Duo Xu

16 papers B 1Misc 2Journal 12Unranked 1

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	HDCS: Hierarchy Discovery and Critic Shaping for Reinforcement Learning with Automaton Specification. Trans. Mach. Learn. Res. Duo Xu, Faramarz Fekri
2025	Misc	`conf`	LLM-Augmented Symbolic RL with Landmark-Based Task Decomposition. ICASSP Alireza Kheirandish, Duo Xu, Faramarz Fekri
2024	J	`jnl`	Generalization of Compositional Tasks with Logical Specification via Implicit Planning. CoRR Duo Xu, Faramarz Fekri
2024	J	`jnl`	Generalization of temporal logic tasks via future dependent options. Mach. Learn. Duo Xu, Faramarz Fekri
2024	J	`jnl`	LLM-Augmented Symbolic Reinforcement Learning with Landmark-Based Task Decomposition. CoRR Alireza Kheirandish, Duo Xu, Faramarz Fekri
2024	J	`jnl`	Learning Hidden Subgoals under Temporal Ordering Constraints in Reinforcement Learning. CoRR Duo Xu, Faramarz Fekri
2023	J	`jnl`	Improving Actor-Critic Reinforcement Learning via Hamiltonian Monte Carlo Method. IEEE Trans. Artif. Intell. Duo Xu, Faramarz Fekri
2022	J	`jnl`	A Framework for Following Temporal Logic Instructions with Unknown Causal Dependencies. CoRR Duo Xu, Faramarz Fekri
2022	J	`jnl`	Generalizing LTL Instructions via Future Dependent Options. CoRR Duo Xu, Faramarz Fekri
2022	Misc	`conf`	Improving Actor-Critic Reinforcement Learning Via Hamiltonian Monte Carlo Method. ICASSP Duo Xu, Faramarz Fekri
2022	B	`conf`	Integrating Symbolic Planning and Reinforcement Learning for Following Temporal Logic Specifications. IJCNN Duo Xu, Faramarz Fekri
2021	J	`jnl`	Accelerating Reinforcement Learning using EEG-based implicit human feedback. Neurocomputing Duo Xu, Mohit Agarwal, Ekansh Gupta, Faramarz Fekri, Raghupathy Sivakumar
2021	J	`jnl`	Improving Actor-Critic Reinforcement Learning via Hamiltonian Policy. CoRR Duo Xu, Faramarz Fekri
2021	J	`jnl`	Interpretable Model-based Hierarchical Reinforcement Learning using Inductive Logic Programming. CoRR Duo Xu, Faramarz Fekri
2020	J	`jnl`	Accelerating Reinforcement Learning Agent with EEG-based Implicit Human Feedback. CoRR Duo Xu, Mohit Agarwal, Faramarz Fekri, Raghupathy Sivakumar
2018	—	`conf`	Time Series Prediction Via Recurrent Neural Networks with the Information Bottleneck Principle. SPAWC Duo Xu, Faramarz Fekri