- Ota, K., Jha, D.K., Romeres, D., van Baar, J., Smith, K., Semistsu, T., Oiki, T., Sullivan, A., Nikovski, D.N., Tenenbaum, J.B., "Data-Efficient Learning for Complex and Real-Time Physical Problem Solving using Augmented Simulation", IEEE Robotics and Automation Letters, DOI: 10.1109/LRA.2021.3068887, Vol. 6, No. 2, March 2021.
BibTeX TR2021-032 PDF Video Software- @article{Ota2021mar,
- author = {Ota, Kei and Jha, Devesh K. and Romeres, Diego and van Baar, Jeroen and Smith, Kevin and Semistsu, Takayuki and Oiki, Tomoaki and Sullivan, Alan and Nikovski, Daniel N. and Tenenbaum, Joshua B.},
- title = {Data-Efficient Learning for Complex and Real-Time Physical Problem Solving using Augmented Simulation},
- journal = {IEEE Robotics and Automation Letters},
- year = 2021,
- volume = 6,
- number = 2,
- month = mar,
- doi = {10.1109/LRA.2021.3068887},
- url = {https://www.merl.com/publications/TR2021-032}
- }
- Kojima, K., Tang, Y., Koike-Akino, T., Wang, Y., Jha, D.K., TaherSima, M., Parsons, K., "Application of Deep Learning for Nanophotonic Device Design", SPIE Photonics West, Bahram Jalali and Ken-ichi Kitayama, Eds., DOI: 10.1117/12.2579104, March 2021.
BibTeX TR2020-182 PDF Video- @inproceedings{Kojima2021mar,
- author = {Kojima, Keisuke and Tang, Yingheng and Koike-Akino, Toshiaki and Wang, Ye and Jha, Devesh K. and TaherSima, Mohammad and Parsons, Kieran},
- title = {Application of Deep Learning for Nanophotonic Device Design},
- booktitle = {SPIE Photonics West},
- year = 2021,
- editor = {Bahram Jalali and Ken-ichi Kitayama},
- month = mar,
- publisher = {SPIE},
- doi = {10.1117/12.2579104},
- url = {https://www.merl.com/publications/TR2020-182}
- }
- Ota, K., Jha, D.K., Kanezaki, A., "Training Larger Networks for Deep Reinforcement Learning", arXiv, February 2021.
BibTeX arXiv- @inproceedings{Ota2021feb,
- author = {Ota, Kei and Jha, Devesh K. and Kanezaki, Asako},
- title = {Training Larger Networks for Deep Reinforcement Learning},
- booktitle = {arXiv},
- year = 2021,
- month = feb,
- url = {https://arxiv.org/abs/2102.07920}
- }
- Kojima, K., TaherSima, M., Koike-Akino, T., Jha, D.K., Tang, Y., Wang, Y., Parsons, K., "Deep Neural Networks for Inverse Design of Nanophotonic Devices", IEEE Journal of Lightwave Technology, DOI: 10.1109/JLT.2021.3050083, January 2021.
BibTeX TR2021-001 PDF- @article{Kojima2021jan,
- author = {Kojima, Keisuke and TaherSima, Mohammad and Koike-Akino, Toshiaki and Jha, Devesh K. and Tang, Yingheng and Wang, Ye and Parsons, Kieran},
- title = {Deep Neural Networks for Inverse Design of Nanophotonic Devices},
- journal = {IEEE Journal of Lightwave Technology},
- year = 2021,
- month = jan,
- doi = {10.1109/JLT.2021.3050083},
- issn = {1558-2213},
- url = {https://www.merl.com/publications/TR2021-001}
- }
- Ota, K., Jha, D.K., Onishi, T., Kanezaki, A., Yoshiyasu, Y., Mariyama, T., Nikovski, D.N., "Deep Reactive Planning in Dynamic Environments", Conference on Robot Learning (CoRL), Kober, Jens and Ramos, Fabio and Tomlin, Calire, Eds., November 2020, pp. 1943-1957.
BibTeX TR2020-144 PDF Video- @inproceedings{Ota2020nov2,
- author = {Ota, Kei and Jha, Devesh K. and Onishi, Tadashi and Kanezaki, Asako and Yoshiyasu, Yusuke and Mariyama, Toshisada and Nikovski, Daniel N.},
- title = {Deep Reactive Planning in Dynamic Environments},
- booktitle = {Conference on Robot Learning (CoRL)},
- year = 2020,
- editor = {Kober, Jens and Ramos, Fabio and Tomlin, Calire},
- pages = {1943--1957},
- month = nov,
- publisher = {Proceedings of Machine Learning Research},
- url = {https://www.merl.com/publications/TR2020-144}
- }
- Ota, K., Sasaki, Y., Jha, D., Yoshiyasu, Y., Kanezaki, A., "Efficient Exploration in Constrained Environments with Goal-Oriented Reference Path", IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), November 2020.
BibTeX TR2020-141 PDF Software- @inproceedings{Ota2020nov,
- author = {Ota, Kei and Sasaki, Yoko and Jha, Devesh and Yoshiyasu, Yusuke and Kanezaki, Asako},
- title = {Efficient Exploration in Constrained Environments with Goal-Oriented Reference Path},
- booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
- year = 2020,
- month = nov,
- url = {https://www.merl.com/publications/TR2020-141}
- }
- Zhang, W., Seto, S., Jha, D.K., "CAZSL: Zero-Shot Regression for Pushing Models by Generalizing Through Context", IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), November 2020.
BibTeX TR2020-140 PDF Software- @inproceedings{Zhang2020nov,
- author = {Zhang, Wenyu and Seto, Skyler and Jha, Devesh K.},
- title = {CAZSL: Zero-Shot Regression for Pushing Models by Generalizing Through Context},
- booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
- year = 2020,
- month = nov,
- url = {https://www.merl.com/publications/TR2020-140}
- }
- Tang, Y., Kojima, K., Koike-Akino, T., Wang, Y., Wu, P., TaherSima, M., Jha, D.K., Parsons, K., Qi, M., "Generative Deep Learning Model for Inverse Design of Integrated Nanophotonic Devices", Lasers and Photonics Reviews, DOI: 10.1002/lpor.202000287, Vol. 2020, pp. 2000287, October 2020.
BibTeX TR2020-135 PDF- @article{Tang2020oct,
- author = {Tang, Yingheng and Kojima, Keisuke and Koike-Akino, Toshiaki and Wang, Ye and Wu, Pengxiang and TaherSima, Mohammad and Jha, Devesh K. and Parsons, Kieran and Qi, Minghao},
- title = {Generative Deep Learning Model for Inverse Design of Integrated Nanophotonic Devices},
- journal = {Lasers and Photonics Reviews},
- year = 2020,
- volume = 2020,
- pages = 2000287,
- month = oct,
- doi = {10.1002/lpor.202000287},
- url = {https://www.merl.com/publications/TR2020-135}
- }
- Kojima, K., Tang, Y., Koike-Akino, T., Wang, Y., Jha, D.K., Parsons, K., TaherSima, M., Sang, F., Klamkin, J., Qi, M., "Inverse Design of Nanophotonic Devices using Deep Neural Networks", Asia Communications and Photonics Conference (ACP), September 2020, pp. Su1A.1.
BibTeX TR2020-130 PDF Video- @inproceedings{Kojima2020sep,
- author = {Kojima, Keisuke and Tang, Yingheng and Koike-Akino, Toshiaki and Wang, Ye and Jha, Devesh K. and Parsons, Kieran and TaherSima, Mohammad and Sang, Fengqiao and Klamkin, Jonathan and Qi, Minghao},
- title = {Inverse Design of Nanophotonic Devices using Deep Neural Networks},
- booktitle = {Asia Communications and Photonics Conference (ACP)},
- year = 2020,
- pages = {Su1A.1},
- month = sep,
- publisher = {Optical Society of America},
- isbn = {978-1-943580-82-8},
- url = {https://www.merl.com/publications/TR2020-130}
- }
- Chakrabarty, A., Jha, D.K., Buzzard, G.T., Wang, Y., Vamvoudakis, K., "Safe Approximate Dynamic Programming via Kernelized Lipschitz Estimation", IEEE Transactions on Neural Networks and Learning Systems, DOI: 10.1109/TNNLS.2020.2978805, July 2020.
BibTeX TR2020-108 PDF- @article{Chakrabarty2020jul2,
- author = {Chakrabarty, Ankush and Jha, Devesh K. and Buzzard, Gregery T. and Wang, Yebin and Vamvoudakis, Kyriakos},
- title = {Safe Approximate Dynamic Programming via Kernelized Lipschitz Estimation},
- journal = {IEEE Transactions on Neural Networks and Learning Systems},
- year = 2020,
- month = jul,
- doi = {10.1109/TNNLS.2020.2978805},
- url = {https://www.merl.com/publications/TR2020-108}
- }
- Romeres, D., Liu, Y., Jha, D.K., Nikovski, D.N., "Understanding Multi-Modal Perception Using Behavioral Cloning for Peg-In-a-Hole Insertion Tasks", Robotics: Science and Systems, July 2020.
BibTeX TR2020-110 PDF- @inproceedings{Romeres2020jul,
- author = {Romeres, Diego and Liu, Yifang and Jha, Devesh K. and Nikovski, Daniel N.},
- title = {Understanding Multi-Modal Perception Using Behavioral Cloning for Peg-In-a-Hole Insertion Tasks},
- booktitle = {Robotics: Science and Systems},
- year = 2020,
- month = jul,
- url = {https://www.merl.com/publications/TR2020-110}
- }
- Ota, K., Oiki, T., Jha, D.K., Mariyama, T., Nikovski, D.N., "Can Increasing Input Dimensionality Improve Deep Reinforcement Learning?", International Conference on Machine Learning (ICML), Daumé III , Hal and Singh, Aarti, Eds., June 2020, pp. 7424-7433.
BibTeX TR2020-083 PDF Software- @inproceedings{Ota2020jun,
- author = {Ota, Kei and Oiki, Tomoaki and Jha, Devesh K. and Mariyama, Toshisada and Nikovski, Daniel N.},
- title = {Can Increasing Input Dimensionality Improve Deep Reinforcement Learning?},
- booktitle = {International Conference on Machine Learning (ICML)},
- year = 2020,
- editor = {Daumé III , Hal and Singh, Aarti},
- pages = {7424--7433},
- month = jun,
- publisher = {PMLR},
- url = {https://www.merl.com/publications/TR2020-083}
- }
- Jha, D.K., Kolaric, P., Raghunathan, A., Lewis, F., Benosman, M., Romeres, D., Nikovski, D.N., "Local Policy Optimization for Trajectory-Centric Reinforcement Learning", IEEE International Conference on Robotics and Automation (ICRA), Ayanna Howard, Eds., May 2020, pp. 5094-5100.
BibTeX TR2020-062 PDF- @inproceedings{Jha2020may,
- author = {Jha, Devesh K. and Kolaric, Patrik and Raghunathan, Arvind and Lewis, Frank and Benosman, Mouhacine and Romeres, Diego and Nikovski, Daniel N.},
- title = {Local Policy Optimization for Trajectory-Centric Reinforcement Learning},
- booktitle = {IEEE International Conference on Robotics and Automation (ICRA)},
- year = 2020,
- editor = {Ayanna Howard},
- pages = {5094--5100},
- month = may,
- publisher = {IEEE},
- isbn = {978-1-7281-7395-5},
- url = {https://www.merl.com/publications/TR2020-062}
- }
- Romeres, D., Dalla Libera, A., Jha, D.K., Yerazunis, W.S., Nikovski, D.N., "Model-Based Reinforcement Learning for Physical Systems Without Velocity and Acceleration Measurements", Robotics and Automation Letters, DOI: 10.1109/LRA.2020.2977255, Vol. 5, No. 2, pp. 3548-3555, May 2020.
BibTeX TR2020-063 PDF- @article{Romeres2020may,
- author = {Romeres, Diego and Dalla Libera, Alberto and Jha, Devesh K. and Yerazunis, William S. and Nikovski, Daniel N.},
- title = {Model-Based Reinforcement Learning for Physical Systems Without Velocity and Acceleration Measurements},
- journal = {Robotics and Automation Letters},
- year = 2020,
- volume = 5,
- number = 2,
- pages = {3548--3555},
- month = may,
- doi = {10.1109/LRA.2020.2977255},
- issn = {2377-3766},
- url = {https://www.merl.com/publications/TR2020-063}
- }
- Kojima, K., TaherSima, M., Koike-Akino, T., Jha, D.K., Tang, Y., Parsons, K., Sang, F., Klamkin, J., "Deep Neural Networks for Designing Integrated Photonics", Optical Fiber Communication Conference and Exposition (OFC), DOI: 10.1364/OFC.2020.Th1A.6, March 2020.
BibTeX TR2020-057 PDF- @inproceedings{Kojima2020mar,
- author = {Kojima, Keisuke and TaherSima, Mohammad and Koike-Akino, Toshiaki and Jha, Devesh K. and Tang, Yingheng and Parsons, Kieran and Sang, Fengqiao and Klamkin, Jonathan},
- title = {Deep Neural Networks for Designing Integrated Photonics},
- booktitle = {Optical Fiber Communication Conference and Exposition (OFC)},
- year = 2020,
- month = mar,
- publisher = {OSA},
- doi = {10.1364/OFC.2020.Th1A.6},
- isbn = {978-1-943580-71-2},
- url = {https://www.merl.com/publications/TR2020-057}
- }
- Tang, Y., Kojima, K., Koike-Akino, T., Wang, Y., Wu, P., TaherSima, M., Jha, D.K., Parsons, K., Qi, M., "Generative Deep Learning Model for a Multi-level NanoOptic Broadband Power Splitter", Optical Fiber Communication Conference and Exposition (OFC), DOI: 10.1364/OFC.2020.Th1A.1, March 2020, pp. Th1A.1.
BibTeX TR2020-025 PDF- @inproceedings{Tang2020mar,
- author = {Tang, Yingheng and Kojima, Keisuke and Koike-Akino, Toshiaki and Wang, Ye and Wu, Pengxiang and TaherSima, Mohammad and Jha, Devesh K. and Parsons, Kieran and Qi, Minghao},
- title = {Generative Deep Learning Model for a Multi-level NanoOptic Broadband Power Splitter},
- booktitle = {Optical Fiber Communication Conference and Exposition (OFC)},
- year = 2020,
- pages = {Th1A.1},
- month = mar,
- publisher = {OSA},
- doi = {10.1364/OFC.2020.Th1A.1},
- isbn = {978-1-943580-71-2},
- url = {https://www.merl.com/publications/TR2020-025}
- }
- Jha, D.K., Kolaric, P., Romeres, D., Raghunathan, A., Benosman, M., Nikovski, D.N., "Robust Optimization for Trajectory-Centric Model-based Reinforcement Learning", NeurIPS Workshop on Safety and Robustness in Decision Making, December 2019.
BibTeX TR2019-156 PDF- @inproceedings{Jha2019dec2,
- author = {Jha, Devesh K. and Kolaric, Patrik and Romeres, Diego and Raghunathan, Arvind and Benosman, Mouhacine and Nikovski, Daniel N.},
- title = {Robust Optimization for Trajectory-Centric Model-based Reinforcement Learning},
- booktitle = {NeurIPS Workshop on Safety and Robustness in Decision Making},
- year = 2019,
- month = dec,
- url = {https://www.merl.com/publications/TR2019-156}
- }
- Jha, D.K., Raghunathan, A., Romeres, D., "QNTRPO: Including Curvature in TRPO", Optimization Foundations for Reinforcement Learning Workshop at NeurIPS, December 2019.
BibTeX TR2019-154 PDF Software- @inproceedings{Jha2019dec,
- author = {Jha, Devesh K. and Raghunathan, Arvind and Romeres, Diego},
- title = {QNTRPO: Including Curvature in TRPO},
- booktitle = {Optimization Foundations for Reinforcement Learning Workshop at NeurIPS},
- year = 2019,
- month = dec,
- url = {https://www.merl.com/publications/TR2019-154}
- }
- Ota, K., Jha, D.K., Oiki, T., Miura, M., Nammoto, T., Nikovski, D., Mariyama, T., "Trajectory Optimization for Unknown Constrained Systems using Reinforcement Learning", IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), DOI: 10.1109/IROS40897.2019.8968010, November 2019, pp. 3487-3494.
BibTeX TR2019-129 PDF- @inproceedings{Ota2019nov,
- author = {Ota, Kei and Jha, Devesh K. and Oiki, Tomohiro and Miura, Mamoru and Nammoto, Takashi and Nikovski, Daniel and Mariyama, Toshisada},
- title = {Trajectory Optimization for Unknown Constrained Systems using Reinforcement Learning},
- booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
- year = 2019,
- pages = {3487--3494},
- month = nov,
- publisher = {IEEE},
- doi = {10.1109/IROS40897.2019.8968010},
- issn = {2153-0866},
- isbn = {978-1-7281-4004-9},
- url = {https://www.merl.com/publications/TR2019-129}
- }
- Jha, D.K., Raghunathan, A., Romeres, D., "Quasi-Newton Trust Region Policy Optimization", Conference on Robot Learning (CoRL), Leslie Pack Kaelbling and Danica Kragic and Komei Sugiura, Eds., October 2019, pp. 945-954.
BibTeX TR2019-120 PDF Software- @inproceedings{Jha2019oct,
- author = {Jha, Devesh K. and Raghunathan, Arvind and Romeres, Diego},
- title = {Quasi-Newton Trust Region Policy Optimization},
- booktitle = {Conference on Robot Learning (CoRL)},
- year = 2019,
- editor = {Leslie Pack Kaelbling and Danica Kragic and Komei Sugiura},
- pages = {945--954},
- month = oct,
- publisher = {Proceedings of Machine Learning Research},
- url = {https://www.merl.com/publications/TR2019-120}
- }
- Zhang, W., Jha, D.K., Laftchiev, E., Nikovski, D.N., "Multi-label Prediction in Time Series Data using Deep Neural Networks", International Journal for Prognostics and Health Management Special Issue on Applications of Deep Learning and Emerging Analytics, Vol. 10, pp. 0-12, September 2019.
BibTeX TR2019-110 PDF- @article{Zhang2019sep2,
- author = {Zhang, Wenyu and Jha, Devesh K. and Laftchiev, Emil and Nikovski, Daniel N.},
- title = {Multi-label Prediction in Time Series Data using Deep Neural Networks},
- journal = {International Journal for Prognostics and Health Management Special Issue on Applications of Deep Learning and Emerging Analytics},
- year = 2019,
- volume = 10,
- pages = {0--12},
- month = sep,
- note = {Special Issue on Deep Learning and Emerging Analytics},
- issn = {2153-2648},
- url = {https://www.merl.com/publications/TR2019-110}
- }
- Chakrabarty, A., Jha, D.K., Wang, Y., "Data-Driven Control Policies for Partially Known Systems via Kernelized Lipschitz Learning", American Control Conference (ACC), DOI: 10.23919/ACC.2019.8815325, July 2019, pp. 4192-4197.
BibTeX TR2019-047 PDF- @inproceedings{Chakrabarty2019jul,
- author = {Chakrabarty, Ankush and Jha, Devesh K. and Wang, Yebin},
- title = {Data-Driven Control Policies for Partially Known Systems via Kernelized Lipschitz Learning},
- booktitle = {American Control Conference (ACC)},
- year = 2019,
- pages = {4192--4197},
- month = jul,
- publisher = {IEEE},
- doi = {10.23919/ACC.2019.8815325},
- url = {https://www.merl.com/publications/TR2019-047}
- }
- Romeres, D., Jha, D.K., Dau, H., Yerazunis, W.S., Nikovski, D.N., "Anomaly Detection for Insertion Tasks in Robotic Assembly Using Gaussian Process Models", European Control Conference (ECC), DOI: 10.23919/ECC.2019.8795698, June 2019, pp. 1017-1022.
BibTeX TR2019-055 PDF- @inproceedings{Romeres2019jun,
- author = {Romeres, Diego and Jha, Devesh K. and Dau, Hoang and Yerazunis, William S. and Nikovski, Daniel N.},
- title = {Anomaly Detection for Insertion Tasks in Robotic Assembly Using Gaussian Process Models},
- booktitle = {European Control Conference (ECC)},
- year = 2019,
- pages = {1017--1022},
- month = jun,
- publisher = {IEEE},
- doi = {10.23919/ECC.2019.8795698},
- isbn = {978-3-907144-00-8},
- url = {https://www.merl.com/publications/TR2019-055}
- }
- Raghunathan, A., Cherian, A., Jha, D.K., "Game Theoretic Optimization via Gradient-based Nikaido-Isoda Function", International Conference on Machine Learning (ICML), Lawrence, N. and Reid, M., Eds., June 2019, pp. 5291-5300.
BibTeX TR2019-045 PDF Software- @inproceedings{Raghunathan2019jun,
- author = {Raghunathan, Arvind and Cherian, Anoop and Jha, Devesh K.},
- title = {Game Theoretic Optimization via Gradient-based Nikaido-Isoda Function},
- booktitle = {International Conference on Machine Learning (ICML)},
- year = 2019,
- editor = {Lawrence, N. and Reid, M.},
- pages = {5291--5300},
- month = jun,
- publisher = {PMLR},
- issn = {2640-3498},
- url = {https://www.merl.com/publications/TR2019-045}
- }
- Romeres, D., Jha, D.K., Dalla Libera, A., Yerazunis, W.S., Nikovski, D.N., "Semiparametrical Gaussian Processes Learning of Forward Dynamical Models for Navigating in a Circular Maze", IEEE International Conference on Robotics and Automation (ICRA), DOI: 10.1109/ICRA.2019.8794229, May 2019, pp. 3195-3202.
BibTeX TR2019-028 PDF Video Software- @inproceedings{Romeres2019may,
- author = {Romeres, Diego and Jha, Devesh K. and Dalla Libera, Alberto and Yerazunis, William S. and Nikovski, Daniel N.},
- title = {Semiparametrical Gaussian Processes Learning of Forward Dynamical Models for Navigating in a Circular Maze},
- booktitle = {IEEE International Conference on Robotics and Automation (ICRA)},
- year = 2019,
- pages = {3195--3202},
- month = may,
- publisher = {IEEE},
- doi = {10.1109/ICRA.2019.8794229},
- issn = {2577-087X},
- isbn = {978-1-5386-6027-0},
- url = {https://www.merl.com/publications/TR2019-028}
- }