官术网_书友最值得收藏!

Learning the Markov decision process 

The Markov property is widely used in RL, and it states that the environment's response at time t+1 depends only on the state and action at time t. In other words, the immediate future only depends on the present and not on the past. This is a useful property that simplifies the math considerably, and is widely used in many fields such as RL and robotics.

Consider a system that transitions from state s0 to s1 by taking an action a0 and receiving a reward r1, and thereafter from s1 to s2 taking action a1, and so on until time t. If the probability of being in a state s' at time t+1 can be represented mathematically as in the following function, then the system is said to follow the Markov property:

Note that the probability of being in state st+1 depends only on st and at and not on the past. An environment that satisfies the following state transition property and reward function as follows is said to be a Markov Decision Process (MDP):

Let's now define the very foundation of RL: the Bellman equation. This equation will help in providing an iterative solution to obtaining value functions.

主站蜘蛛池模板: 平江县| 扎兰屯市| 乌海市| 山阳县| 龙游县| 广汉市| 丹棱县| 罗甸县| 湛江市| 隆子县| 资源县| 信宜市| 务川| 眉山市| 盐池县| 乃东县| 南漳县| 厦门市| 定日县| 平定县| 桑植县| 隆尧县| 新津县| 通道| 上虞市| 黔江区| 抚顺市| 开封县| 资源县| 腾冲县| 南丰县| 钟祥市| 米易县| 石河子市| 襄汾县| 友谊县| 郑州市| 临沭县| 青阳县| 牙克石市| 西城区|