Leslie Kaelbling: Reinforcement Learning, Planning, and Robotics | Lex Fridman Podcast #15

Ғылым және технология

Пікірлер: 42

  • @lexfridman
    @lexfridman5 жыл бұрын

    From philosophy to POMDPs to reinforcement learning & hierarchical planning to the publishing model in academia, I really enjoyed this conversation with Leslie.

  • @PhilosopherRex

    @PhilosopherRex

    5 жыл бұрын

    Sorry Lex, I admit to having misspelled your name when telling people about your channel -- but I won't do it again ;-) Thanks for your efforts and interviews!

  • @handetoffoli3610
    @handetoffoli3610 Жыл бұрын

    I was just following Leslie's MIT OCW course and thinking what a great teacher she is. I then find this! So excited to listen now.

  • @ricardoborgesba

    @ricardoborgesba

    Ай бұрын

    Same here

  • @saturten
    @saturten4 жыл бұрын

    Leslie is so eloquent, I think this is my favorite interview from the podcast

  • @fengliu975
    @fengliu9755 жыл бұрын

    Like this lady. A free thinker who doesn't care for competition and care for investing into hard problems

  • @anirudhramesh8207
    @anirudhramesh82075 жыл бұрын

    Thank you so much for this, Lex. Much love...

  • @OldGamerNoob
    @OldGamerNoob5 жыл бұрын

    Being someone whose work environment is not alongside other programmers where I have to either use lay terminology or keep to myself with descriptions of what I do, it's intriguing and almost refreshing to hear conversations on this podcast constantly referring to everyday life in terms of functions, problem spaces, sets, and the like. really enjoying it.

  • @index7787

    @index7787

    5 жыл бұрын

    Right?! It's literally a different language and I perfer it.

  • @Lunsterful
    @Lunsterful5 жыл бұрын

    Begins with a GEB mention, eloquently articulates issues I have been trying to categorise for years, is pro open access, isn't getting distracted by ill-formed big ideas... anything this person has ever said or written is now priority reading for me. Genius.

  • @contactdi8426
    @contactdi84265 жыл бұрын

    Thanks for this podcast

  • @farhanislam4693
    @farhanislam46932 жыл бұрын

    3rd yr undergrad student. Learning ai on his own. I could understand the problem statements for deep learning and computer vision(couldn't solve them , obviously) , but not so much in reinforcement learning. This really helped. Reinforcement learning isn't just a computation problem. It's a merging of the disciplines mentioned under symbolic systems . One can specialize in one or more of thosw fields, but to make things work, all those perspectives are needed. Thanks for this.

  • @cogoid
    @cogoid2 жыл бұрын

    Leslie is one those amazing guests who do not proffer opinions on supposedly deep questions, but are very lucid in what they do say. I really liked her!

  • @CharlesVanNoland
    @CharlesVanNoland5 жыл бұрын

    What a great conversation.

  • @mikejordan2428
    @mikejordan24285 жыл бұрын

    Great conversation!

  • @yossimolcho841
    @yossimolcho8415 жыл бұрын

    Great channel thank you

  • @douglasholman6300
    @douglasholman63005 жыл бұрын

    Wow Leslie is smart as heck!

  • @quentinmunch3700
    @quentinmunch37005 жыл бұрын

    I think the output we want from a "perception" system is a cost or a credit of the current state of the world. Just like we do in inverse reinforcement learning or target propagation for the credit assignement problem. Awesome video btw !

  • @menatoorus5696
    @menatoorus56965 жыл бұрын

    Mind-opening

  • @yichaoliang5500
    @yichaoliang55003 жыл бұрын

    @lex can you please add the outline back for videos?

  • @varunsharma8573
    @varunsharma85735 жыл бұрын

    wow!!...very knowledgeable...

  • @rickharold69
    @rickharold695 жыл бұрын

    Rock out! Nice love it !

  • @kaouterkarboub5405
    @kaouterkarboub54055 жыл бұрын

    You know Listening to her made me think that humans are amazing !! really

  • @aidenstill7179
    @aidenstill71795 жыл бұрын

    How to create your own deep learning library?

  • @PeihuiBrandonYeo
    @PeihuiBrandonYeo3 жыл бұрын

    It will take a surprising amount of time to walk through Kuala Lumpur airport

  • @ProfessionalTycoons
    @ProfessionalTycoons5 жыл бұрын

    interesting talk

  • @paulinesz15
    @paulinesz15 Жыл бұрын

    Glad to see a few women in this field. 😍

  • @alonamaloh
    @alonamaloh5 жыл бұрын

    She's great. I hold almost exactly the same opinions, but I am much worse at articulating them.

  • @ValerianTexeira
    @ValerianTexeira5 жыл бұрын

    Liked her AI perspective.

  • @patrickpei9256
    @patrickpei92565 жыл бұрын

    Who is the author mentioned at 0:45?

  • @ggolu2

    @ggolu2

    5 жыл бұрын

    en.wikipedia.org/wiki/G%C3%B6del,_Escher,_Bach

  • @krokodils1977
    @krokodils19775 жыл бұрын

    It would be great to see Jeff Hawkins on Your podcast.

  • @jettrink918
    @jettrink9183 жыл бұрын

    What did she read that makes her interested in computer science?

  • @clutchcarabelli8054
    @clutchcarabelli80545 ай бұрын

    I really like the way she.....Talks?

  • @YouTube_Staff
    @YouTube_Staff5 жыл бұрын

    Feels like listening to AMSR

  • @thecactus7950
    @thecactus79505 жыл бұрын

    She sounds, and kind of looks like Judith Butler :D

  • @tylergaye6110
    @tylergaye61105 жыл бұрын

    "paper is not required for prestige, as it turns out." sums up todays colleges/universities.

  • @gbiotaone5814
    @gbiotaone58145 жыл бұрын

    Any person who doesn't value competition based on 'personal feelings' loses a lot of credibility. Its better than resenting it for ideological reasons, but its our most general method, and possibly most fundamental method of finding truth. Dismiss it at your peril.

  • @oversightentertainment6733
    @oversightentertainment67335 жыл бұрын

    Here @ 2278; views..... ...... ......

  • @spinLOL533
    @spinLOL5335 жыл бұрын

    Third

  • @fengliu975
    @fengliu9755 жыл бұрын

    Anyone find the intro just a bit creepy?

Келесі