Approximate Dynamic Programming(近似动态规划算法) Chapter 6 阅读笔记前言一、Myopic Policies(贪婪策略)二、Lookahead Policies(前视策略)三、Policy Function Approximations(策略函数估计)四、Value Function Approximations(价值函数估计)五、Hybrid Strategies(混合策略)六、Randomized Policies(随机策略)总结
Approximate Dynamic Programming(近似动态规划算法) Chapter 6 阅读笔记文章目录Approximate Dynamic Programming(近似动态规划算法) Chapter 6 阅读笔记前言一、Myopic Policies(贪婪策略)二、Lookahead Policies(前视策略)1.Tree search2.Sparse sampling tree search3.Rollout heuristics4.Rolling horizon pro