<p dir="ltr">The horizon for inclusion of data-driven algorithms in cyber-physical systems is rapidly expanding due to evermore availability of high-performance computing tools and the inception of novel mathematical models in the fields of deep learning and reinforcement learning. In this regard, energy systems are a suitable candidate for data-driven algorithms utilization due to rapid expansion of smart measuring tools and infrastructure. Accordingly, I decided to explore the capabilities of deep reinforcement learning in control, security, and restoration of smart energy systems to tackle well-known problems such as ensuring stability, adversarial attack avoidance, and the black start restoration. To achieve this goal, I employed various reinforcement learning techniques in different capacities to develop transfer learning modules based on a rule-based approach for online control of the power system, utilized reinforcement learning for procedural noise generation in adversarial attacks against contingency detection in a power system and exploited multiple reinforcement learning algorithms to fully restore an energy system in an optimal manner. Per the results of these endeavors, I managed to develop a rule-based transfer learning logic to control the power system under various disturbance types and intensities. Furthermore, I developed an optimal adversarial attack module using a reinforcement-learning-based procedural noise generation to avoid detection by conventional deep-learning-based detection. Finally for the system restoration, the proposed intelligent restoration module managed to provide sustainable results for the black start restoration in energy system.</p>

The emergence of reinforcement learning from human feedback (RLHF) has made great strides toward giving AI decision-making the ability to learn from external human advice. In general, this machine learning technique is concerned with producing agents that learn to work toward optimizing and achieving some goal, advanced by interactions with the environment and feedback given in terms of a quantifiable reward. In the scope of this project, we seek to merge the intricate realms of AI robustness, ethical decision-making, and RLHF. With no way to truly quantify human values, human feedback is an essential bridge in the learning process, allowing AI models to reflect better ethical principles rather than just replicating human behavior. By exploring the transformative potential of RLHF in AI-human interactions, acknowledging the dynamic nature of human behavior beyond simplistic models, and emphasizing the necessity for ethically framed AI systems, this thesis constructs a deep reinforcement learning framework that is not only robust but also well aligned with human ethical standards. Through a methodology that incorporates simulated ethical dilemmas and evaluates AI decisions against established ethical frameworks, the focus is to contribute significantly to the understanding and application of RLHF in creating AI systems that embody robustness and ethical integrity.