James Queeney
- Phone: 617-621-7511
- Email:
-
Position:
Research / Technical Staff
Postdoctoral Research Fellow -
Education:
Ph.D., Boston University, 2023 -
Research Areas:
External Links:
Jimmy's Quick Links
-
Biography
Jimmy conducts research on data-driven methods for decision making and control. During his PhD, he developed reliable deep reinforcement learning algorithms with guarantees on training stability, robustness, and safety.
-
MERL Publications
- , "Optimal Transport Perturbations for Safe Reinforcement Learning with Robustness Guarantees", Transactions on Machine Learning Research (TMLR), April 2024.BibTeX TR2024-037 PDF
- @article{Queeney2024apr,
- author = {Queeney, James and Ozcan, Erhan Can and Paschalidis, Ioannis Ch. and Cassandras, Christos G.},
- title = {Optimal Transport Perturbations for Safe Reinforcement Learning with Robustness Guarantees},
- journal = {Transactions on Machine Learning Research (TMLR)},
- year = 2024,
- month = apr,
- issn = {2835-8856},
- url = {https://www.merl.com/publications/TR2024-037}
- }
- , "A Model-Based Approach for Improving Reinforcement Learning Efficiency Leveraging Expert Observations", arXiv, February 2024.BibTeX arXiv
- @article{Ozcan2024feb,
- author = {Ozcan, Erhan Can and Giammarino, Vittorio and Queeney, James and Paschalidis, Ioannis Ch.},
- title = {A Model-Based Approach for Improving Reinforcement Learning Efficiency Leveraging Expert Observations},
- journal = {arXiv},
- year = 2024,
- month = feb,
- url = {https://arxiv.org/abs/2402.18836}
- }
- , "Risk-Averse Model Uncertainty for Distributionally Robust Safe Reinforcement Learning", Advances in Neural Information Processing Systems (NeurIPS), A. Oh and T. Neumann and A. Globerson and K. Saenko and M. Hardt and S. Levine, Eds., December 2023, pp. 1659-1680.BibTeX TR2023-143 PDF
- @inproceedings{Queeney2023dec,
- author = {Queeney, James and Benosman, Mouhacine},
- title = {Risk-Averse Model Uncertainty for Distributionally Robust Safe Reinforcement Learning},
- booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
- year = 2023,
- editor = {A. Oh and T. Neumann and A. Globerson and K. Saenko and M. Hardt and S. Levine},
- pages = {1659--1680},
- month = dec,
- publisher = {Curran Associates, Inc.},
- url = {https://www.merl.com/publications/TR2023-143}
- }
- , "Optimal Transport Perturbations for Safe Reinforcement Learning with Robustness Guarantees", Transactions on Machine Learning Research (TMLR), April 2024.
-
Other Publications
- , "Opportunities and Challenges from Using Animal Videos in Reinforcement Learning for Navigation", 22nd IFAC World Congress, 2023.BibTeX
- @Inproceedings{giammarino_2023_ifac,
- author = {Giammarino, Vittorio and Queeney, James and Carstensen, Lucas C. and Hasselmo, Michael E. and Paschalidis, Ioannis Ch.},
- title = {Opportunities and Challenges from Using Animal Videos in Reinforcement Learning for Navigation},
- booktitle = {22nd IFAC World Congress},
- year = 2023
- }
- , "Adversarial Imitation Learning from Visual Observations using Latent Information", 2023.BibTeX
- @Misc{giammarino_2023_laifo,
- author = {Giammarino, Vittorio and Queeney, James and Paschalidis, Ioannis Ch.},
- title = {Adversarial Imitation Learning from Visual Observations using Latent Information},
- year = 2023
- }
- , "Reliable Deep Reinforcement Learning: Stable Training and Robust Deployment", 2023, Boston University.BibTeX
- @Phdthesis{queeney_2023_dissertation,
- author = {Queeney, James},
- title = {Reliable Deep Reinforcement Learning: Stable Training and Robust Deployment},
- school = {Boston University},
- year = 2023
- }
- , "Optimal Transport Perturbations for Safe Reinforcement Learning with Robustness Guarantees", 2023.BibTeX
- @Misc{queeney_2023_otp,
- author = {Queeney, James and Ozcan, Erhan Can and Paschalidis, Ioannis Ch. and Cassandras, Christos G.},
- title = {Optimal Transport Perturbations for Safe Reinforcement Learning with Robustness Guarantees},
- year = 2023
- }
- , "Risk-Averse Model Uncertainty for Distributionally Robust Safe Reinforcement Learning", Advances in Neural Information Processing Systems, 2023, vol. 36.BibTeX
- @Inproceedings{queeney_2023_ramu,
- author = {Queeney, James and Benosman, Mouhacine},
- title = {Risk-Averse Model Uncertainty for Distributionally Robust Safe Reinforcement Learning},
- booktitle = {Advances in Neural Information Processing Systems},
- year = 2023,
- volume = 36,
- publisher = {Curran Associates, Inc.}
- }
- , "Generalized Policy Improvement Algorithms with Theoretically Supported Sample Reuse", 2022.BibTeX
- @Misc{queeney_2022_gpi,
- author = {Queeney, James and Paschalidis, Ioannis Ch. and Cassandras, Christos G.},
- title = {Generalized Policy Improvement Algorithms with Theoretically Supported Sample Reuse},
- year = 2022
- }
- , "Generalized Proximal Policy Optimization with Sample Reuse", Advances in Neural Information Processing Systems, 2021, vol. 34.BibTeX
- @Inproceedings{queeney_2021_geppo,
- author = {Queeney, James and Paschalidis, Ioannis Ch. and Cassandras, Christos G.},
- title = {Generalized Proximal Policy Optimization with Sample Reuse},
- booktitle = {Advances in Neural Information Processing Systems},
- year = 2021,
- volume = 34,
- publisher = {Curran Associates, Inc.}
- }
- , "Uncertainty-Aware Policy Optimization: A Robust, Adaptive Trust Region Approach", Proceedings of the AAAI Conference on Artificial Intelligence, 2021, vol. 35, pp. 9377-9385.BibTeX
- @Inproceedings{queeney_2021_uatrpo,
- author = {Queeney, James and Paschalidis, Ioannis Ch. and Cassandras, Christos G.},
- title = {Uncertainty-Aware Policy Optimization: A Robust, Adaptive Trust Region Approach},
- booktitle = {Proceedings of the {AAAI} Conference on Artificial Intelligence},
- year = 2021,
- volume = 35,
- pages = {9377--9385},
- publisher = {{AAAI} Press}
- }
- , "Opportunities and Challenges from Using Animal Videos in Reinforcement Learning for Navigation", 22nd IFAC World Congress, 2023.