ND Tree----论文复现

ND_Tree_based update_a Fast Algorithm for the Dynamic Non-Dominance Problem的程序复现

多目标粒子群优化算法+多目标进化 MATLAB

A structure MATLAB implementation of MOPSO for Evolutionary Multi-Objective Optimization A structured MATLAB implementation of MOEA/D for Evolutionary Multi-Objective Optimization

贝叶斯 actor critic

内含论文 Bayesian Policy Gradient and Actor-Critic Algorithms ，本代码是论文的实现

强化学习策略梯度

Cart Pole ，Grid World ，Mountain Car ，Pendulum，Toy

强化学习动态规划

Comparison of Reinforcement Learning Algorithms applied to the Cart-Pole Problem，APPLICATION OF REINFORCEMENT LEARNING ALGORITHMS TO OPTIMIZATION AND CONTROL PROBLEMS 论文实现代码

模糊强化学习

用模糊强化学习，需预先设定模糊规则，本代码描述了Cartpole学习的强化学习过程，有兴趣可以学习一下