arXiv subjects

Qing-Shan Jia

Publications and source records attributed to Qing-Shan Jia.

At least 19 recordsLinked to original sources

arXiv2026

Multi-Agent Reinforcement Learning via Agent-Specific Preference

Multi-agent reinforcement learning (MARL) is a powerful framework for solving complex collaborative tasks, but it relies heavily on well-defined global reward functions. Designing such rewards is challenging, especially in systems with heterogeneous agents, where a single scalar objective may fail to capture diverse behaviors. In this paper, we introduce Multi-AGent Preference-Integrated lEarning (MAGPIE), which addresses these challenges through agent-specific preference modeling. Each agent is evaluated by a dedicated expert through preference signals, eliminating the need for global evaluation. We theoretically prove that optimizing these decentralized preferences converges to a Nash equilibrium policy. To integrate local preferences into a coherent global objective, we construct agent-specific reward models from preference data and combine them via a monotonic aggregation mechanism. We further prove that optimizing this aggregate reward model is equivalent to training the Nash equilibrium policy. Extensive experiments on benchmark multi-agent tasks and a sequential production line task show that MAGPIE achieves performance comparable to reward-engineered baselines, demonstrating its potential to facilitate policy learning in scenarios where precise reward engineering is impractical.

cs.LG↗

arXiv2026

COLLIE: Guiding Skill Discovery in Semantically Coherent Latent Space

Unsupervised skill discovery (USD) aims to learn diverse behaviors without reward functions, but often results in task-irrelevant or hazardous behaviors due to uniform exploration. Guided skill discovery (GSD) addresses this issue by incorporating human intent to focus exploration on meaningful regions. However, existing GSD methods typically require training additional guidance models, and rely on pre-defined rules or expert demonstration, which can be ineffective under sparse, online-collected human feedback. To overcome this, we propose COLLIE, a GSD framework that leverages dense unsupervised data to construct a semantically coherent skill latent space. This latent space is well-structured, enabling reliable guidance with sparse online feedback. Moreover, its semantic coherence property enables training-free construction of guidance signals, eliminating the need for additional model training beyond skill learning. Theoretical analysis justifies the effectiveness of our training-free guidance signal, while experiments across diverse state-based and pixel-based tasks show that COLLIE learns diverse, human-aligned skills, avoids hazardous behaviors, and achieves superior downstream performance with minimal human feedback.

cs.LG↗

arXiv2026

Towards provable probabilistic safety for scalable embodied AI systems

Embodied AI systems, comprising AI models and physical plants, are increasingly prevalent across various applications. Due to the rarity of system failures, ensuring their safety in complex operating environments remains a major challenge, which severely hinders their large-scale deployment in safety-critical domains, such as autonomous vehicles, medical devices, and robotics. While achieving provable deterministic safety-verifying system safety across all possible scenarios-remains theoretically ideal, the rarity and complexity of corner cases make this approach impractical for scalable embodied AI systems. Instead, empirical safety evaluation is employed as an alternative, but the absence of provable guarantees imposes significant limitations. To address these issues, we argue for a paradigm shift to provable probabilistic safety that integrates provable guarantees with progressive achievement toward a probabilistic safety boundary on overall system performance. The new paradigm better leverages statistical methods to enhance feasibility and scalability, and a well-defined probabilistic safety boundary enables embodied AI systems to be deployed at scale. In this Perspective, we outline a roadmap for provable probabilistic safety, along with corresponding challenges and potential solutions. By bridging the gap between theoretical safety assurance and practical deployment, this Perspective offers a pathway toward safer, large-scale adoption of embodied AI systems in safety-critical applications.

eess.SY↗

arXiv2026

Representation Learning Enhanced Deep Reinforcement Learning for Optimal Operation of Hydrogen-based Multi-Energy Systems

Hydrogen-based multi-energy systems (HMES) have emerged as a promising low-carbon and energy-efficient solution, as it can enable the coordinated operation of electricity, heating and cooling supply and demand to enhance operational flexibility, improve overall energy efficiency, and increase the share of renewable integration. However, the optimal operation of HMES remains challenging due to the nonlinear and multi-physics coupled dynamics of hydrogen energy storage systems (HESS) (consisting of electrolyters, fuel cells and hydrogen tanks) as well as the presence of multiple uncertainties from supply and demand. To address these challenges, this paper develops a comprehensive operational model for HMES that fully captures the nonlinear dynamics and multi-physics process of HESS. Moreover, we propose an enhanced deep reinforcement learning (DRL) framework by integrating the emerging representation learning techniques, enabling substantially accelerated and improved policy optimization for spatially and temporally coupled complex networked systems, which is not provided by conventional DRL. Experimental studies based on real-world datasets show that the comprehensive model is crucial to ensure the safe and reliable of HESS. In addition, the proposed SR-DRL approaches demonstrate superior convergence rate and performance over conventional DRL counterparts in terms of reducing the operation cost of HMES and handling the system operating constraints. Finally, we provide some insights into the role of representation learning in DRL, speculating that it can reorganize the original state space into a well-structured and cluster-aware geometric representation, thereby smoothing and facilitating the learning process of DRL.

cs.LG↗

arXiv2025

An Equivalent and Unified Virtual Battery Modeling Framework for Flexibility Characterization of Building HVAC Systems

The heating, ventilation and air-conditioning (HVAC) system dominates building's energy consumption and meanwhile exhibits substantial operational flexibility that can be exploited for providing grid services. However, the goal is largely hindered by the difficulty to characterize the system's operating flexibility due to the complex building thermal dynamics, system operating limits and human comfort constraints. To address this challenge, this paper develops an unified virtual battery (VB) modeling framework for characterizing the operating flexibility of both single-zone and multi-zone building HVAC systems, enabling flexible buildings to function like virtual batteries. Specifically, a physically meaningful representation state is first identified to represent building thermal conditions under thermal comfort constraints and a VB model is then established for characterizing the operating flexibility of single-zone HVAC systems. We subsequently extend the VB modeling framework to multi-zone HVAC systems and establish a set of zone-level VB models to characterize the building's zonal operating flexibility. We further develop a systematic method to aggregate the VB models into a low-order and low-complexity aggregated VB model, significantly reducing model and computational complexity. We demonstrate the VB model through demand response (DR) applications and conclude that the VB model can well capture the operating flexibility of building HVAC systems and enable effective DR participation. The DR strategies obtained from the VB model can be efficiently decomposed to zone-level control inputs for maintaining human thermal comfort while achieving near-optimal operation cost.

eess.SY↗

arXiv2025

STAIR: Addressing Stage Misalignment through Temporal-Aligned Preference Reinforcement Learning

Preference-based reinforcement learning (PbRL) bypasses complex reward engineering by learning rewards directly from human preferences, enabling better alignment with human intentions. However, its effectiveness in multi-stage tasks, where agents sequentially perform sub-tasks (e.g., navigation, grasping), is limited by stage misalignment: Comparing segments from mismatched stages, such as movement versus manipulation, results in uninformative feedback, thus hindering policy learning. In this paper, we validate the stage misalignment issue through theoretical analysis and empirical experiments. To address this issue, we propose STage-AlIgned Reward learning (STAIR), which first learns a stage approximation based on temporal distance, then prioritizes comparisons within the same stage. Temporal distance is learned via contrastive learning, which groups temporally close states into coherent stages, without predefined task knowledge, and adapts dynamically to policy changes. Extensive experiments demonstrate STAIR's superiority in multi-stage tasks and competitive performance in single-stage tasks. Furthermore, human studies show that stages approximated by STAIR are consistent with human cognition, confirming its effectiveness in mitigating stage misalignment.

cs.LG↗

arXiv2025

Preference-based Multi-Objective Reinforcement Learning

Multi-objective reinforcement learning (MORL) is a structured approach for optimizing tasks with multiple objectives. However, it often relies on pre-defined reward functions, which can be hard to design for balancing conflicting goals and may lead to oversimplification. Preferences can serve as more flexible and intuitive decision-making guidance, eliminating the need for complicated reward design. This paper introduces preference-based MORL (Pb-MORL), which formalizes the integration of preferences into the MORL framework. We theoretically prove that preferences can derive policies across the entire Pareto frontier. To guide policy optimization using preferences, our method constructs a multi-objective reward model that aligns with the given preferences. We further provide theoretical proof to show that optimizing this reward model is equivalent to training the Pareto optimal policy. Extensive experiments in benchmark multi-objective tasks, a multi-energy management task, and an autonomous driving task on a multi-line highway show that our method performs competitively, surpassing the oracle method, which uses the ground truth reward function. This highlights its potential for practical applications in complex real-world systems.

cs.LG↗

arXiv2025

CLARIFY: Contrastive Preference Reinforcement Learning for Untangling Ambiguous Queries

Preference-based reinforcement learning (PbRL) bypasses explicit reward engineering by inferring reward functions from human preference comparisons, enabling better alignment with human intentions. However, humans often struggle to label a clear preference between similar segments, reducing label efficiency and limiting PbRL's real-world applicability. To address this, we propose an offline PbRL method: Contrastive LeArning for ResolvIng Ambiguous Feedback (CLARIFY), which learns a trajectory embedding space that incorporates preference information, ensuring clearly distinguished segments are spaced apart, thus facilitating the selection of more unambiguous queries. Extensive experiments demonstrate that CLARIFY outperforms baselines in both non-ideal teachers and real human feedback settings. Our approach not only selects more distinguished queries but also learns meaningful trajectory embeddings.

cs.LG↗

arXiv2025

Robust Co-Optimization of Distribution Network Hardening and Mobile Resource Scheduling with Decision-Dependent Uncertainty

This paper studies the robust co-planning of proactive network hardening and mobile hydrogen energy resources (MHERs) scheduling, which is to enhance the resilience of power distribution network (PDN) against the disastrous events. A decision-dependent robust optimization model is formulated with min-max resilience constraint and discrete recourse structure, which helps achieve the load survivability target considering endogenous uncertainties. Different from the traditional model with a fixed uncertainty set, we adopt a dynamic representation that explicitly captures the endogenous uncertainties of network contingency as well as the available hydrogen storage levels of MHERs, which induces a decision-dependent uncertainty (DDU) set. Also, the multi-period adaptive routing and energy scheduling of MHERs are modeled as a mixed-integer recourse problem for further decreasing the resilience cost. Then, a nested parametric column-and-constraint generation (N-PC&CG) algorithm is customized and developed to solve this challenging formulation. By leveraging the structural property of the DDU set as well as the combination of discrete recourse decisions and the corresponding extreme points, we derive a strengthened solution scheme with nontrivial enhancement strategies to realize efficient and exact computation. Numerical results on 14-bus test system and 56-bus real-world distribution network demonstrate the resilience benefits and economical feasibility of the proposed method under different damage severity levels. Moreover, the enhanced N-PC&CG shows a superior solution capability to support prompt decisions for resilient planning with DDU models.

eess.SY↗

arXiv2025

Proactive Robust Hardening of Resilient Power Distribution Network: Decision-Dependent Uncertainty Modeling and Fast Solution Strategy

To address the power system hardening problem, traditional approaches often adopt robust optimization (RO) that considers a fixed set of concerned contingencies, regardless of the fact that hardening some components actually renders relevant contingencies impractical. In this paper, we directly adopt a dynamic uncertainty set that explicitly incorporates the impact of hardening decisions on the worst-case contingencies, which leads to a decision-dependent uncertainty (DDU) set. Then, a DDU-based robust-stochastic optimization (DDU-RSO) model is proposed to support the hardening decisions on distribution lines and distributed generators (DGs). Also, the randomness of load variations and available storage levels is considered through stochastic programming (SP) in the innermost level problem. Various corrective measures (e.g., the joint scheduling of DGs and energy storage) are included, coupling with a finite support of stochastic scenarios, for resilience enhancement. To relieve the computation burden of this new hardening formulation, an enhanced customization of parametric column-and-constraint generation (P-C&CG) algorithm is developed. By leveraging the network structural information, the enhancement strategies based on resilience importance indices are designed to improve the convergence performance. Numerical results on 33-bus and 118-bus test distribution networks have demonstrated the effectiveness of DDU-RSO aided hardening scheme. Furthermore, in comparison to existing solution methods, the enhanced P-C&CG has achieved a superior performance by reducing the solution time by a few orders of magnitudes.

eess.SY↗

arXiv2024

Query-Policy Misalignment in Preference-Based Reinforcement Learning

Preference-based reinforcement learning (PbRL) provides a natural way to align RL agents' behavior with human desired outcomes, but is often restrained by costly human feedback. To improve feedback efficiency, most existing PbRL methods focus on selecting queries to maximally improve the overall quality of the reward model, but counter-intuitively, we find that this may not necessarily lead to improved performance. To unravel this mystery, we identify a long-neglected issue in the query selection schemes of existing PbRL studies: Query-Policy Misalignment. We show that the seemingly informative queries selected to improve the overall quality of reward model actually may not align with RL agents' interests, thus offering little help on policy learning and eventually resulting in poor feedback efficiency. We show that this issue can be effectively addressed via near on-policy query and a specially designed hybrid experience replay, which together enforce the bidirectional query-policy alignment. Simple yet elegant, our method can be easily incorporated into existing approaches by changing only a few lines of code. We showcase in comprehensive experiments that our method achieves substantial gains in both human feedback and RL sample efficiency, demonstrating the importance of addressing query-policy misalignment in PbRL tasks.

cs.LG↗

arXiv2023

Mind the Gap: Offline Policy Optimization for Imperfect Rewards

Reward function is essential in reinforcement learning (RL), serving as the guiding signal to incentivize agents to solve given tasks, however, is also notoriously difficult to design. In many cases, only imperfect rewards are available, which inflicts substantial performance loss for RL agents. In this study, we propose a unified offline policy optimization approach, \textit{RGM (Reward Gap Minimization)}, which can smartly handle diverse types of imperfect rewards. RGM is formulated as a bi-level optimization problem: the upper layer optimizes a reward correction term that performs visitation distribution matching w.r.t. some expert data; the lower layer solves a pessimistic RL problem with the corrected rewards. By exploiting the duality of the lower layer, we derive a tractable algorithm that enables sampled-based learning without any online interactions. Comprehensive experiments demonstrate that RGM achieves superior performance to existing methods under diverse settings of imperfect rewards. Further, RGM can effectively correct wrong or inconsistent rewards against expert preference and retrieve useful information from biased rewards.

cs.LG↗

arXiv2022

Towards Efficient Dynamic Uplink Scheduling over Multiple Unknown Channels

Age-of-Information (AoI) is a critical metric for network applications. Existing works mostly address optimization with homogeneous AoI requirements, which is different from practice. In this work, we optimize uplink scheduling for an access point (AP) over multiple unknown channels with heterogeneous AoI requirements defined by AoI-dependent costs. The AP serves $N$ users by using $M$ channels without the channel state information. Each channel serves only one user in each decision epoch. The optimization objective is to minimize the time-averaged AoI-dependent costs plus additional communication transmission costs over an infinite horizon. This decision-making problem can be formulated as a Markov decision process, but it is computationally intractable because the size of the state space grows exponentially with respect to the number of users. To alleviate the challenge, we reformulate the problem as a variant of the restless multi-armed bandit (RMAB) problem and leverage Whittle's index theory to design an index-based scheduling policy algorithm. We derive an analytic formula for the indices, which reduces the computational overhead and facilitates online adaptation. Our numerical examples show that our index-based scheduling policy achieves comparable performance to the optimal policy and outperforms several other heuristics.

eess.SY↗

arXiv2022

A Two-phase On-line Joint Scheduling for Welfare Maximization of Charging Station

The large adoption of EVs brings practical interest to the operation optimization of the charging station. The joint scheduling of pricing and charging control will achieve a win-win situation both for the charging station and EV drivers, thus enhancing the operational capability of the station. We consider this important problem in this paper and make the following contributions. First, a joint scheduling model of pricing and charging control is developed to maximize the expected social welfare of the charging station considering the Quality of Service and the price fluctuation sensitivity of EV drivers. It is formulated as a Markov decision process with variance criterion to capture uncertainties during operation. Second, a two-phase on-line policy learning algorithm is proposed to solve this joint scheduling problem. In the first phase, it implements event-based policy iteration to find the optimal pricing scheme, while in the second phase, it implements scenario-based model predictive control for smart charging under the updated pricing scheme. Third, by leveraging the performance difference theory, the optimality of the proposed algorithm is theoretically analyzed. Numerical experiments for a charging station with distributed generation and energy storage demonstrate the effectiveness of the proposed method and the improved social welfare of the charging station.

eess.SY↗

arXiv2022

Proximal ADMM for Nonconvex and Nonsmooth Optimization

By enabling the nodes or agents to solve small-sized subproblems to achieve coordination, distributed algorithms are favored by many networked systems for efficient and scalable computation. While for convex problems, substantial distributed algorithms are available, the results for the more broad nonconvex counterparts are extremely lacking. This paper develops a distributed algorithm for a class of nonconvex and nonsmooth problems featured by i) a nonconvex objective formed by both separate and composite objective components regarding the decision components of interconnected agents, ii) local bounded convex constraints, and iii) coupled linear constraints. This problem is directly originated from smart buildings and is also broad in other domains. To provide a distributed algorithm with convergence guarantee, we revise the powerful tool of alternating direction method of multiplier (ADMM) and proposed a proximal ADMM. Specifically, noting that the main difficulty to establish the convergence for the nonconvex and nonsmooth optimization within the ADMM framework is to assume the boundness of dual updates, we propose to update the dual variables in a discounted manner. This leads to the establishment of a so-called sufficiently decreasing and lower bounded Lyapunov function, which is critical to establish the convergence. We prove that the method converges to some approximate stationary points. We besides showcase the efficacy and performance of the method by a numerical example and the concrete application to multi-zone heating, ventilation, and air-conditioning (HVAC) control in smart buildings.

math.OC↗

arXiv2022

A Survey of ADMM Variants for Distributed Optimization: Problems, Algorithms and Features

By coordinating terminal smart devices or microprocessors to engage in cooperative computation to achieve systemlevel targets, distributed optimization is incrementally favored by both engineering and computer science. The well-known alternating direction method of multipliers (ADMM) has turned out to be one of the most popular tools for distributed optimization due to many advantages, such as modular structure, superior convergence, easy implementation and high flexibility. In the past decade, ADMM has experienced widespread developments. The developments manifest in both handling more general problems and enabling more effective implementation. Specifically, the method has been generalized to broad classes of problems (i.e.,multi-block, coupled objective, nonconvex, etc.). Besides, it has been extensively reinforced for more effective implementation, such as improved convergence rate, easier subproblems, higher computation efficiency, flexible communication, compatible with inaccurate information, robust to communication delays, etc. These developments lead to a plentiful of ADMM variants to be celebrated by broad areas ranging from smart grids, smart buildings, wireless communications, machine learning and beyond. However, there lacks a survey to document those developments and discern the results. To achieve such a goal, this paper provides a comprehensive survey on ADMM variants. Particularly, we discern the five major classes of problems that have been mostly concerned and discuss the related ADMM variants in terms of main ideas, main assumptions, convergence behaviors and main features. In addition, we figure out several important future research directions to be addressed. This survey is expected to work as a tutorial for both developing distributed optimization in broad areas and identifying existing theoretical research gaps.

cs.DC↗

arXiv2021

An Actor-Critic Method for Simulation-Based Optimization

We focus on a simulation-based optimization problem of choosing the best design from the feasible space. Although the simulation model can be queried with finite samples, its internal processing rule cannot be utilized in the optimization process. We formulate the sampling process as a policy searching problem and give a solution from the perspective of Reinforcement Learning (RL). Concretely, Actor-Critic (AC) framework is applied, where the Actor serves as a surrogate model to predict the performance on unknown designs, whereas the actor encodes the sampling policy to be optimized. We design the updating rule and propose two algorithms for the cases where the feasible spaces are continuous and discrete respectively. Some experiments are designed to validate the effectiveness of proposed algorithms, including two toy examples, which intuitively explain the algorithms, and two more complex tasks, i.e., adversarial attack task and RL task, which validate the effectiveness in large-scale problems. The results show that the proposed algorithms can successfully deal with these problems. Especially note that in the RL task, our methods give a new perspective to robot control by treating the task as a simulation model and solving it by optimizing the policy generating process, while existing works commonly optimize the policy itself directly.

cs.LG↗

arXiv2021

Decentralized Multi-Agent Reinforcement Learning: An Off-Policy Method

We discuss the problem of decentralized multi-agent reinforcement learning (MARL) in this work. In our setting, the global state, action, and reward are assumed to be fully observable, while the local policy is protected as privacy by each agent, and thus cannot be shared with others. There is a communication graph, among which the agents can exchange information with their neighbors. The agents make individual decisions and cooperate to reach a higher accumulated reward. Towards this end, we first propose a decentralized actor-critic (AC) setting. Then, the policy evaluation and policy improvement algorithms are designed for discrete and continuous state-action-space Markov Decision Process (MDP) respectively. Furthermore, convergence analysis is given under the discrete-space case, which guarantees that the policy will be reinforced by alternating between the processes of policy evaluation and policy improvement. In order to validate the effectiveness of algorithms, we design experiments and compare them with previous algorithms, e.g., Q-learning \cite{watkins1992q} and MADDPG \cite{lowe2017multi}. The results show that our algorithms perform better from the aspects of both learning speed and final performance. Moreover, the algorithms can be executed in an off-policy manner, which greatly improves the data efficiency compared with on-policy algorithms.

cs.MA↗