提出了基于进化梯度搜索的多机器人主动嗅觉的一种实现策略。
An active olfaction implementation scheme based on evolutionary gradient search using a swarm of robots is put forward.
随机梯度遗传算法进化代数从5增加到10以及从10增加到15时,三个航速下的目标识别率按照接近20%的比例增加。
Target recognition rates, under the three speeds, increase by about 20% in evolutional generation(EG) ranges, of SGGA, from 5 to 10 and from 10 to 15.
求解马氏决策问题的梯度增强学习算法; 求解马氏决策问题的进化-梯度混合学习算法;
One part of the main contents in this paper is the generalization methods for reinforcement learning in solving Markov decision problems with continuous states and actions.
应用推荐