Accelerating Reinforcement Learning using EEG-based implicit human feedback D Xu, M Agarwal, E Gupta, F Fekri, R Sivakumar Neurocomputing 460, 139-153, 2021 | 41* | 2021 |
Interpretable model-based hierarchical reinforcement learning using inductive logic programming D Xu, F Fekri arXiv preprint arXiv:2106.11417, 2021 | 12 | 2021 |
Playing games with implicit human feedback D Xu, M Agarwal, F Fekri, R Sivakumar Workshop on Reinforcement Learning in Games, AAAI 6, 2020 | 10 | 2020 |
Time series prediction via recurrent neural networks with the information bottleneck principle D Xu, F Fekri 2018 IEEE 19th International Workshop on Signal Processing Advances in …, 2018 | 10 | 2018 |
Improving Actor-Critic Reinforcement Learning via Hamiltonian Monte Carlo Method D Xu, F Fekri IEEE Transactions on Artificial Intelligence, 2022 | 9 | 2022 |
Generalization of Temporal Logic Tasks via Future Dependent Options D Xu, F Fekri Machine Learning, 2024 | 3* | 2024 |
A Framework for Following Temporal Logic Instructions with Unknown Causal Dependencies D Xu, F Fekri IJCNN 2022 (Oral), 2022 | 3* | 2022 |
Learning Hidden Subgoals under Temporal Ordering Constraints in Reinforcement Learning D Xu, F Fekri arXiv preprint arXiv:2411.01425, 2024 | | 2024 |
Generalization of Compositional Tasks with Logical Specification via Implicit Planning D Xu, F Fekri arXiv preprint arXiv:2410.09686, 2024 | | 2024 |
LLM-Augmented Symbolic Reinforcement Learning with Landmark-Based Task Decomposition A Kheirandish, D Xu, F Fekri arXiv preprint arXiv:2410.01929, 2024 | | 2024 |