Abstract Computing power network (CPN) can alleviate the resource bottleneck in mobile edge computing (MEC). In this paper, we investigate the caching-assisted CPN system for task offloading. A combination of policies such as task offloading and caching is considered to reduce the energy consumption of the system under the condition of meeting a certain delay. Besides, we propose an advanced deep reinforcement learning (DRL) algorithm called Request Sensitive Multi Agent Soft Actor-Critic (RS-MASAC) algorithm to achieve minimal system energy consumption by obtaining the optimal policy. Simulation results show that our proposed algorithm has better performance than baseline algorithms.