6 citations · 15 across the 12 of their papers we have counts for
12 papers
NeSyFS: A Neuro-symbolic Fast-Slow Thinking Framework for LLM Agent under Partial Observability
Duo Xu, Faramarz Fekri
Recently Large Language Models (LLMs) have been increasingly deployed as autonomous agents in applications such as self-reflection, retrieval-augmented generation, and scientific d…
Goal-Oriented Logic-based Semantic Communication for Neuro-Symbolic Reasoning with Applications onto Autonomous Driving
Ahmet Faruk Saz, Duo Xu, Faramarz Fekri
We consider First-Order Logic (FOL)-based semantic communication for neuro-symbolic decision-making in collaborative environments such as autonomous driving networks. Each connecte…
Reinforcement Learning-Augmented LLM Agents for Collaborative Decision Making and Performance Optimization
Dong Qiu, Duo Xu, Limengxi Yue
Large Language Models (LLMs) perform well in language tasks but often lack collaborative awareness and struggle to optimize global performance in multi-agent settings. We present a…
Learning Hidden Subgoals under Temporal Ordering Constraints in Reinforcement Learning
Duo Xu, Faramarz Fekri
In real-world applications, the success of completing a task is often determined by multiple key steps which are distant in time steps and have to be achieved in a fixed time order…
Generalization of Compositional Tasks with Logical Specification via Implicit Planning
Duo Xu, Faramarz Fekri
In this study, we address the challenge of learning generalizable policies for compositional tasks defined by logical specifications. These tasks consist of multiple temporally ext…
LLM-Augmented Symbolic Reinforcement Learning with Landmark-Based Task Decomposition
Alireza Kheirandish, Duo Xu, Faramarz Fekri
One of the fundamental challenges in reinforcement learning (RL) is to take a complex task and be able to decompose it to subtasks that are simpler for the RL agent to learn. In th…
Generalizing LTL Instructions via Future Dependent Options
Duo Xu, Faramarz Fekri
In many real-world applications of control system and robotics, linear temporal logic (LTL) is a widely-used task specification language which has a compositional grammar that natu…
A Framework for Following Temporal Logic Instructions with Unknown Causal Dependencies
Duo Xu, Faramarz Fekri
Teaching a deep reinforcement learning (RL) agent to follow instructions in multi-task environments is a challenging problem. We consider that user defines every task by a linear t…
Interpretable Model-based Hierarchical Reinforcement Learning using Inductive Logic Programming
Duo Xu, Faramarz Fekri
Recently deep reinforcement learning has achieved tremendous success in wide ranges of applications. However, it notoriously lacks data-efficiency and interpretability. Data-effici…
Improving Actor-Critic Reinforcement Learning via Hamiltonian Monte Carlo Method
Duo Xu, Faramarz Fekri
The actor-critic RL is widely used in various robotic control tasks. By viewing the actor-critic RL from the perspective of variational inference (VI), the policy network is traine…
Accelerating Reinforcement Learning Agent with EEG-based Implicit Human Feedback
Duo Xu, Mohit Agarwal, Ekansh Gupta +2
Providing Reinforcement Learning (RL) agents with human feedback can dramatically improve various aspects of learning. However, previous methods require human observer to give inpu…
Learning Nonlinear State Space Models with Hamiltonian Sequential Monte Carlo Sampler
Duo Xu
State space models (SSM) have been widely applied for the analysis and visualization of large sequential datasets. Sequential Monte Carlo (SMC) is a very popular particle-based met…