Extreme Edge Computing (EEC) aims to offload tasks to users’ edge devices such as smartphones, laptops, tablets, etc. rather than edge servers, presenting challenges due to the mobile, heterogeneous, and resource-limited nature of these devices. Additionally, tasks are often complex and interdependent, complicating offloading and workload orchestration. The dynamicity of EEC systems, where both task generation and resources can be mobile, alongside task interdependencies, escalates the complexity of task offloading and workload management. This research aims to propose a novel task orchestration model based on Reinforcement Learning to find the optimal resource destination for all offloaded tasks in a dynamic extreme edge environment.