Abstract: The introduction of evolutionary algorithm has greatly improved the performance of reinforcement learning algorithms. However, existing algorithms based on evolutionary reinforcement learning (ERL) still suffer from the problems such as susceptibility to fall into deceptive rewards, easy convergence to local optimums and poor stability. To address these problems, a stochastic symmetric search strategy is proposed. It acts directly on the policy network parameters, and guides the global policy network parameter optimization update by the optimal policy network parameter based on the central of the policy network parameter. Besides, it is supplemented by gradient optimization to guide the intelligentsia for multivariate exploration. Experimental results in five continuous control tasks of robot motion in MuJoCo show that the proposed algorithm outperforms previous evolutionary reinforcement learning algorithms and has a faster convergence rate. 

Key words: deep reinforcement learning, evolutionary algorithm, evolutionary reinforcement learning, stochastic symmet