Sequential Resource Allocation with situational constraints presents a significant challenge in real-world applications, where resource demands and priorities are context-dependent. This paper introduces a novel framework, SCRL, to address this problem. We formalize situational constraints as logic implications and develop a new algorithm that dynamically penalizes constraint violations. To handle situational constraints effectively, we propose a probabilistic selection mechanism to overcome limitations of traditional constraint reinforcement learning (CRL) approaches. We evaluate SCRL across two scenarios: medical resource allocation during a pandemic and pesticide distribution in agriculture. Experiments demonstrate that SCRL outperforms existing baselines in satisfying constraints while maintaining high resource efficiency, showcasing its potential for real-world, context-sensitive decision-making tasks.

--T o empower precision agriculture through distributed machine learning (DML), split learning (SL) has emerged as a promising paradigm, partitioning deep neural networks (DNNs) between edge devices and servers to reduce computational burdens and preserve data privacy. However, conventional SL frameworks' one-split-fits-all strategy is a critical limitation in agricultural ecosystems where edge insect monitoring devices exhibit vast heterogeneity in computational power, energy constraints, and connectivity. This leads to straggler bottlenecks, inefficient resource utilization, and compromised model performance. Bridging this gap, we introduce ReinDSplit, a novel reinforcement learning (RL)-driven framework that dynamically tailors DNN split points for each device, optimizing efficiency without sacrificing accuracy. Specifically, a Q-learning agent acts as an adaptive orchestrator, balancing workloads and latency thresholds across devices to mitigate computational starvation or overload. By framing split layer selection as a finite-state Markov decision process, ReinDSplit convergence ensures that highly constrained devices contribute meaningfully to model training over time.

The job shop scheduling problem is an NP-hard combinatorial optimization problem relevant to manufacturing and timetabling. Traditional approaches use priority dispatching rules based on simple heuristics. Recent work has attempted to replace these with deep learning models, particularly graph neural networks (GNNs), that learn to assign priorities from data. However, training such models requires customizing numerous factors: graph representation, node features, action space, and reward functions. The lack of modular libraries for experimentation makes this research time-consuming. This work introduces JobShopLib, a modular library that allows customizing these factors and creating new components with its reinforcement learning environment. We trained several dispatchers through imitation learning to demonstrate the environment's utility. One model outperformed various graph-based dispatchers using only individual operation features, highlighting the importance of feature customization. Our GNN model achieved near state-of-the-art results on large-scale problems. These results suggest significant room for improvement in developing such models. JobShopLib provides the necessary tools for future experimentation.

Despite the recent advancements in artificial intelligence technologies have shown great potential in improving transport efficiency and safety, autonomous vehicles(AVs) still face great challenge of driving in time-varying traffic flow, especially in dense and interactive situations. Meanwhile, human have free wills and usually do not make the same decisions even situate in the exactly same scenarios, leading to the data-driven methods suffer from poor migratability and high search cost problems, decreasing the efficiency and effectiveness of the behavior policy. In this research, we propose a safety-first human-like decision-making framework(SF-HLDM) for AVs to drive safely, comfortably, and social compatiblely in effiency. The framework integrates a hierarchical progressive framework, which combines a spatial-temporal attention (S-TA) mechanism for other road users' intention inference, a social compliance estimation module for behavior regulation, and a Deep Evolutionary Reinforcement Learning(DERL) model for expanding the search space efficiently and effectively to make avoidance of falling into the local optimal trap and reduce the risk of overfitting, thus make human-like decisions with interpretability and flexibility. The SF-HLDM framework enables autonomous driving AI agents dynamically adjusts decision parameters to maintain safety margins and adhering to contextually appropriate driving behaviors at the same time.

Unsupervised Reinforcement Learning (RL) aims to discover diverse behaviors that can accelerate the learning of downstream tasks. Previous methods typically focus on entropy-based exploration or empowerment-driven skill learning. However, entropy-based exploration struggles in large-scale state spaces (e.g., images), and empowerment-based methods with Mutual Information (MI) estimations have limitations in state exploration. To address these challenges, we propose a novel skill discovery objective that maximizes the deviation of the state density of one skill from the explored regions of other skills, encouraging inter-skill state diversity similar to the initial MI objective. For state-density estimation, we construct a novel conditional autoencoder with soft modularization for different skill policies in high-dimensional space. Meanwhile, to incentivize intra-skill exploration, we formulate an intrinsic reward based on the learned autoencoder that resembles count-based exploration in a compact latent space. Through extensive experiments in challenging state and image-based tasks, we find our method learns meaningful skills and achieves superior performance in various downstream tasks.

In standard Reinforcement Learning (RL) settings, the interaction between the agent and the environment is typically modeled as a Markov Decision Process (MDP), which assumes that the agent observes the system state instantaneously, selects an action without delay, and executes it immediately. In real-world dynamic environments, such as cyber-physical systems, this assumption often breaks down due to delays in the interaction between the agent and the system. These delays can vary stochastically over time and are typically unobservable, meaning they are unknown when deciding on an action. Existing methods deal with this uncertainty conservatively by assuming a known fixed upper bound on the delay, even if the delay is often much lower. In this work, we introduce the interaction layer, a general framework that enables agents to adaptively and seamlessly handle unobservable and time-varying delays. Specifically, the agent generates a matrix of possible future actions to handle both unpredictable delays and lost action packets sent over networks. Building on this framework, we develop a model-based algorithm, Actor-Critic with Delay Adaptation (ACDA), which dynamically adjusts to delay patterns. Our method significantly outperforms state-of-the-art approaches across a wide range of locomotion benchmark environments.

--High-density Wi-Fi deployments often result in significant co-channel interference, which degrades overall network performance. T o address this issue, coordination of multi access points (APs) has been considered to enable coordinated spatial reuse (CSR) in next generation wireless local area networks. This paper tackles the challenge of downlink spatial reuse in Wi-Fi networks, specifically in scenarios involving overlapping basic service sets, by employing hierarchical multi-agent reinforcement learning (HMARL). We decompose the CSR process into two phases, i.e., a polling phase and a decision phase, and introduce the HMARL algorithm to enable efficient CSR. T o enhance training efficiency, the proposed HMARL algorithm employs a hierarchical structure, where station selection and power control are determined by a high-and low-level policy network, respectively. Simulation results demonstrate that this approach consistently outperforms baseline methods in terms of throughput and latency across various network topologies. Moreover, the algorithm exhibits robust performance when coexisting with legacy APs. Additional experiments in a representative topology further reveal that the carefully designed reward function not only maximizes the overall network throughput, but also improves fairness in transmission opportunities for APs in high-interference regions. Index T erms --Overlapping basic service set, channel access, multi-agent reinforcement learning, coordinated spatial reuse. Wi-Fi has become a pivotal technology in wireless local area networks (WLANs), with the latest commercial technologies Wi-Fi 6 [1] and Wi-Fi 7 [2] widely deployed in various scenarios to provide users with high data rate coverage.

Developing agents capable of exploring, planning and learning in complex open-ended environments is a grand challenge in artificial intelligence (AI). Hierarchical reinforcement learning (HRL) offers a promising solution to this challenge by discovering and exploiting the temporal structure within a stream of experience. The strong appeal of the HRL framework has led to a rich and diverse body of literature attempting to discover a useful structure. However, it is still not clear how one might define what constitutes good structure in the first place, or the kind of problems in which identifying it may be helpful. This work aims to identify the benefits of HRL from the perspective of the fundamental challenges in decision-making, as well as highlight its impact on the performance trade-offs of AI agents. Through these benefits, we then cover the families of methods that discover temporal structure in HRL, ranging from learning directly from online experience to offline datasets, to leveraging large language models (LLMs). Finally, we highlight the challenges of temporal structure discovery and the domains that are particularly well-suited for such endeavours.

In Reinforcement Learning (RL), regularization has emerged as a popular tool both in theory and practice, typically based either on an entropy bonus or a Kullback-Leibler divergence that constrains successive policies. In practice, these approaches have been shown to improve exploration, robustness and stability, giving rise to popular Deep RL algorithms such as SAC and TRPO. Policy Mirror Descent (PMD) is a theoretical framework that solves this general regularized policy optimization problem, however the closed-form solution involves the sum of all past Q-functions, which is intractable in practice. We propose and analyze PMD-like algorithms that only keep the last $M$ Q-functions in memory, and show that for finite and large enough $M$, a convergent algorithm can be derived, introducing no error in the policy update, unlike prior deep RL PMD implementations. StaQ, the resulting algorithm, enjoys strong theoretical guarantees and is competitive with deep RL baselines, while exhibiting less performance oscillation, paving the way for fully stable deep RL algorithms and providing a testbed for experimentation with Policy Mirror Descent.

Reinforcement Learning (RL) agents often exhibit learning behaviors that are not intuitively interpretable by human observers, which can result in suboptimal feedback in collaborative teaching settings. Yet, how humans perceive and interpret RL agent's learning behavior is largely unknown. In a bottom-up approach with two experiments, this work provides a data-driven understanding of the factors of human observers' understanding of the agent's learning process. A novel, observation-based paradigm to directly assess human inferences about agent learning was developed. In an exploratory interview study (\textit{N}=9), we identify four core themes in human interpretations: Agent Goals, Knowledge, Decision Making, and Learning Mechanisms. A second confirmatory study (\textit{N}=34) applied an expanded version of the paradigm across two tasks (navigation/manipulation) and two RL algorithms (tabular/function approximation). Analyses of 816 responses confirmed the reliability of the paradigm and refined the thematic framework, revealing how these themes evolve over time and interrelate. Our findings provide a human-centered understanding of how people make sense of agent learning, offering actionable insights for designing interpretable RL systems and improving transparency in Human-Robot Interaction.