We analyze the efficacy of modern neuro-evolutionary strategies for\ncontinuous control optimization. Overall, the results collected on a wide\nvariety of qualitatively different benchmark problems indicate that these\nmethods are generally effective and scale well with respect to the number of\nparameters and the complexity of the problem. Moreover, they are relatively\nrobust with respect to the setting of hyper-parameters. The comparison of the\nmost promising methods indicates that the OpenAI-ES algorithm outperforms or\nequals the other algorithms on all considered problems. Moreover, we\ndemonstrate how the reward functions optimized for reinforcement learning\nmethods are not necessarily effective for evolutionary strategies and vice\nversa. This finding can lead to reconsideration of the relative efficacy of the\ntwo classes of algorithm since it implies that the comparisons performed to\ndate are biased toward one or the other class.\n