Abstract: Aiming at the uncertain mechanism  of node activation strategies and redundancy of feasible solution sets in the process of solving target coverage problem in wireless sensor networks, we proposed a deep Q learning based target coverage algorithm to learn the scheduling strategies of nodes in wireless sensor networks. Firstly, the algorithm abstracted the construction of feasible solution sets into  Markov decision process, and intelligently selected activated sensor nodes as discrete actions according to the network environment. Secondly, a reward function  evaluated the performance of the intelligent agent in selecting actions based on the 
 coverage capacity and its residual energy of the active node. The simulation  experiment result shows that the algorithm is effective in different network environments, and the network lifecycle is superior to the  three  greedy algorithms, the maximum lifetime  coverage algorithm and the adaptive learning automaton algorithm.

Key words: target coverage problem, deep Q learning, wireless sensor networks, reinforcement learning