Bellman Equation

Tags: #machine learning

Equation

$$v_{\pi}(s)=\sum_{a}\pi(a|s)\sum_{s^{'},r}p(s^{'},r|s,a)[r+\gamma v_{\pi}(s^{'})]$$

Latex Code

                                 v_{\pi}(s)=\sum_{a}\pi(a|s)\sum_{s^{'},r}p(s^{'},r|s,a)[r+\gamma v_{\pi}(s^{'})]
                            

Have Fun

Let's Vote for the Most Difficult Equation!

Introduction

Equation



Latex Code

            v_{\pi}(s)=\sum_{a}\pi(a|s)\sum_{s^{'},r}p(s^{'},r|s,a)[r+\gamma v_{\pi}(s^{'})]
        

Explanation

  • : Value at state s in policy \pi
  • : Value at state s^{'} in policy \pi
  • : Probability of choosing action a given state s
  • : Reward at state s
  • : Reward discount factor \gamma

You can check more detailed information of Bellman Equation in this tutorial Introduction to Reinforcement Learning for more details.

Related Documents

Related Videos

Discussion

Comment to Make Wishes Come True

Leave your wishes (e.g. Passing Exams) in the comments and earn as many upvotes as possible to make your wishes come true


  • Timothy Cook
    I'm keeping hope alive to pass this exam.
    2023-07-10 00:00

    Reply


    Mark Jackson reply to Timothy Cook
    You can make it...
    2023-08-04 00:00:00.0

    Reply


  • Sandra Jackson
    Craving a victory on this upcoming test.
    2023-12-10 00:00

    Reply


    Julie Wright reply to Sandra Jackson
    Nice~
    2024-01-03 00:00:00.0

    Reply


  • Henry Rivera
    Please let me pass this test.
    2023-07-22 00:00

    Reply


    Randy Murphy reply to Henry Rivera
    You can make it...
    2023-08-19 00:00:00.0

    Reply