Transfer learning via minimizing the performance gap between domains B Wang, JA Mendez, M Cai, E Eaton Advances in Neural Information Processing Systems, 2019 | 75 | 2019 |
Modular lifelong reinforcement learning via neural composition JA Mendez, H van Seijen, E Eaton International Conference on Learning Representations, 2022 | 50 | 2022 |
Lifelong learning of compositional structures JA Mendez, E Eaton International Conference on Learning Representations, 2021 | 43 | 2021 |
Lifelong policy gradient learning of factored policies for faster training without forgetting JA Mendez, B Wang, E Eaton Advances in Neural Information Processing Systems, 2020 | 41 | 2020 |
How to reuse and compose knowledge for a lifetime of tasks: A survey on continual learning and functional composition JA Mendez, E Eaton Transactions on Machine Learning Research, 2023 | 32 | 2023 |
A domain-agnostic approach for characterization of lifelong learning systems MM Baker, A New, M Aguilar-Simon, Z Al-Halah, SMR Arnold, ... Neural Networks 160, 274-296, 2023 | 25 | 2023 |
Lifelong inverse reinforcement learning JA Mendez, S Shivkumar, E Eaton Advances in Neural Information Processing Systems, 2018 | 20 | 2018 |
Embodied lifelong learning for task and motion planning J Mendez-Mendez, LP Kaelbling, T Lozano-Pérez Conference on Robot Learning, 2134-2150, 2023 | 19 | 2023 |
CompoSuite: A Compositional Reinforcement Learning Benchmark JA Mendez*, M Hussing*, M Gummadi, E Eaton Conference on Lifelong Learning Agents, 2022 | 13 | 2022 |
Gap Minimization for Knowledge Sharing and Transfer B Wang, JA Mendez, C Shui, F Zhou, D Wu, X Gezheng, C Gagné, ... Journal of Machine Learning Research 24 (33), 1-57, 2023 | 10 | 2023 |
SHELS: Exclusive Feature Sets for Novelty Detection and Continual Learning Without Class Boundaries M Gummadi, C Kent, JA Mendez, E Eaton Conference on Lifelong Learning Agents, 2022 | 10 | 2022 |
Reinforcement learning of multi-domain dialog policies via action embeddings JA Mendez, A Geramifard, M Ghavamzadeh, B Liu Conversational AI Workshop at NeurIPS, 2019 | 8 | 2019 |
Robotic Manipulation Datasets for Offline Compositional Reinforcement Learning M Hussing*, JA Mendez*, C Kent, E Eaton CoRL Workshop on Pre-training Robot Learning, 2022 | 6 | 2022 |
Improving Black-box Robustness with In-Context Rewriting K O'Brien, N Ng, I Puri, J Mendez-Mendez, H Palangi, Y Kim, M Ghassemi, ... Transactions on Machine Learning Research (TMLR), 2024 | 2 | 2024 |
Lifelong Machine Learning of Functionally Compositional Structures JA Méndez University of Pennsylvania, 2022 | 2 | 2022 |
Learning Long-Horizon Action Dependencies in Sampling-Based Bilevel Planning B Cieślar, LP Kaelbling, T Lozano-Pérez, J Mendez-Mendez 8th Annual Conference on Robot Learning, 2024 | | 2024 |
Continual Improvement of Threshold-Based Novelty Detection A Ejilemele, J Mendez-Mendez arXiv preprint arXiv:2309.02551, 2023 | | 2023 |
A General Framework for Continual Learning of Compositional Structures JA Mendez, E Eaton Continual Learning Workshop at ICML, 2020 | | 2020 |