Browsing by Author "Alharbi, Meshal"

Now showing 1 - 2 of 2

Restricted
Sample Efficient Reinforcement Learning with Partial Dynamics Knowledge
(Massachusetts Institute of Technology, 2024-05-17) Alharbi, Meshal; Roozbehani, Mardavij
The problem of sample complexity of online reinforcement learning is often studied in the literature without taking into account any partial knowledge about the system dynamics that could potentially accelerate the learning process. In this thesis, we study the sample complexity of online Q-learning methods when some prior knowledge about the dynamics is available or can be learned efficiently. We focus on systems that evolve according to an additive disturbance model where the underlying dynamics are described by a deterministic function of states and actions, along with an unknown additive disturbance that is independent of states and actions. In the setting of finite Markov decision processes, we present an optimistic Q-learning algorithm that achieves Õ(√T) regret without polynomial dependency on the number of states and actions under perfect knowledge of the dynamics function. This is in contrast to the typical Õ(√SAT) regret for existing Q-learning methods. Further, if only a noisy estimate of the dynamics function is available, our method can learn an approximately optimal policy in a number of samples that is independent of the cardinalities of state and action spaces. The sub-optimality gap depends on the approximation error of the noisy estimate, as well as the Lipschitz constant of the corresponding optimal value function. Our approach does not require modeling of the transition probabilities and enjoys the same memory complexity as model-free methods.
39 0
Restricted
The impact of leadership style on employee motivation and performance in the Saudi financial sector
(Saudi Digital Library, 2025) Alharbi, Meshal; Das, Ranjit
This study investigates the impact of four leadership styles—transformational, transactional, authoritarian, and laissez-faire—on employee motivation and performance in the Saudi financial sector, within the broader context of institutional reforms and Vision 2030. A quantitative, positivist approach was adopted, using a structured online questionnaire distributed to a sample of 80 employees from government, semi-government, and commercial financial institutions. The data were analysed using SPSS, applying descriptive and inferential statistical methods such as correlation and multiple regression analysis. The results showed that the transactional leadership style was the most successful, exerting a significant beneficial impact on performance and motivation. Although it did not immediately result in better performance, transformational leadership dramatically increased employee motivation, indicating that institutional and regulatory limitations might restrict its usefulness. Laissez-faire leadership was negatively correlated with motivation and did not significantly correlate with performance, whereas authoritarian leadership had no discernible impact on either. Additionally, a strong positive link between motivation and performance was validated, highlighting the essential role of motivation as a mediating component in the dynamics between leadership and performance. Theoretically, this study challenges the notion that transformational leadership is always preferable by providing a comparative analysis of leadership philosophies in a Saudi setting. It offers valuable perspectives for managers, legislators, and human resources specialists, emphasising the importance of fusing the motivating attributes of transformational leadership with the accountability and structural clarity of transactional leadership. The study findings also advise reducing the dependence on authoritarian and laissez-faire methods.
25 0