Many practical reinforcement learning environments have a discrete factored action space that induces a large combinatorial set of actions, thereby posing significant challenges. Existing approaches leverage the regular structure of the action space and resort to a linear decomposition of Q-functions, which avoids enumerating all combinations of factored actions. In this paper, we consider Q-functions defined over a lower dimensional projected subspace of the original action space, and study the condition for the unbiasedness of decomposed Q-functions using causal effect estimation from the no unobserved confounder setting in causal statistics. This leads to a general scheme which we call action decomposed reinforcement learning that uses the projected Q-functions to approximate the Q-function in standard model-free reinforcement learning algorithms. The proposed approach is shown to improve sample complexity in a model-based reinforcement learning setting. We demonstrate improvements in sample efficiency compared to state-of-the-art baselines in online continuous control environments and a real-world offline sepsis treatment environment.

Autonomous parking is a key technology in modern autonomous driving systems, requiring high precision, strong adaptability, and efficiency in complex environments. This paper proposes a Deep Reinforcement Learning (DRL) framework based on the Soft Actor-Critic (SAC) algorithm to optimize autonomous parking tasks. SAC, an off-policy method with entropy regularization, is particularly well-suited for continuous action spaces, enabling fine-grained vehicle control. We model the parking task as a Markov Decision Process (MDP) and train an agent to maximize cumulative rewards while balancing exploration and exploitation through entropy maximization. The proposed system integrates multiple sensor inputs into a high-dimensional state space and leverages SAC's dual critic networks and policy network to achieve stable learning. Simulation results show that the SAC-based approach delivers high parking success rates, reduced maneuver times, and robust handling of dynamic obstacles, outperforming traditional rule-based methods and other DRL algorithms. This study demonstrates SAC's potential in autonomous parking and lays the foundation for real-world applications.

Multi-Agent Reinforcement Learning (MARL) has become a powerful framework for numerous real-world applications, modeling distributed decision-making and learning from interactions with complex environments. Resource Allocation Optimization (RAO) benefits significantly from MARL's ability to tackle dynamic and decentralized contexts. MARL-based approaches are increasingly applied to RAO challenges across sectors playing pivotal roles to Industry 4.0 developments. This survey provides a comprehensive review of recent MARL algorithms for RAO, encompassing core concepts, classifications, and a structured taxonomy. By outlining the current research landscape and identifying primary challenges and future directions, this survey aims to support researchers and practitioners in leveraging MARL's potential to advance resource allocation solutions.

Graph neural networks have been widely utilized to solve graph-related tasks because of their strong learning power in utilizing the local information of neighbors. However, recent studies on graph adversarial attacks have proven that current graph neural networks are not robust against malicious attacks. Yet much of the existing work has focused on the optimization objective based on attack performance to obtain (near) optimal perturbations, but paid less attention to the strength quantification of each perturbation such as the injection of a particular node/link, which makes the choice of perturbations a black-box model that lacks interpretability. In this work, we propose the concept of noise to quantify the attack strength of each adversarial link. Furthermore, we propose three attack strategies based on the defined noise and classification margins in terms of single and multiple steps optimization. Extensive experiments conducted on benchmark datasets against three representative graph neural networks demonstrate the effectiveness of the proposed attack strategies. Particularly, we also investigate the preferred patterns of effective adversarial perturbations by analyzing the corresponding properties of the selected perturbation nodes.

A burgeoning area within reinforcement learning (RL) is the design of sequential decision-making agents centered around large language models (LLMs). While autonomous decision-making agents powered by modern LLMs could facilitate numerous real-world applications, such successes demand agents that are capable of data-efficient RL. One key obstacle to achieving data efficiency in RL is exploration, a challenge that we demonstrate many recent proposals for LLM agent designs struggle to contend with. Meanwhile, classic algorithms from the RL literature known to gracefully address exploration require technical machinery that can be challenging to operationalize in purely natural language settings. In this work, rather than relying on finetuning or in-context learning to coax LLMs into implicitly imitating a RL algorithm, we illustrate how LLMs can be used to explicitly implement an existing RL algorithm (Posterior Sampling for Reinforcement Learning) whose capacity for statistically-efficient exploration is already well-studied. We offer empirical results demonstrating how our LLM-based implementation of a known, data-efficient RL algorithm can be considerably more effective in natural language tasks that demand prudent exploration.

Continual learning is the one of the most essential abilities for autonomous agents, which can incrementally learn daily-life skills. For this ultimate goal, a simple but powerful method, dark experience replay (DER), has been proposed recently. DER mitigates catastrophic forgetting, in which the skills acquired in the past are unintentionally forgotten, by stochastically storing the streaming data in a reservoir sampling (RS) buffer and by relearning them or retaining the past outputs for them. However, since DER considers multiple objectives, it will not function properly without appropriate weighting of them. In addition, the ability to retain past outputs inhibits learning if the past outputs are incorrect due to distribution shift or other effects. This is due to a tradeoff between memory consolidation and plasticity. The tradeoff is hidden even in the RS buffer, which gradually stops storing new data for new skills in it as data is continuously passed to it. To alleviate the tradeoff and achieve better balance, this paper proposes improvement strategies to each of DER and RS. Specifically, DER is improved with automatic adaptation of weights, block of replaying erroneous data, and correction of past outputs. RS is also improved with generalization of acceptance probability, stratification of plural buffers, and intentional omission of unnecessary data. These improvements are verified through multiple benchmarks including regression, classification, and reinforcement learning problems. As a result, the proposed methods achieve steady improvements in learning performance by balancing the memory consolidation and plasticity.

Developing scalable and efficient reinforcement learning algorithms for cooperative multi-agent control has received significant attention over the past years. Existing literature has proposed inexact decompositions of local Q-functions based on empirical information structures between the agents. In this paper, we exploit inter-agent coupling information and propose a systematic approach to exactly decompose the local Q-function of each agent. We develop an approximate least square policy iteration algorithm based on the proposed decomposition and identify two architectures to learn the local Q-function for each agent. We establish that the worst-case sample complexity of the decomposition is equal to the centralized case and derive necessary and sufficient graphical conditions on the inter-agent couplings to achieve better sample efficiency. We demonstrate the improved sample efficiency and computational efficiency on numerical examples.

Intelligent Task Offloading in V ANETs: A Hybrid AI-Driven Approach for Low-Latency and Energy Efficiency Tariq Qayyum, Asadullah Tariq, Muhammad Ali, Mohamed Adel Serhani, Zouheir Trabelsi, Maite L opez-S anchez College of Information Technology, United Arab Emirates University, Al Ain, Abu Dhabi, UAE Department of Computer Science, SCIT, Beaconhouse National University, Lahore Pakistan College of Computing and Informatics, University of Sharjah, Sharjah, UAE Department of Mathematics, University of Barcelona, Gran Via de les Corts Catalanes, Barcelona Abstract --V ehicular Ad-hoc Networks (V ANETs) are integral to intelligent transportation systems, enabling vehicles to offload computational tasks to nearby roadside units (RSUs) and mobile edge computing (MEC) servers for real-time processing. However, the highly dynamic nature of V ANETs introduces challenges, such as unpredictable network conditions, high latency, energy inefficiency, and task failure. Extensive simulations demonstrate that the proposed framework achieves significant reductions in latency and energy usage while improving task success rates and network throughput. By offering an efficient, and scalable solution, this framework sets the foundation for enhancing real-time applications in dynamic vehicular environments. Index T erms--V ANET, T ask offloading, vehicular communication, resource allocation, scalable I.

Learning from few demonstrations to develop policies robust to variations in robot initial positions and object poses is a problem of significant practical interest in robotics. Compared to imitation learning, which often struggles to generalize from limited samples, reinforcement learning (RL) can autonomously explore to obtain robust behaviors. Training RL agents through direct interaction with the real world is often impractical and unsafe, while building simulation environments requires extensive manual effort, such as designing scenes and crafting task-specific reward functions. To address these challenges, we propose an integrated real-to-sim-to-real pipeline that constructs simulation environments based on expert demonstrations by identifying scene objects from images and retrieving their corresponding 3D models from existing libraries. We introduce a projection-based reward model for RL policy training that is supervised by a vision-language model (VLM) using human-guided object projection relationships as prompts, with the policy further fine-tuned using expert demonstrations. In general, our work focuses on the construction of simulation environments and RL-based policy training, ultimately enabling the deployment of reliable robotic control policies in real-world scenarios.

-- In this paper, we present an adherence-aware reinforcement learning (RL) approach aimed at seeking optimal lane-changing recommendations within a semi-autonomous driving environment to enhance a single vehicles travel efficiency. The problem is framed within a Markov decision process setting and is addressed through an adherence-aware deep Q network, which takes into account the partial compliance of human drivers with the recommended actions. This approach is evaluated within CARLAs driving environment under realistic scenarios. Autonomous driving is classified into five levels, ranging from Level 1 to Level 5 [1]. However, complete Level 5 automation has yet to be realized. Current research and development primarily focus on partially autonomous vehicles at Levels 2 to 4, where human drivers retain varying degrees of responsibility. In such a semi-autonomous driving environment, an artificial intelligence (AI) system usually provides recommendations on driving decisions.