Q Learning Algorithm | Reinforcement learning | Machine Learning by Dr. Mahesh Huddar

Поділитися
Вставка
  • Опубліковано 27 сер 2024

КОМЕНТАРІ • 31

  • @Eelcowww
    @Eelcowww 2 роки тому +50

    From state 5, you can go to state 5.

  • @codeXtree
    @codeXtree 10 місяців тому +5

    I spent days going through various tutorials. to understand this topic with example. The way you explained this was very clear from start to finish. Thank you Mahesh

    • @MaheshHuddar
      @MaheshHuddar  10 місяців тому +1

      Glad it was helpful!
      Do like share and subscribe

  • @jameelunnisamohammed730
    @jameelunnisamohammed730 Рік тому +15

    Sir can't we take self loop from 5 to 5 having 100 as reward? Then the update value will become 180

    • @Dark_Peace
      @Dark_Peace Рік тому +2

      Yes you could

    • @alluripranitha
      @alluripranitha 9 місяців тому +2

      y stop ones do it thrice take 300

    • @blaze9558
      @blaze9558 7 місяців тому

      🤣@@alluripranitha

    • @blaze9558
      @blaze9558 7 місяців тому

      why to do it thrice ? do it 10 times and take 1000@@alluripranitha

    • @dipankarbarman6395
      @dipankarbarman6395 22 дні тому

      ​@@blaze9558 why does the self loop s5 have not considered ?

  • @PIYUSH-lz1zq
    @PIYUSH-lz1zq 2 роки тому +7

    can you take real world example/case study question based on that explain ML approach on it ?? It would be great

  • @pravindesai6687
    @pravindesai6687 2 роки тому

    very nice explaination - please try making videos on value iteration and policy iteration - would help a lot with your example solving approach

  • @zachn1666
    @zachn1666 2 роки тому +1

    Thank you so much, I finally get the algorithm now!

    • @MaheshHuddar
      @MaheshHuddar  2 роки тому

      Welcome
      Do like share and subscribe

  • @meha1233
    @meha1233 6 місяців тому +1

    When at state s5 why we don’t consider S5 as a possible move??? I think at s5 we have 3 possible move s1-s4 and s5. Because it a loop on s5

  • @aishwaryagopalakrishnan8709

    you are a saver ! Thank you so much ji

  • @satya-ni2rc
    @satya-ni2rc Рік тому

    Hi sir, your lessons are amazing please try to provide lesson on audio files extraction using librosa

  • @wiamfadel7321
    @wiamfadel7321 3 місяці тому

    thank u

    • @MaheshHuddar
      @MaheshHuddar  3 місяці тому

      Welcome
      Do like share and subscribe

  • @suresh.suthar.24
    @suresh.suthar.24 2 роки тому

    Best explanation thanks 👍👍

    • @MaheshHuddar
      @MaheshHuddar  2 роки тому

      Welcome
      Do like share and subscribe

  • @MDIMTEIYAZALAM
    @MDIMTEIYAZALAM 4 місяці тому

    Sir , could you please post a video on SARSA numerical probelm

  • @anubhavgupta7251
    @anubhavgupta7251 2 роки тому

    thanks for the video sir

    • @MaheshHuddar
      @MaheshHuddar  2 роки тому

      Welcome
      Do like share and subscribe

  • @shambhavisheelavantar8409
    @shambhavisheelavantar8409 2 роки тому +1

    Sir pls upload AI&ML lab programs explaination.

  • @shahzaibmehmood6400
    @shahzaibmehmood6400 2 роки тому

    "That is nothing but" the way you are teaching is superb🤭

    • @MaheshHuddar
      @MaheshHuddar  2 роки тому +1

      Thank You
      Do like share and subscribe

  • @buh357
    @buh357 Рік тому

    thank you

  • @marryammalik9500
    @marryammalik9500 2 роки тому

  • @Alysai-zy3yq
    @Alysai-zy3yq Рік тому

    Can I contact with you