Simens and
Amanda Askell and
Peter Welinder and
Paul F. Christiano and
Jan Leike and
Ryan Lowe},
editor = {Sanmi Koyejo and
S. Mohamed and
A. Agarwal and
Danielle Belgrave and
K. Cho and
A. Oh},
title = {Training language models to follow instructions with human feedback},
booktitle = {Advances in Neural Information Processing Systems 35: Annual Conference
on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans,
LA, USA, November 28 - December 9, 2022},
year = {2022},
url = {http://papers.nips.cc/paper\_files/paper/2022/hash/b1efde53be364a73914f58805a001731-Abstract-Conference.html},
timestamp = {Mon, 08 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/Ouyang0JAWMZASR22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2203-02155,
author = {Long Ouyang and
Jeff Wu and
Xu Jiang and
Diogo Almeida and
Carroll L. Wainwright and
Pamela Mishkin and
Chong Zhang and
Sandhini Agarwal and
Katarina Slama and
Alex Ray and
John Schulman and
Jacob Hilton and
Fraser Kelton and
Luke Miller and
Maddie Simens and
Amanda Askell and
Peter Welinder and
Paul F. Christiano and
Jan Leike and
Ryan Lowe},
title = {Training language models to follow instructions with human feedback},
journal = {CoRR},
volume = {abs/2203.02155},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2203.02155},
doi = {10.48550/ARXIV.2203.02155},
eprinttype = {arXiv},
eprint = {2203.02155},
timestamp = {Sat, 21 Oct 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2203-02155.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2207-14255,
author = {Mohammad Bavarian and
Heewoo Jun and
Nikolas Tezak and
John Schulman and
Christine McLeavey and
Jerry Tworek and
Mark Chen},
title = {Efficient Training of Language Models to Fill in the Middle},
journal = {CoRR},
volume = {abs/2207.14255},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2207.14255},
doi = {10.48550/ARXIV.2207.14255},
eprinttype = {arXiv},
eprint = {2207.14255},
timestamp = {Thu, 25 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2207-14255.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2210-10760,
author = {Leo Gao and
John Schulman and
Jacob Hilton},
title = {Scaling Laws for Reward Model Overoptimization},
journal = {CoRR},
volume = {abs/2210.10760},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2210.10760},
doi = {10.48550/ARXIV.2210.10760},
eprinttype = {arXiv},
eprint = {2210.10760},
timestamp = {Mon, 28 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2210-10760.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/CobbeHKS21,
author = {Karl Cobbe and
Jacob Hilton and
Oleg Klimov and
John Schulman},
editor = {Marina Meila and
Tong Zhang},
title = {Phasic Policy Gradient},
booktitle = {Proceedings of the 38th International Conference on Machine Learning,
{ICML} 2021, 18-24 July 2021, Virtual Event},
series = {Proceedings of Machine Learning Research},
volume = {139},
pages = {2020--2027},
publisher = {{PMLR}},
year = {2021},
url = {http://proceedings.mlr.press/v139/cobbe21a.html},
timestamp = {Wed, 25 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/CobbeHKS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2101-11071,
author = {William H. Guss and
Mario Ynocente Castro and
Sam Devlin and
Brandon Houghton and
Noboru Sean Kuno and
Crissman Loomis and
Stephanie Milani and
Sharada P. Mohanty and
Keisuke Nakata and
Ruslan Salakhutdinov and
John Schulman and
Shinya Shiroshita and
Nicholay Topin and
Avinash Ummadisingu and
Oriol Vinyals},
title = {The MineRL 2020 Competition on Sample Efficient Reinforcement Learning
using Human Priors},
journal = {CoRR},
volume = {abs/2101.11071},
year = {2021},
url = {https://arxiv.org/abs/2101.11071},
eprinttype = {arXiv},
eprint = {2101.11071},
timestamp = {Sun, 31 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2101-11071.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2103-15332,
author = {Sharada P. Mohanty and
Jyotish Poonganam and
Adrien Gaidon and
Andrey Kolobov and
Blake Wulfe and
Dipam Chakraborty and
Grazvydas Semetulskis and
Jo{\~{a}}o Schapke and
Jonas Kubilius and
Jurgis Pasukonis and
Linas Klimas and
Matthew J. Hausknecht and
Patrick MacAlpine and
Quang Nhat Tran and
Thomas Tumiel and
Xiaocheng Tang and
Xinwei Chen and
Christopher Hesse and
Jacob Hilton and
William Hebgen Guss and
Sahika Genc and
John Schulman and
Karl Cobbe},
title = {Measuring Sample Efficiency and Generalization in Reinforcement Learning
Benchmarks: NeurIPS 2020 Procgen Benchmark},
journal = {CoRR},
volume = {abs/2103.15332},
year = {2021},
url = {https://arxiv.org/abs/2103.15332},
eprinttype = {arXiv},
eprint = {2103.15332},
timestamp = {Wed, 07 Apr 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2103-15332.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2109-13916,
author = {Dan Hendrycks and
Nicholas Carlini and
John Schulman and
Jacob Steinhardt},
title = {Unsolved Problems in {ML} Safety},
journal = {CoRR},
volume = {abs/2109.13916},
year = {2021},
url = {https://arxiv.org/abs/2109.13916},
eprinttype = {arXiv},
eprint = {2109.13916},
timestamp = {Mon, 04 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2109-13916.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2110-00641,
author = {Jacob Hilton and
Karl Cobbe and
John Schulman},
title = {Batch size-invariance for policy optimization},
journal = {CoRR},
volume = {abs/2110.00641},
year = {2021},
url = {https://arxiv.org/abs/2110.00641},
eprinttype = {arXiv},
eprint = {2110.00641},
timestamp = {Fri, 08 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2110-00641.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2110-14168,
author = {Karl Cobbe and
Vineet Kosaraju and
Mohammad Bavarian and
Mark Chen and
Heewoo Jun and
Lukasz Kaiser and
Matthias Plappert and
Jerry Tworek and
Jacob Hilton and
Reiichiro Nakano and
Christopher Hesse and
John Schulman},
title = {Training Verifiers to Solve Math Word Problems},
journal = {CoRR},
volume = {abs/2110.14168},
year = {2021},
url = {https://arxiv.org/abs/2110.14168},
eprinttype = {arXiv},
eprint = {2110.14168},
timestamp = {Mon, 12 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2110-14168.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2112-09332,
author = {Reiichiro Nakano and
Jacob Hilton and
Suchir Balaji and
Jeff Wu and
Long Ouyang and
Christina Kim and
Christopher Hesse and
Shantanu Jain and
Vineet Kosaraju and
William Saunders and
Xu Jiang and
Karl Cobbe and
Tyna Eloundou and
Gretchen Krueger and
Kevin Button and
Matthew Knight and
Benjamin Chess and
John Schulman},
title = {WebGPT: Browser-assisted question-answering with human feedback},
journal = {CoRR},
volume = {abs/2112.09332},
year = {2021},
url = {https://arxiv.org/abs/2112.09332},
eprinttype = {arXiv},
eprint = {2112.09332},
timestamp = {Mon, 03 Jan 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2112-09332.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tnn/MatiisenOCS20,
author = {Tambet Matiisen and
Avital Oliver and
Taco Cohen and
John Schulman},
title = {Teacher-Student Curriculum Learning},
journal = {{IEEE} Trans. Neural Networks Learn. Syst.},
volume = {31},
number = {9},
pages = {3732--3740},
year = {2020},
url = {https://doi.org/10.1109/TNNLS.2019.2934906},
doi = {10.1109/TNNLS.2019.2934906},
timestamp = {Sun, 11 Oct 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tnn/MatiisenOCS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/CobbeHHS20,
author = {Karl Cobbe and
Christopher Hesse and
Jacob Hilton and
John Schulman},
title = {Leveraging Procedural Generation to Benchmark Reinforcement Learning},
booktitle = {Proceedings of the 37th International Conference on Machine Learning,
{ICML} 2020, 13-18 July 2020, Virtual Event},
series = {Proceedings of Machine Learning Research},
volume = {119},
pages = {2048--2056},
publisher = {{PMLR}},
year = {2020},
url = {http://proceedings.mlr.press/v119/cobbe20a.html},
timestamp = {Tue, 15 Dec 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icml/CobbeHHS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/JunCCSRRS20,
author = {Heewoo Jun and
Rewon Child and
Mark Chen and
John Schulman and
Aditya Ramesh and
Alec Radford and
Ilya Sutskever},
title = {Distribution Augmentation for Generative Modeling},
booktitle = {Proceedings of the 37th International Conference on Machine Learning,
{ICML} 2020, 13-18 July 2020, Virtual Event},
series = {Proceedings of Machine Learning Research},
volume = {119},
pages = {5006--5019},
publisher = {{PMLR}},
year = {2020},
url = {http://proceedings.mlr.press/v119/jun20a.html},
timestamp = {Thu, 25 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/JunCCSRRS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/MohantyPGKWCSSK20,
author = {Sharada P. Mohanty and
Jyotish Poonganam and
Adrien Gaidon and
Andrey Kolobov and
Blake Wulfe and
Dipam Chakraborty and
Grazvydas Semetulskis and
Jo{\~{a}}o Schapke and
Jonas Kubilius and
Jurgis Pasukonis and
Linas Klimas and
Matthew J. Hausknecht and
Patrick MacAlpine and
Quang Nhat Tran and
Thomas Tumiel and
Xiaocheng Tang and
Xinwei Chen and
Christopher Hesse and
Jacob Hilton and
William Hebgen Guss and
Sahika Genc and
John Schulman and
Karl Cobbe},
editor = {Hugo Jair Escalante and
Katja Hofmann},
title = {Measuring Sample Efficiency and Generalization in Reinforcement Learning
Benchmarks: NeurIPS 2020 Procgen Benchmark},
booktitle = {NeurIPS 2020 Competition and Demonstration Track, 6-12 December 2020,
Virtual Event / Vancouver, BC, Canada},
series = {Proceedings of Machine Learning Research},
volume = {133},
pages = {361--395},
publisher = {{PMLR}},
year = {2020},
url = {http://proceedings.mlr.press/v133/mohanty21a.html},
timestamp = {Wed, 25 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/MohantyPGKWCSSK20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2009-04416,
author = {Karl Cobbe and
Jacob Hilton and
Oleg Klimov and
John Schulman},
title = {Phasic Policy Gradient},
journal = {CoRR},
volume = {abs/2009.04416},
year = {2020},
url = {https://arxiv.org/abs/2009.04416},
eprinttype = {arXiv},
eprint = {2009.04416},
timestamp = {Thu, 17 Sep 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2009-04416.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-14701,
author = {Tom Henighan and
Jared Kaplan and
Mor Katz and
Mark Chen and
Christopher Hesse and
Jacob Jackson and
Heewoo Jun and
Tom B. Brown and
Prafulla Dhariwal and
Scott Gray and
Chris Hallacy and
Benjamin Mann and
Alec Radford and
Aditya Ramesh and
Nick Ryder and
Daniel M. Ziegler and
John Schulman and
Dario Amodei and
Sam McCandlish},
title = {Scaling Laws for Autoregressive Generative Modeling},
journal = {CoRR},
volume = {abs/2010.14701},
year = {2020},
url = {https://arxiv.org/abs/2010.14701},
eprinttype = {arXiv},
eprint = {2010.14701},
timestamp = {Thu, 25 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2010-14701.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/CobbeKHKS19,
author = {Karl Cobbe and
Oleg Klimov and
Christopher Hesse and
Taehoon Kim and
John Schulman},
editor = {Kamalika Chaudhuri and
Ruslan Salakhutdinov},
title = {Quantifying Generalization in Reinforcement Learning},
booktitle = {Proceedings of the 36th International Conference on Machine Learning,
{ICML} 2019, 9-15 June 2019, Long Beach, California, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {97},
pages = {1282--1289},
publisher = {{PMLR}},
year = {2019},
url = {http://proceedings.mlr.press/v97/cobbe19a.html},
timestamp = {Tue, 11 Jun 2019 15:37:38 +0200},
biburl = {https://dblp.org/rec/conf/icml/CobbeKHKS19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1902-02336,
author = {Jacob Jackson and
John Schulman},
title = {Semi-Supervised Learning by Label Gradient Alignment},
journal = {CoRR},
volume = {abs/1902.02336},
year = {2019},
url = {http://arxiv.org/abs/1902.02336},
eprinttype = {arXiv},
eprint = {1902.02336},
timestamp = {Tue, 21 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1902-02336.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1904-03646,
author = {Thomas Anthony and
Robert Nishihara and
Philipp Moritz and
Tim Salimans and
John Schulman},
title = {Policy Gradient Search: Online Planning and Expert Iteration without
Search Trees},
journal = {CoRR},
volume = {abs/1904.03646},
year = {2019},
url = {http://arxiv.org/abs/1904.03646},
eprinttype = {arXiv},
eprint = {1904.03646},
timestamp = {Wed, 28 Sep 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1904-03646.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1912-01588,
author = {Karl Cobbe and
Christopher Hesse and
Jacob Hilton and
John Schulman},
title = {Leveraging Procedural Generation to Benchmark Reinforcement Learning},
journal = {CoRR},
volume = {abs/1912.01588},
year = {2019},
url = {http://arxiv.org/abs/1912.01588},
eprinttype = {arXiv},
eprint = {1912.01588},
timestamp = {Thu, 02 Jan 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1912-01588.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/corl/ClaveraRS0AA18,
author = {Ignasi Clavera and
Jonas Rothfuss and
John Schulman and
Yasuhiro Fujita and
Tamim Asfour and
Pieter Abbeel},
title = {Model-Based Reinforcement Learning via Meta-Policy Optimization},
booktitle = {2nd Annual Conference on Robot Learning, CoRL 2018, Z{\"{u}}rich,
Switzerland, 29-31 October 2018, Proceedings},
series = {Proceedings of Machine Learning Research},
volume = {87},
pages = {617--629},
publisher = {{PMLR}},
year = {2018},
url = {http://proceedings.mlr.press/v87/clavera18a.html},
timestamp = {Wed, 03 Apr 2019 18:17:24 +0200},
biburl = {https://dblp.org/rec/conf/corl/ClaveraRS0AA18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/FransH0AS18,
author = {Kevin Frans and
Jonathan Ho and
Xi Chen and
Pieter Abbeel and
John Schulman},
title = {Meta Learning Shared Hierarchies},
booktitle = {6th International Conference on Learning Representations, {ICLR} 2018,
Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings},
publisher = {OpenReview.net},
year = {2018},
url = {https://openreview.net/forum?id=SyX0IeWAW},
timestamp = {Thu, 25 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iclr/FransH0AS18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/rss/RajeswaranKGVST18,
author = {Aravind Rajeswaran and
Vikash Kumar and
Abhishek Gupta and
Giulia Vezzani and
John Schulman and
Emanuel Todorov and
Sergey Levine},
editor = {Hadas Kress{-}Gazit and
Siddhartha S. Srinivasa and
Tom Howard and
Nikolay Atanasov},
title = {Learning Complex Dexterous Manipulation with Deep Reinforcement Learning
and Demonstrations},
booktitle = {Robotics: Science and Systems XIV, Carnegie Mellon University, Pittsburgh,
Pennsylvania, USA, June 26-30, 2018},
year = {2018},
url = {http://www.roboticsproceedings.org/rss14/p49.html},
doi = {10.15607/RSS.2018.XIV.049},
timestamp = {Fri, 04 Aug 2023 08:25:46 +0200},
biburl = {https://dblp.org/rec/conf/rss/RajeswaranKGVST18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1803-02999,
author = {Alex Nichol and
Joshua Achiam and
John Schulman},
title = {On First-Order Meta-Learning Algorithms},
journal = {CoRR},
volume = {abs/1803.02999},
year = {2018},
url = {http://arxiv.org/abs/1803.02999},
eprinttype = {arXiv},
eprint = {1803.02999},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1803-02999.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1804-03720,
author = {Alex Nichol and
Vicki Pfau and
Christopher Hesse and
Oleg Klimov and
John Schulman},
title = {Gotta Learn Fast: {A} New Benchmark for Generalization in {RL}},
journal = {CoRR},
volume = {abs/1804.03720},
year = {2018},
url = {http://arxiv.org/abs/1804.03720},
eprinttype = {arXiv},
eprint = {1804.03720},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1804-03720.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1809-05214,
author = {Ignasi Clavera and
Jonas Rothfuss and
John Schulman and
Yasuhiro Fujita and
Tamim Asfour and
Pieter Abbeel},
title = {Model-Based Reinforcement Learning via Meta-Policy Optimization},
journal = {CoRR},
volume = {abs/1809.05214},
year = {2018},
url = {http://arxiv.org/abs/1809.05214},
eprinttype = {arXiv},
eprint = {1809.05214},
timestamp = {Sun, 14 Oct 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1809-05214.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1812-02341,
author = {Karl Cobbe and
Oleg Klimov and
Christopher Hesse and
Taehoon Kim and
John Schulman},
title = {Quantifying Generalization in Reinforcement Learning},
journal = {CoRR},
volume = {abs/1812.02341},
year = {2018},
url = {http://arxiv.org/abs/1812.02341},
eprinttype = {arXiv},
eprint = {1812.02341},
timestamp = {Tue, 01 Jan 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1812-02341.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/0022KSDDSSA17,
author = {Xi Chen and
Diederik P. Kingma and
Tim Salimans and
Yan Duan and
Prafulla Dhariwal and
John Schulman and
Ilya Sutskever and
Pieter Abbeel},
title = {Variational Lossy Autoencoder},
booktitle = {5th International Conference on Learning Representations, {ICLR} 2017,
Toulon, France, April 24-26, 2017, Conference Track Proceedings},
publisher = {OpenReview.net},
year = {2017},
url = {https://openreview.net/forum?id=BysvGP5ee},
timestamp = {Thu, 25 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iclr/0022KSDDSSA17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/TangHFSCDSTA17,
author = {Haoran Tang and
Rein Houthooft and
Davis Foote and
Adam Stooke and
Xi Chen and
Yan Duan and
John Schulman and
Filip De Turck and
Pieter Abbeel},
editor = {Isabelle Guyon and
Ulrike von Luxburg and
Samy Bengio and
Hanna M. Wallach and
Rob Fergus and
S. V. N. Vishwanathan and
Roman Garnett},
title = {{\#}Exploration: {A} Study of Count-Based Exploration for Deep Reinforcement
Learning},
booktitle = {Advances in Neural Information Processing Systems 30: Annual Conference
on Neural Information Processing Systems 2017, December 4-9, 2017,
Long Beach, CA, {USA}},
pages = {2753--2762},
year = {2017},
url = {https://proceedings.neurips.cc/paper/2017/hash/3a20f62a0af1aa152670bab3c602feed-Abstract.html},
timestamp = {Thu, 21 Jan 2021 13:58:27 +0100},
biburl = {https://dblp.org/rec/conf/nips/TangHFSCDSTA17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/SchulmanAC17,
author = {John Schulman and
Pieter Abbeel and
Xi Chen},
title = {Equivalence Between Policy Gradients and Soft Q-Learning},
journal = {CoRR},
volume = {abs/1704.06440},
year = {2017},
url = {http://arxiv.org/abs/1704.06440},
eprinttype = {arXiv},
eprint = {1704.06440},
timestamp = {Mon, 03 Sep 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/SchulmanAC17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/ChenSAS17,
author = {Richard Y. Chen and
Szymon Sidor and
Pieter Abbeel and
John Schulman},
title = {{UCB} and InfoGain Exploration via {\textdollar}{\textbackslash}boldsymbol\{Q\}{\textdollar}-Ensembles},
journal = {CoRR},
volume = {abs/1706.01502},
year = {2017},
url = {http://arxiv.org/abs/1706.01502},
eprinttype = {arXiv},
eprint = {1706.01502},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/ChenSAS17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/MatiisenOCS17,
author = {Tambet Matiisen and
Avital Oliver and
Taco Cohen and
John Schulman},
title = {Teacher-Student Curriculum Learning},
journal = {CoRR},
volume = {abs/1707.00183},
year = {2017},
url = {http://arxiv.org/abs/1707.00183},
eprinttype = {arXiv},
eprint = {1707.00183},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/MatiisenOCS17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/SchulmanWDRK17,
author = {John Schulman and
Filip Wolski and
Prafulla Dhariwal and
Alec Radford and
Oleg Klimov},
title = {Proximal Policy Optimization Algorithms},
journal = {CoRR},
volume = {abs/1707.06347},
year = {2017},
url = {http://arxiv.org/abs/1707.06347},
eprinttype = {arXiv},
eprint = {1707.06347},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/SchulmanWDRK17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1709-10087,
author = {Aravind Rajeswaran and
Vikash Kumar and
Abhishek Gupta and
John Schulman and
Emanuel Todorov and
Sergey Levine},
title = {Learning Complex Dexterous Manipulation with Deep Reinforcement Learning
and Demonstrations},
journal = {CoRR},
volume = {abs/1709.10087},
year = {2017},
url = {http://arxiv.org/abs/1709.10087},
eprinttype = {arXiv},
eprint = {1709.10087},
timestamp = {Thu, 20 Dec 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1709-10087.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1710-09767,
author = {Kevin Frans and
Jonathan Ho and
Xi Chen and
Pieter Abbeel and
John Schulman},
title = {Meta Learning Shared Hierarchies},
journal = {CoRR},
volume = {abs/1710.09767},
year = {2017},
url = {http://arxiv.org/abs/1710.09767},
eprinttype = {arXiv},
eprint = {1710.09767},
timestamp = {Mon, 03 Sep 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1710-09767.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@phdthesis{DBLP:phd/us/Schulman16,
author = {John Schulman},
title = {Optimizing Expectations: From Deep Reinforcement Learning to Stochastic
Computation Graphs},
school = {University of California, Berkeley, {USA}},
year = {2016},
url = {https://www.escholarship.org/uc/item/9z908523},
timestamp = {Wed, 22 Jun 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/phd/us/Schulman16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/DuanCHSA16,
author = {Yan Duan and
Xi Chen and
Rein Houthooft and
John Schulman and
Pieter Abbeel},
editor = {Maria{-}Florina Balcan and
Kilian Q. Weinberger},
title = {Benchmarking Deep Reinforcement Learning for Continuous Control},
booktitle = {Proceedings of the 33nd International Conference on Machine Learning,
{ICML} 2016, New York City, NY, USA, June 19-24, 2016},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {48},
pages = {1329--1338},
publisher = {JMLR.org},
year = {2016},
url = {http://proceedings.mlr.press/v48/duan16.html},
timestamp = {Wed, 29 May 2019 08:41:46 +0200},
biburl = {https://dblp.org/rec/conf/icml/DuanCHSA16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/HouthooftCCDSTA16,
author = {Rein Houthooft and
Xi Chen and
Yan Duan and
John Schulman and
Filip De Turck and
Pieter Abbeel},
editor = {Daniel D. Lee and
Masashi Sugiyama and
Ulrike von Luxburg and
Isabelle Guyon and
Roman Garnett},
title = {{VIME:} Variational Information Maximizing Exploration},
booktitle = {Advances in Neural Information Processing Systems 29: Annual Conference
on Neural Information Processing Systems 2016, December 5-10, 2016,
Barcelona, Spain},
pages = {1109--1117},
year = {2016},
url = {https://proceedings.neurips.cc/paper/2016/hash/abd815286ba1007abfbb8415b83ae2cf-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/HouthooftCCDSTA16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/ChenCDHSSA16,
author = {Xi Chen and
Yan Duan and
Rein Houthooft and
John Schulman and
Ilya Sutskever and
Pieter Abbeel},
editor = {Daniel D. Lee and
Masashi Sugiyama and
Ulrike von Luxburg and
Isabelle Guyon and
Roman Garnett},
title = {InfoGAN: Interpretable Representation Learning by Information Maximizing
Generative Adversarial Nets},
booktitle = {Advances in Neural Information Processing Systems 29: Annual Conference
on Neural Information Processing Systems 2016, December 5-10, 2016,
Barcelona, Spain},
pages = {2172--2180},
year = {2016},
url = {https://proceedings.neurips.cc/paper/2016/hash/7c9d0b1f96aebd7b5eca8c3edaa19ebb-Abstract.html},
timestamp = {Thu, 21 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/ChenCDHSSA16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:journals/corr/SchulmanMLJA15,
author = {John Schulman and
Philipp Moritz and
Sergey Levine and
Michael I. Jordan and
Pieter Abbeel},
editor = {Yoshua Bengio and
Yann LeCun},
title = {High-Dimensional Continuous Control Using Generalized Advantage Estimation},
booktitle = {4th International Conference on Learning Representations, {ICLR} 2016,
San Juan, Puerto Rico, May 2-4, 2016, Conference Track Proceedings},
year = {2016},
url = {http://arxiv.org/abs/1506.02438},
timestamp = {Thu, 25 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/SchulmanMLJA15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/DuanCHSA16,
author = {Yan Duan and
Xi Chen and
Rein Houthooft and
John Schulman and
Pieter Abbeel},
title = {Benchmarking Deep Reinforcement Learning for Continuous Control},
journal = {CoRR},
volume = {abs/1604.06778},
year = {2016},
url = {http://arxiv.org/abs/1604.06778},
eprinttype = {arXiv},
eprint = {1604.06778},
timestamp = {Mon, 03 Sep 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/DuanCHSA16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/Al-RfouAAa16,
author = {Rami Al{-}Rfou and
Guillaume Alain and
Amjad Almahairi and
Christof Angerm{\"{u}}ller and
Dzmitry Bahdanau and
Nicolas Ballas and
Fr{\'{e}}d{\'{e}}ric Bastien and
Justin Bayer and
Anatoly Belikov and
Alexander Belopolsky and
Yoshua Bengio and
Arnaud Bergeron and
James Bergstra and
Valentin Bisson and
Josh Bleecher Snyder and
Nicolas Bouchard and
Nicolas Boulanger{-}Lewandowski and
Xavier Bouthillier and
Alexandre de Br{\'{e}}bisson and
Olivier Breuleux and
Pierre Luc Carrier and
Kyunghyun Cho and
Jan Chorowski and
Paul F. Christiano and
Tim Cooijmans and
Marc{-}Alexandre C{\^{o}}t{\'{e}} and
Myriam C{\^{o}}t{\'{e}} and
Aaron C. Courville and
Yann N. Dauphin and
Olivier Delalleau and
Julien Demouth and
Guillaume Desjardins and
Sander Dieleman and
Laurent Dinh and
Melanie Ducoffe and
Vincent Dumoulin and
Samira Ebrahimi Kahou and
Dumitru Erhan and
Ziye Fan and
Orhan Firat and
Mathieu Germain and
Xavier Glorot and
Ian J. Goodfellow and
Matthew Graham and
{\c{C}}aglar G{\"{u}}l{\c{c}}ehre and
Philippe Hamel and
Iban Harlouchet and
Jean{-}Philippe Heng and
Bal{\'{a}}zs Hidasi and
Sina Honari and
Arjun Jain and
S{\'{e}}bastien Jean and
Kai Jia and
Mikhail Korobov and
Vivek Kulkarni and
Alex Lamb and
Pascal Lamblin and
Eric Larsen and
C{\'{e}}sar Laurent and
Sean Lee and
Simon Lefran{\c{c}}ois and
Simon Lemieux and
Nicholas L{\'{e}}onard and
Zhouhan Lin and
Jesse A. Livezey and
Cory Lorenz and
Jeremiah Lowin and
Qianli Ma and
Pierre{-}Antoine Manzagol and
Olivier Mastropietro and
Robert McGibbon and
Roland Memisevic and
Bart van Merri{\"{e}}nboer and
Vincent Michalski and
Mehdi Mirza and
Alberto Orlandi and
Christopher Joseph Pal and
Razvan Pascanu and
Mohammad Pezeshki and
Colin Raffel and
Daniel Renshaw and
Matthew Rocklin and
Adriana Romero and
Markus Roth and
Peter Sadowski and
John Salvatier and
Fran{\c{c}}ois Savard and
Jan Schl{\"{u}}ter and
John Schulman and
Gabriel Schwartz and
Iulian Vlad Serban and
Dmitriy Serdyuk and
Samira Shabanian and
{\'{E}}tienne Simon and
Sigurd Spieckermann and
S. Ramana Subramanyam and
Jakub Sygnowski and
J{\'{e}}r{\'{e}}mie Tanguay and
Gijs van Tulder and
Joseph P. Turian and
Sebastian Urban and
Pascal Vincent and
Francesco Visin and
Harm de Vries and
David Warde{-}Farley and
Dustin J. Webb and
Matthew Willson and
Kelvin Xu and
Lijun Xue and
Li Yao and
Saizheng Zhang and
Ying Zhang},
title = {Theano: {A} Python framework for fast computation of mathematical
expressions},
journal = {CoRR},
volume = {abs/1605.02688},
year = {2016},
url = {http://arxiv.org/abs/1605.02688},
eprinttype = {arXiv},
eprint = {1605.02688},
timestamp = {Thu, 30 Apr 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/Al-RfouAAa16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/HouthooftCDSTA16,
author = {Rein Houthooft and
Xi Chen and
Yan Duan and
John Schulman and
Filip De Turck and
Pieter Abbeel},
title = {Curiosity-driven Exploration in Deep Reinforcement Learning via Bayesian
Neural Networks},
journal = {CoRR},
volume = {abs/1605.09674},
year = {2016},
url = {http://arxiv.org/abs/1605.09674},
eprinttype = {arXiv},
eprint = {1605.09674},
timestamp = {Mon, 03 Sep 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/HouthooftCDSTA16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/BrockmanCPSSTZ16,
author = {Greg Brockman and
Vicki Cheung and
Ludwig Pettersson and
Jonas Schneider and
John Schulman and
Jie Tang and
Wojciech Zaremba},
title = {OpenAI Gym},
journal = {CoRR},
volume = {abs/1606.01540},
year = {2016},
url = {http://arxiv.org/abs/1606.01540},
eprinttype = {arXiv},
eprint = {1606.01540},
timestamp = {Fri, 08 Nov 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/BrockmanCPSSTZ16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/ChenDHSSA16,
author = {Xi Chen and
Yan Duan and
Rein Houthooft and
John Schulman and
Ilya Sutskever and
Pieter Abbeel},
title = {InfoGAN: Interpretable Representation Learning by Information Maximizing
Generative Adversarial Nets},
journal = {CoRR},
volume = {abs/1606.03657},
year = {2016},
url = {http://arxiv.org/abs/1606.03657},
eprinttype = {arXiv},
eprint = {1606.03657},
timestamp = {Mon, 03 Sep 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/ChenDHSSA16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/AmodeiOSCSM16,
author = {Dario Amodei and
Chris Olah and
Jacob Steinhardt and
Paul F. Christiano and
John Schulman and
Dan Man{\'{e}}},
title = {Concrete Problems in {AI} Safety},
journal = {CoRR},
volume = {abs/1606.06565},
year = {2016},
url = {http://arxiv.org/abs/1606.06565},
eprinttype = {arXiv},
eprint = {1606.06565},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/AmodeiOSCSM16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/ChenKSDDSSA16,
author = {Xi Chen and
Diederik P. Kingma and
Tim Salimans and
Yan Duan and
Prafulla Dhariwal and
John Schulman and
Ilya Sutskever and
Pieter Abbeel},
title = {Variational Lossy Autoencoder},
journal = {CoRR},
volume = {abs/1611.02731},
year = {2016},
url = {http://arxiv.org/abs/1611.02731},
eprinttype = {arXiv},
eprint = {1611.02731},
timestamp = {Mon, 03 Sep 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/ChenKSDDSSA16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/DuanSCBSA16,
author = {Yan Duan and
John Schulman and
Xi Chen and
Peter L. Bartlett and
Ilya Sutskever and
Pieter Abbeel},
title = {RL{\textdollar}{\^{}}2{\textdollar}: Fast Reinforcement Learning via
Slow Reinforcement Learning},
journal = {CoRR},
volume = {abs/1611.02779},
year = {2016},
url = {http://arxiv.org/abs/1611.02779},
eprinttype = {arXiv},
eprint = {1611.02779},
timestamp = {Mon, 03 Sep 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/DuanSCBSA16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/TangHFSCDSTA16,
author = {Haoran Tang and
Rein Houthooft and
Davis Foote and
Adam Stooke and
Xi Chen and
Yan Duan and
John Schulman and
Filip De Turck and
Pieter Abbeel},
title = {{\#}Exploration: {A} Study of Count-Based Exploration for Deep Reinforcement
Learning},
journal = {CoRR},
volume = {abs/1611.04717},
year = {2016},
url = {http://arxiv.org/abs/1611.04717},
eprinttype = {arXiv},
eprint = {1611.04717},
timestamp = {Mon, 03 Sep 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/TangHFSCDSTA16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/SchulmanLAJM15,
author = {John Schulman and
Sergey Levine and
Pieter Abbeel and
Michael I. Jordan and
Philipp Moritz},
editor = {Francis R. Bach and
David M. Blei},
title = {Trust Region Policy Optimization},
booktitle = {Proceedings of the 32nd International Conference on Machine Learning,
{ICML} 2015, Lille, France, 6-11 July 2015},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {37},
pages = {1889--1897},
publisher = {JMLR.org},
year = {2015},
url = {http://proceedings.mlr.press/v37/schulman15.html},
timestamp = {Wed, 29 May 2019 08:41:45 +0200},
biburl = {https://dblp.org/rec/conf/icml/SchulmanLAJM15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/SchulmanHWA15,
author = {John Schulman and
Nicolas Heess and
Theophane Weber and
Pieter Abbeel},
editor = {Corinna Cortes and
Neil D. Lawrence and
Daniel D. Lee and
Masashi Sugiyama and
Roman Garnett},
title = {Gradient Estimation Using Stochastic Computation Graphs},
booktitle = {Advances in Neural Information Processing Systems 28: Annual Conference
on Neural Information Processing Systems 2015, December 7-12, 2015,
Montreal, Quebec, Canada},
pages = {3528--3536},
year = {2015},
url = {https://proceedings.neurips.cc/paper/2015/hash/de03beffeed9da5f3639a621bcab5dd4-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/SchulmanHWA15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/SchulmanLMJA15,
author = {John Schulman and
Sergey Levine and
Philipp Moritz and
Michael I. Jordan and
Pieter Abbeel},
title = {Trust Region Policy Optimization},
journal = {CoRR},
volume = {abs/1502.05477},
year = {2015},
url = {http://arxiv.org/abs/1502.05477},
eprinttype = {arXiv},
eprint = {1502.05477},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/SchulmanLMJA15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/SchulmanHWA15,
author = {John Schulman and
Nicolas Heess and
Theophane Weber and
Pieter Abbeel},
title = {Gradient Estimation Using Stochastic Computation Graphs},
journal = {CoRR},
volume = {abs/1506.05254},
year = {2015},
url = {http://arxiv.org/abs/1506.05254},
eprinttype = {arXiv},
eprint = {1506.05254},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/SchulmanHWA15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ijrr/SchulmanDHLABPPGA14,
author = {John Schulman and
Yan Duan and
Jonathan Ho and
Alex X. Lee and
Ibrahim Awwal and
Henry Bradlow and
Jia Pan and
Sachin Patil and
Ken Goldberg and
Pieter Abbeel},
title = {Motion planning with sequential convex optimization and convex collision
checking},
journal = {Int. J. Robotics Res.},
volume = {33},
number = {9},
pages = {1251--1270},
year = {2014},
url = {https://doi.org/10.1177/0278364914528132},
doi = {10.1177/0278364914528132},
timestamp = {Thu, 17 Sep 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ijrr/SchulmanDHLABPPGA14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icra/DuanPSGA14,
author = {Yan Duan and
Sachin Patil and
John Schulman and
Kenneth Y. Goldberg and
Pieter Abbeel},
title = {Planning locally optimal, curvature-constrained trajectories in 3D
using sequential convex optimization},
booktitle = {2014 {IEEE} International Conference on Robotics and Automation, {ICRA}
2014, Hong Kong, China, May 31 - June 7, 2014},
pages = {5889--5895},
publisher = {{IEEE}},
year = {2014},
url = {https://doi.org/10.1109/ICRA.2014.6907726},
doi = {10.1109/ICRA.2014.6907726},
timestamp = {Wed, 16 Oct 2019 14:14:51 +0200},
biburl = {https://dblp.org/rec/conf/icra/DuanPSGA14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icra/PatilDSGA14,
author = {Sachin Patil and
Yan Duan and
John Schulman and
Ken Goldberg and
Pieter Abbeel},
title = {Gaussian belief space planning with discontinuities in sensing domains},
booktitle = {2014 {IEEE} International Conference on Robotics and Automation, {ICRA}
2014, Hong Kong, China, May 31 - June 7, 2014},
pages = {6483--6490},
publisher = {{IEEE}},
year = {2014},
url = {https://doi.org/10.1109/ICRA.2014.6907816},
doi = {10.1109/ICRA.2014.6907816},
timestamp = {Wed, 14 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icra/PatilDSGA14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/wafr/PatilKLSGA14,
author = {Sachin Patil and
Gregory Kahn and
Michael Laskey and
John Schulman and
Ken Goldberg and
Pieter Abbeel},
editor = {H. Levent Akin and
Nancy M. Amato and
Volkan Isler and
A. Frank van der Stappen},
title = {Scaling up Gaussian Belief Space Planning Through Covariance-Free
Trajectory Optimization and Automatic Differentiation},
booktitle = {Algorithmic Foundations of Robotics {XI} - Selected Contributions
of the Eleventh International Workshop on the Algorithmic Foundations
of Robotics, {WAFR} 2014, 3-5 August 2014, Bo{\u{g}}azi{\c{c}}i University,
{\.{I}}stanbul, Turkey},
series = {Springer Tracts in Advanced Robotics},
volume = {107},
pages = {515--533},
publisher = {Springer},
year = {2014},
url = {https://doi.org/10.1007/978-3-319-16595-0\_30},
doi = {10.1007/978-3-319-16595-0\_30},
timestamp = {Sun, 25 Oct 2020 23:03:12 +0100},
biburl = {https://dblp.org/rec/conf/wafr/PatilKLSGA14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icra/SchulmanLHA13,
author = {John Schulman and
Alex X. Lee and
Jonathan Ho and
Pieter Abbeel},
title = {Tracking deformable objects with point clouds},
booktitle = {2013 {IEEE} International Conference on Robotics and Automation, Karlsruhe,
Germany, May 6-10, 2013},
pages = {1130--1137},
publisher = {{IEEE}},
year = {2013},
url = {https://doi.org/10.1109/ICRA.2013.6630714},
doi = {10.1109/ICRA.2013.6630714},
timestamp = {Wed, 16 Oct 2019 14:14:51 +0200},
biburl = {https://dblp.org/rec/conf/icra/SchulmanLHA13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iros/SchulmanGVTA13,
author = {John Schulman and
Ankush Gupta and
Sibi Venkatesan and
Mallory Tayson{-}Frederick and
Pieter Abbeel},
title = {A case study of trajectory transfer through non-rigid registration
for a simplified suturing scenario},
booktitle = {2013 {IEEE/RSJ} International Conference on Intelligent Robots and
Systems, {IROS} 2013, Tokyo, Japan, November 3-7, 2013},
pages = {4111--4117},
publisher = {{IEEE}},
year = {2013},
url = {https://doi.org/10.1109/IROS.2013.6696945},
doi = {10.1109/IROS.2013.6696945},
timestamp = {Tue, 05 Sep 2023 15:06:24 +0200},
biburl = {https://dblp.org/rec/conf/iros/SchulmanGVTA13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iros/LeeDPSMBGA13,
author = {Alex X. Lee and
Yan Duan and
Sachin Patil and
John Schulman and
Zoe McCarthy and
Jur van den Berg and
Ken Goldberg and
Pieter Abbeel},
title = {Sigma hulls for Gaussian belief space planning for imprecise articulated
robots amid obstacles},
booktitle = {2013 {IEEE/RSJ} International Conference on Intelligent Robots and
Systems, {IROS} 2013, Tokyo, Japan, November 3-7, 2013},
pages = {5660--5667},
publisher = {{IEEE}},
year = {2013},
url = {https://doi.org/10.1109/IROS.2013.6697176},
doi = {10.1109/IROS.2013.6697176},
timestamp = {Wed, 14 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/iros/LeeDPSMBGA13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/isrr/SchulmanHLA13,
author = {John Schulman and
Jonathan Ho and
Cameron Lee and
Pieter Abbeel},
editor = {Masayuki Inaba and
Peter Corke},
title = {Learning from Demonstrations Through the Use of Non-rigid Registration},
booktitle = {Robotics Research - The 16th International Symposium ISRR, 16-19 December
2013, Singapore},
series = {Springer Tracts in Advanced Robotics},
volume = {114},
pages = {339--354},
publisher = {Springer},
year = {2013},
url = {https://doi.org/10.1007/978-3-319-28872-7\_20},
doi = {10.1007/978-3-319-28872-7\_20},
timestamp = {Sat, 24 Nov 2018 11:59:52 +0100},
biburl = {https://dblp.org/rec/conf/isrr/SchulmanHLA13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/rss/SchulmanHLABA13,
author = {John Schulman and
Jonathan Ho and
Alex X. Lee and
Ibrahim Awwal and
Henry Bradlow and
Pieter Abbeel},
editor = {Paul Newman and
Dieter Fox and
David Hsu},
title = {Finding Locally Optimal, Collision-Free Trajectories with Sequential
Convex Optimization},
booktitle = {Robotics: Science and Systems IX, Technische Universit{\"{a}}t
Berlin, Berlin, Germany, June 24 - June 28, 2013},
year = {2013},
url = {http://www.roboticsproceedings.org/rss09/p31.html},
doi = {10.15607/RSS.2013.IX.031},
timestamp = {Fri, 29 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/rss/SchulmanHLABA13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/isrr/SchulmanGA11,
author = {John D. Schulman and
Ken Goldberg and
Pieter Abbeel},
editor = {Henrik I. Christensen and
Oussama Khatib},
title = {Grasping and Fixturing as Submodular Coverage Problems},
booktitle = {Robotics Research - The 15th International Symposium ISRR, 9-12 December
2011, Flagstaff, Arizona, {USA}},
series = {Springer Tracts in Advanced Robotics},
volume = {100},
pages = {571--583},
publisher = {Springer},
year = {2011},
url = {https://doi.org/10.1007/978-3-319-29363-9\_32},
doi = {10.1007/978-3-319-29363-9\_32},
timestamp = {Fri, 26 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/isrr/SchulmanGA11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
last updated on 2024-08-21 21:29 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
