This study offers a pervasive maximum power point tracking (MPPT) technique to increase the reliability of the perturb & observe (P & O) maximum power point tracking method under various partial shadow circumferences. The capacity of the PV system to capture maximum power via maximum power point tracking is impeded mostly by partial shadow. Several MPPT strategies based on bio-inspired optimisation methodologies have been reported in the literature. Traditional perturb and observe methods include flaws such as steady-state oscillations, poor tracking performance, incorrect tracking directions, and power loss. The techniques of these algorithms differ, leading them to react differently when calculating global peak power. The tracking performance of the aforementioned technique is enhanced by selecting the appropriate duty cycle, dynamic perturbation step size, and current parameter. The difficulty of monitoring the worldwide peak as sun irradiance and temperature vary is addressed by this method. This paper presents a unique Hybrid MPPT model that combines the Reinforcement Learning (RL) algorithm with the Perturb & Observe approach to maximise electricity from photovoltaic fixed overheads in response to fluctuations in sun irradiance and partial shadowing. RL performs the first phases of maximum power point tracking in order to provide a more accurate estimate of the global peak, which contributes to the overall stage selection of the P & O technique. This strategy might be useful for reducing the effects of partial shade.The proposed approach is tested on a PV array under a range of partial shade circumstances. The efficiency of the proposed approach is assessed by comparing it to conventional P & O using the MATLAB/SIMULINK tool. The examination found that the proposed MPPT controller provides a 10% gain in tracking efficiency over the typical P&O MPPT approach in even the most demanding scenarios.