Yao Chen

Reinforcement learning is increasingly deployed in autonomous systems whose reward functions encode operational priorities and decision-making objectives. However, observable behavior can enable external observers to infer sensitive reward parameters through inverse reinforcement learning. Existing deployment-time defenses mainly rely on action randomization or deception, without explicitly accounting for how previously released behavior affects the additional reward-sensitive information contributed by subsequent actions. To address this gap, we propose FisherShield, a deployment-time mechanism that balances task value against marginal reward-information exposure. Under a specified reference observer model, FisherShield computes the sensitivity of action log-likelihoods to the private reward and accumulates the sensitivity directions of released actions in an empirical information matrix. For each candidate action, the increase in the matrix’s log-determinant measures its marginal reference-score exposure and is converted into a weighted penalty subtracted from the task value. Updating the matrix after each release makes the penalty depend on the observation history, enabling sequential exposure control without retraining the task policy. Experiments show that FisherShield reduces cumulative reference-score log-det exposure by 26.4% in FourRooms and 34.3% in LavaGrid relative to Expert while preserving near-expert utility. The results are limited to the specified reference-model Bayesian observer and do not establish robustness to model misspecification or a defense-aware attacker.

UAV pursuit–evasion in multi-obstacle environments constitutes a safety-critical decision-making problem in which the pursuer must intercept a maneuvering evader while satisfying obstacle-avoidance constraints. Existing safety-constrained methods typically optimize expected safety costs or apply immediate interventions, but they do not explicitly determine when recovery should begin once finite-horizon risk emerges. To address this issue, we propose the ReSwitch framework, which separates task-oriented pursuit from safety-oriented recovery. When flight risk emerges, a value-preserving switch-time planner evaluates candidate switching times through opponent-conditioned hybrid rollouts. The feasible switch time with the largest pursuit value after recovery is selected for execution, allowing the controller to prioritize safety while preserving pursuit effectiveness whenever possible. Experiments demonstrate that ReSwitch achieves a mean success rate of 89.02% and a physical safety rate of 91.67%, showing favorable performance compared with the baselines. These results indicate that ReSwitch provides a favorable pursuit–safety trade-off under the tested conditions.

The asymmetric semantic information within directionality makes directed network embedding essentially different from undirected network embedding. Existing directed network embedding methods, explicitly or implicitly, are established by preserving pairwise interactions yet distinguishing in-direction and out-direction. Noticing that the inherent semantic connotation of edge directions is still seldom leveraged to enhance directed network embedding, in this work, we propose a novel random walk embedding framework named RW4CF to encode hierarchical collaborative filtering features within directed networks. In detail, we interpret the directed link as a type of user-item interaction and formulate the concept of hierarchical collaborative filtering matrices as a heuristic structural feature for directed network embedding. Specifically, we incorporate a collaborative filtering window in the random walk scheme to encode collaborative filtering information. Theoretical analysis is given to prove that the obtained embedding by RW4CF is indeed a factorization of the hierarchical collaborative filtering matrices of the directed network. Moreover, to validate the efficiency of RW4CF, we conduct extensive experiments on directed network datasets and demonstrate the superior performances of RW4CF than the state-of-the-arts.

Cooperative operations in which a UAV advances ahead of a UGV to conduct forward reconnaissance are critical in disaster relief and urban inspection missions. Prevalent air–ground coordination methods operate under the assumption of ideal communication or treat connectivity as a secondary objective. However, obstacle occlusion, such as high-rise buildings in urban areas and mountainous terrain, results in Non-Line-of-Sight (NLOS) conditions, disrupting communication between the two platforms. To address these challenges, this paper introduces a cooperative control framework based on dynamically varying modulation matrices for both the UAV and the UGV. By evaluating and mapping occlusion risks in real time, the cooperative motions of the UAV and UGV are adaptively adjusted to maintain Line-of-Sight (LOS). An LOS assessment function is designed and mapped to the eigenvalues of the modulation matrices, enabling smooth and adaptive coordination under changing environmental conditions while avoiding the limitations of traditional discrete mode-switching strategies. Theoretical analysis and simulation results confirm that the proposed approach not only ensures stable LOS connectivity but also enhances trajectory smoothness, adaptability, and computational efficiency.

In adversarial reinforcement learning, designing dense reward functions is a traditional approach to address the sparsity of adversarial objectives. However, conventional reward design often relies on high-quality domain knowledge and may fail in practice, thereby inducing objective misalignment—a discrepancy between optimizing the designed reward and achieving the true adversarial utility. To reduce this discrepancy, a Value-Based Reward Shaping (VBRS) framework is proposed. VBRS integrates an intrinsic state-value estimate, which is a dynamic predictor of long-term utility, into the immediate reward function. As a result, exploration can be encouraged toward states predicted to be strategically advantageous, potentially avoiding some local optima in practice. Experiments demonstrate that VBRS outperforms a baseline that relies solely on the original reward function. The results confirm that the proposed method enhances adversarial performance and helps bridge the gap between designed reward guidance and the adversarial objective.

This study is concerned with probabilistic Boolean control networks (PBCNs) with state feedback control. A novel definition of bisimilar PBCNs is proposed

Given a distributed coordination algorithm (DCA) for agents coupled by a network, which can be characterized by a stochastic matrix, we say that the DCA can be asynchronously implemented if the consensus property is preserved when the agents are activated to update their states according to their own clocks. This paper focuses on two central problems in asynchronous implementation of DCA: which class of DCA can be asynchronously implemented, and which other cannot. We identify two types of stochastic matrices, called partially scrambling and essentially cyclic matrices, for which we prove that DCA associated with a partially scrambling matrix can be asynchronously implemented, and there exists at least one asynchronous implementation sequence, which fails to realize consensus for DCA associated with an essentially cyclic matrix.