Microalgae, such as Chlorella vulgaris and Scenedesmus obliquus, are highly efficient at capturing carbon dioxide through photosynthesis, converting it into valuable biomass. This biomass can be further processed into carbon materials with applications in various fields, including water treatment. The reinforcement learning (RL) method was used to dynamically optimize environmental conditions for microalgae growth, improving the efficiency of biodiesel production. The contributions of this study include demonstrating the effectiveness of RL in optimizing biological systems, highlighting the potential of microalgae-derived materials in various industrial applications, and showcasing the integration of renewable energy technologies to enhance sustainability. The study demonstrated that Chlorella vulgaris and Scenedesmus obliquus, cultivated under controlled conditions, significantly improved absorption rates by 50% and 80%, respectively, showcasing their potential in residential heating systems. Post-cultivation, the extracted lipids were effectively utilized for biodiesel production. The RL models achieved high predictive accuracy, with R2 values of 0.98 for temperature and 0.95 for oxygen levels, confirming their effectiveness in system regulation. The development of activated carbon from microalgae biomass also highlighted its utility in removing heavy metals and dyes from water, proving its efficacy and stability, thus enhancing the sustainability of environmental management. This study underscores the successful integration of advanced machine learning with biological processes to optimize microalgae cultivation and develop practical byproducts for ecological applications.