arXiv subjects

Huy T. Tran

Publications and source records attributed to Huy T. Tran.

8 recordsLinked to original sources

arXiv2026

Contraction-Aware Reinforcement Learning for Nonlinear Control with Statistical Robustness

Control contraction metrics (CCMs)-defined by Riemannian metrics under which a closed-loop system is incrementally exponentially stable-offer a constructive framework for synthesizing contracting policies in nonlinear path-tracking problems. However, while the synthesized policies ensure pointwise satisfaction of the CCM conditions, they may not ensure long-term optimality (i.e., minimizing cumulative trajectory-level tracking error) over both transient and steady-state regimes. Furthermore, the myopic nature of these policies could also make them more susceptible to learning biases when approximate dynamics are used to formulate CCMs. To address these issues, we propose to integrate CCMs into reinforcement learning (RL). CCMs provide dynamics-informed feedback for learning a policy that has a stability guarantee-i.e., is contraction-aware-while RL provides a framework for minimizing cumulative tracking error under approximate dynamics. Given a pretrained dynamics model, our algorithm, contraction-aware RL (CARL), simultaneously learns to generate CCMs and optimize a policy for rewards defined by those CCMs. We demonstrate that CARL enhances path-tracking performance and is robust to errors in approximated dynamics compared to relevant baselines in both simulated and real-world robot experiments. We also provide theoretical rationale for integrating CCMs into RL. Our code is available at https://github.com/Mgineer117/CARL, and a video of our real-world robot experiments can be found at https://youtu.be/sOJ4hulbop0.

cs.LG↗

arXiv2026

Pathfinders in the Sky: Formal Decision-Making Models for Collaborative Air Traffic Control in Convective Weather

Air traffic can be significantly disrupted by weather. Pathfinder operations involve assigning a designated aircraft to assess whether airspace that was previously impacted by weather can be safely traversed through. Despite relatively routine use in air traffic control, there is little research on the underlying multi-agent decision-making problem. We seek to address this gap herein by formulating decision models to capture the operational dynamics and implications of pathfinders. Specifically, we construct a Markov chain to represent the stochastic transitions between key operational states (e.g., pathfinder selection). We then analyze its steady-state behavior to understand long-term system dynamics. We also propose models to characterize flight-specific acceptance behaviors (based on utility trade-offs) and pathfinder selection strategies (based on sequential offer allocations). We then conduct a worst-case scenario analysis that highlights risks from collective rejection and explores how selfless behavior and uncertainty affect system resilience. Empirical analysis of data from the US Federal Aviation Administration demonstrates the real-world significance of pathfinder operations and informs future model calibration.

cs.MA↗

arXiv2026

Zero-Shot Coordination in Ad Hoc Teams with Generalized Policy Improvement and Difference Rewards

Real-world multi-agent systems may require ad hoc teaming, where an agent must coordinate with other previously unseen teammates to solve a task in a zero-shot manner. Prior work often either selects a pretrained policy based on an inferred model of the new teammates or pretrains a single policy that is robust to potential teammates. Instead, we propose to leverage all pretrained policies in a zero-shot transfer setting. We formalize this problem as an ad hoc multi-agent Markov decision process and present a solution that uses two key ideas, generalized policy improvement and difference rewards, for efficient and effective knowledge transfer between different teams. We empirically demonstrate that our algorithm, Generalized Policy improvement for Ad hoc Teaming (GPAT), successfully enables zero-shot transfer to new teams in three simulated environments: cooperative foraging, predator-prey, and Overcooked. We also demonstrate our algorithm in a real-world multi-robot setting.

cs.MA↗

arXiv2026

S2Act: Simple Spiking Actor

Spiking neural networks (SNNs) and biologically-inspired learning mechanisms are attractive in mobile robotics, where the size and performance of onboard neural network policies are constrained by power and computational budgets. Existing SNN approaches, such as population coding, reward modulation, and hybrid artificial neural network (ANN)-SNN architectures, have shown promising results; however, they face challenges in complex, highly stochastic environments due to SNN sensitivity to hyperparameters and inconsistent gradient signals. To address these challenges, we propose simple spiking actor (S2Act), a computationally lightweight framework that deploys an RL policy using an SNN in three steps: (1) architect an actor-critic model based on an approximated network of rate-based spiking neurons, (2) train the network with gradients using compatible activation functions, and (3) transfer the trained weights into physical parameters of rate-based leaky integrate-and-fire (LIF) neurons for inference and deployment. By globally shaping LIF neuron parameters such that their rate-based responses approximate ReLU activations, S2Act effectively mitigates the vanishing gradient problem, while pre-constraining LIF response curves reduces reliance on complex SNN-specific hyperparameter tuning. We demonstrate our method in two multi-agent stochastic environments (capture-the-flag and parking) that capture the complexity of multi-robot interactions, and deploy our trained policies on physical TurtleBot platforms using Intel's Loihi neuromorphic hardware. Our experimental results show that S2Act outperforms relevant baselines in task performance and real-time inference in nearly all considered scenarios, highlighting its potential for rapid prototyping and efficient real-world deployment of SNN-based RL policies.

cs.MA↗

arXiv2026

Neuro-Symbolic Generation of Explanations for Robot Policies with Weighted Signal Temporal Logic

Neural network-based policies have demonstrated success in many robotic applications, but often lack human-explanability, which poses challenges in safety-critical deployments. To address this, we propose a neuro-symbolic explanation framework that generates a weighted signal temporal logic (wSTL) specification to describe a robot policy in a interpretable form. Existing methods typically produce explanations that are verbose and inconsistent, which hinders explainability, and loose, which do not give meaningful insights into the underlying policy. We address these issues by introducing a simplification process consisting of predicate filtering, regularization, and iterative pruning. We also introduce three novel explainability evaluation metrics -- conciseness, consistency, and strictness -- to assess explanation quality beyond conventional classification metrics. Our method is validated in three simulated robotic environments, where it outperforms baselines in generating concise, consistent, and strict wSTL explanations without sacrificing classification accuracy. This work bridges policy learning with formal methods, contributing to safer and more transparent decision-making in robotics.

cs.RO↗

arXiv2026

Collaborative Decision-Making and Optimal Utilization of Pathfinding Flights during Convective Weather

Air traffic operations are strongly influenced by convective weather, and one common response is pathfinder operations, in which a designated aircraft tests the viability of weather-impacted airspace and routes. Despite relatively routine use in practice, how pathfinder operations evolve under uncertainty and how the pathfinder decision-making process unfolds are largely treated as exogenous. Addressing this gap requires jointly modeling weather-driven system accessibility, flight responses to pathfinder offers, and the sequencing of those offers to improve outcomes. We develop a unified analytical framework that connects weather-driven system state transitions, flight acceptance decisions, and the sequencing of pathfinder offers. We first construct a four-state Markov chain to model stochastic closure and reopening of exit points, or fixes, out of the terminal departure airspace surrounding a major airport, pathfinder selection, and pathfinding execution, and analyze its steady-state behavior to characterize long-term capacity and delay implications. We introduce utility-based decision models for flights, air traffic control (ATC), and dispatchers, and analyze worst-case collective rejection to quantify system vulnerability under selfless behavior and uncertainty. Finally, we formulate optimization problems that model ATC-initiated and dispatcher-initated pathfinder offers, with the goal of optimizing the sequence of pathfinder offers. Using a discrete event simulation for a major US airport, we show that ATC- and dispatcher-driven objectives lead to distinct, near real-time sequencing strategies, providing the first formal decision models for pathfinder operations under weather uncertainty.

math.OC↗

arXiv2025

On Generating Explanations for Reinforcement Learning Policies: An Empirical Study

Understanding a \textit{reinforcement learning} policy, which guides state-to-action mappings to maximize rewards, necessitates an accompanying explanation for human comprehension. In this paper, we introduce a set of \textit{linear temporal logic} formulae designed to provide explanations for policies, and an algorithm for searching through those formulae for the one that best explains a given policy. Our focus is on explanations that elucidate both the ultimate objectives accomplished by the policy and the prerequisite conditions it upholds throughout its execution. The effectiveness of our proposed approach is illustrated through a simulated game of capture-the-flag and a car-parking environment,

cs.AI↗

arXiv2022

Disentangling Successor Features for Coordination in Multi-agent Reinforcement Learning

Multi-agent reinforcement learning (MARL) is a promising framework for solving complex tasks with many agents. However, a key challenge in MARL is defining private utility functions that ensure coordination when training decentralized agents. This challenge is especially prevalent in unstructured tasks with sparse rewards and many agents. We show that successor features can help address this challenge by disentangling an individual agent's impact on the global value function from that of all other agents. We use this disentanglement to compactly represent private utilities that support stable training of decentralized agents in unstructured tasks. We implement our approach using a centralized training, decentralized execution architecture and test it in a variety of multi-agent environments. Our results show improved performance and training time relative to existing methods and suggest that disentanglement of successor features offers a promising approach to coordination in MARL.

cs.MA↗