Despite its exceptional soft tissue contrast, Magnetic Resonance Imaging (MRI) faces the challenge of long scanning times compared to other modalities like X-ray radiography. Shortening scanning times is crucial in clinical settings, as it increases patient comfort, decreases examination costs and improves throughput. Recent advances in compressed sensing (CS) and deep learning allow accelerated MRI acquisition by reconstructing high-quality images from undersampled data. While reconstruction algorithms have received most of the focus, designing acquisition trajectories to optimize reconstruction quality remains an open question. This thesis explores two approaches to address this gap in the context of Cartesian MRI. First, we propose two algorithms, lazy LBCS and stochastic LBCS, that significantly improve upon G\"ozc\"u et al.'s greedy learning-based CS (LBCS) approach. These algorithms scale to large, clinically relevant scenarios like multi-coil 3D MR and dynamic MRI, previously inaccessible to LBCS. Additionally, we demonstrate that generative adversarial networks (GANs) can serve as a natural criterion for adaptive sampling by leveraging variance in the measurement domain to guide acquisition. Second, we delve into the underlying structures or assumptions that enable mask design algorithms to perform well in practice. Our experiments reveal that state-of-the-art deep reinforcement learning (RL) approaches, while capable of adaptation and long-horizon planning, offer only marginal improvements over stochastic LBCS, which is neither adaptive nor does long-term planning. Altogether, our findings suggest that stochastic LBCS and similar methods represent promising alternatives to deep RL. They shine in particular by their scalability and computational efficiency and could be key in the deployment of optimized acquisition trajectories in Cartesian MRI.

Deep reinforcement learning (RL) provides powerful methods for training optimal sequential decision-making agents. As collecting real-world interactions can entail additional costs and safety risks, the common paradigm of sim2real conducts training in a simulator, followed by real-world deployment. Unfortunately, RL agents easily overfit to the choice of simulated training environments, and worse still, learning ends when the agent masters the specific set of simulated environments. In contrast, the real world is highly open-ended, featuring endlessly evolving environments and challenges, making such RL approaches unsuitable. Simply randomizing over simulated environments is insufficient, as it requires making arbitrary distributional assumptions and can be combinatorially less likely to sample specific environment instances that are useful for learning. An ideal learning process should automatically adapt the training environment to maximize the learning potential of the agent over an open-ended task space that matches or surpasses the complexity of the real world. This thesis develops a class of methods called Unsupervised Environment Design (UED), which aim to produce such open-ended processes. Given an environment design space, UED automatically generates an infinite sequence or curriculum of training environments at the frontier of the learning agent's capabilities. Through extensive empirical studies and theoretical arguments founded on minimax-regret decision theory and game theory, the findings in this thesis show that UED autocurricula can produce RL agents exhibiting significantly improved robustness and generalization to previously unseen environment instances. Such autocurricula are promising paths toward open-ended learning systems that achieve more general intelligence by continually generating and mastering additional challenges of their own design.

Reinforcement learning (RL) makes an agent learn from trial-and-error experiences gathered during the interaction with the environment. Recently, offline RL has become a popular RL paradigm because it saves the interactions with environments. In offline RL, data providers share large pre-collected datasets, and others can train high-quality agents without interacting with the environments. This paradigm has demonstrated effectiveness in critical tasks like robot control, autonomous driving, etc. However, less attention is paid to investigating the security threats to the offline RL system. This paper focuses on backdoor attacks, where some perturbations are added to the data (observations) such that given normal observations, the agent takes high-rewards actions, and low-reward actions on observations injected with triggers. In this paper, we propose Baffle (Backdoor Attack for Offline Reinforcement Learning), an approach that automatically implants backdoors to RL agents by poisoning the offline RL dataset, and evaluate how different offline RL algorithms react to this attack. Our experiments conducted on four tasks and four offline RL algorithms expose a disquieting fact: none of the existing offline RL algorithms is immune to such a backdoor attack. More specifically, Baffle modifies 10\% of the datasets for four tasks (3 robotic controls and 1 autonomous driving). Agents trained on the poisoned datasets perform well in normal settings. However, when triggers are presented, the agents' performance decreases drastically by 63.2\%, 53.9\%, 64.7\%, and 47.4\% in the four tasks on average. The backdoor still persists after fine-tuning poisoned agents on clean datasets. We further show that the inserted backdoor is also hard to be detected by a popular defensive method. This paper calls attention to developing more effective protection for the open-source offline RL dataset.

Intelligent reflecting surface (IRS)-assisted unmanned aerial vehicle (UAV) communications are expected to alleviate the load of ground base stations in a cost-effective way. Existing studies mainly focus on the deployment and resource allocation of a single IRS instead of multiple IRSs, whereas it is extremely challenging for joint multi-IRS multi-user association in UAV communications with constrained reflecting resources and dynamic scenarios. To address the aforementioned challenges, we propose a new optimization algorithm for joint IRS-user association, trajectory optimization of UAVs, successive interference cancellation (SIC) decoding order scheduling and power allocation to maximize system energy efficiency. We first propose an inverse soft-Q learning-based algorithm to optimize multi-IRS multi-user association. Then, SCA and Dinkelbach-based algorithm are leveraged to optimize UAV trajectory followed by the optimization of SIC decoding order scheduling and power allocation. Finally, theoretical analysis and performance results show significant advantages of the designed algorithm in convergence rate and energy efficiency.

Cooperative multi-agent reinforcement learning (MARL) aims to coordinate a system of agents towards optimizing global returns (Vinyals et al., 2019), and has witnessed significant prospects in various domains, such as autonomous vehicles (Zhou et al., 2020), smart grid (Chen et al., 2021a), robotics (Yu et al., 2023), and social science (Leibo et al., 2017). Training reliable control policies for coordinating such systems remains a major challenge. The centralized training with decentralized execution (CTDE) (Foerster et al., 2016) hybrids the merits of independent Q-learning (Foerster et al., 2017) and joint action learning (Sukhbaatar et al., 2016), and becomes a compelling paradigm that exploits the centralized training opportunity for training fully decentralized policies (Wang et al., 2023). Subsequently, numerous popular algorithms are proposed, including VDN (Sunehag et al., 2018), QMIX (Rashid et al., 2020), MAAC (Iqbal & Sha, 2019), and MAPPO (Yu et al., 2022). Sharing policy parameters is crucial for scaling these algorithms to massive agents with accelerated cooperation learning (Fu et al., 2022). However, it is widely observed that agents tend to acquire homogeneous behaviors, which might hinder diversified exploration and sophisticated coordination (Christianos et al., 2021). Some methods (Li et al., 2021; Jiang & Lu, 2021; Liu et al., 2023) attempt to promote individualized behaviors by distinguishing each agent from the others, while they often neglect the prospect of effective team composition with implicit task allocation. Real-world multi-agent tasks usually involve dynamic team composition with the emergence of roles (Shao et al., 2022; Hu et al., 2022).

Autonomous Vehicle (AV) technology is advancing rapidly, promising a significant shift in road transportation safety and potentially resolving various complex transportation issues. With the increasing deployment of AVs by various companies, questions emerge about how AVs interact with each other and with human drivers, especially when AVs are prevalent on the roads. Ensuring cooperative interaction between AVs and between AVs and human drivers is critical, though there are concerns about possible negative competitive behaviors. This paper presents a multi-stage approach, starting with the development of a single AV and progressing to connected AVs, incorporating sharing and caring V2V communication strategy to enhance mutual coordination. A survey is conducted to validate the driving performance of the AV and will be utilized for a mixed traffic case study, which focuses on how the human drivers will react to the AV driving alongside them on the same road. Results show that using deep reinforcement learning, the AV acquired driving behavior that reached human driving performance. The adoption of sharing and caring based V2V communication within AV networks enhances their driving behavior, aids in more effective action planning, and promotes collaborative behavior amongst the AVs. The survey shows that safety in mixed traffic cannot be guaranteed, as we cannot control human ego-driven actions if they decide to compete with AV.

Despite numerous successes, the field of reinforcement learning (RL) remains far from matching the impressive generalisation power of human behaviour learning. One possible way to help bridge this gap be to provide RL agents with richer, more human-like feedback expressed in natural language. To investigate this idea, we first extend BabyAI to automatically generate language feedback from the environment dynamics and goal condition success. Then, we modify the Decision Transformer architecture to take advantage of this additional signal. We find that training with language feedback either in place of or in addition to the return-to-go or goal descriptions improves agents' generalisation performance, and that agents can benefit from feedback even when this is only available during training, but not at inference.

Artificial Intelligence (AI) is expected to play an instrumental role in the next generation of wireless systems, such as sixth-generation (6G) mobile network. However, massive data, energy consumption, training complexity, and sensitive data protection in wireless systems are all crucial challenges that must be addressed for training AI models and gathering intelligence and knowledge from distributed devices. Federated Learning (FL) is a recent framework that has emerged as a promising approach for multiple learning agents to build an accurate and robust machine learning models without sharing raw data. By allowing mobile handsets and devices to collaboratively learn a global model without explicit sharing of training data, FL exhibits high privacy and efficient spectrum utilization. While there are a lot of survey papers exploring FL paradigms and usability in 6G privacy, none of them has clearly addressed how FL can be used to improve the protocol stack and wireless operations. The main goal of this survey is to provide a comprehensive overview on FL usability to enhance mobile services and enable smart ecosystems to support novel use-cases. This paper examines the added-value of implementing FL throughout all levels of the protocol stack. Furthermore, it presents important FL applications, addresses hot topics, provides valuable insights and explicits guidance for future research and developments. Our concluding remarks aim to leverage the synergy between FL and future 6G, while highlighting FL's potential to revolutionize wireless industry and sustain the development of cutting-edge mobile services.

This paper addresses the challenges associated with decentralized voltage control in power grids due to an increase in distributed generations (DGs). Traditional model-based voltage control methods struggle with the rapid energy fluctuations and uncertainties of these DGs. While multi-agent reinforcement learning (MARL) has shown potential for decentralized secondary control, scalability issues arise when dealing with a large number of DGs. This problem lies in the dominant centralized training and decentralized execution (CTDE) framework, where the critics take global observations and actions. To overcome these challenges, we propose a scalable network-aware (SNA) framework that leverages network structure to truncate the input to the critic's Q-function, thereby improving scalability and reducing communication costs during training. Further, the SNA framework is theoretically grounded with provable approximation guarantee, and it can seamlessly integrate with multiple multi-agent actor-critic algorithms. The proposed SNA framework is successfully demonstrated in a system with 114 DGs, providing a promising solution for decentralized voltage control in increasingly complex power grid systems.

In recent years, we have seen an increase in the adoption of blockchain-based systems in non-financial applications, looking to benefit from what the technology has to offer. Although many fields have managed to include blockchain in their core functionalities, the adoption of blockchain, in general, is constrained by the so-called trilemma trade-off between decentralization, scalability, and security. In our previous work, we have shown that using a digital twin for dynamically managing blockchain systems during runtime can be effective in managing the trilemma trade-off. Our Digital Twin leverages DDDAS feedback loop, which is responsible for getting the data from the system to the digital twin, conducting optimisation, and updating the physical system. This paper examines how leveraging DDDAS feedback loop can support the optimisation component of the trilemma benefiting from Reinforcement Learning agents and a simulation component to augment the quality of the learned model while reducing the computational overhead required for decision-making.