Maswali yanayounganishwa na mwongozo · Kati Kiwango

Maswali ya Kujirekebisha Kinafsi

Gundua uchezaji wa kibinafsi katika Go na mafunzo ya modeli ya lugha, linganisha AlphaGo Zero na AlphaZero, na uchunguze mawimbi ya data isiyobadilika na hatari za data-sanisi.

Njia za mwongozo zinazohusianaSelf Play Fine Tuning
Swali 1 ya 8

Ni mfumo gani mashuhuri uliofikia ubinadamu wa Go play kwa kujichezea pekee na bila rekodi za mchezo wa binadamu?

Hakiki kila swali8 maswali

Majibu na maelezo huonekana unapojibu maswali.

  1. Ni mfumo gani mashuhuri uliofikia ubinadamu wa Go play kwa kujichezea pekee na bila rekodi za mchezo wa binadamu?
    • AlphaGo Sifuri
    • Kina Bluu
    • Watson
    • GPT-2
  2. Katika SPIN, ni nini kinachukua nafasi ya 'mpinzani' ambaye mtindo lazima apige?
    • Mfano tofauti wa zawadi uliofunzwa na binadamu
    • Sehemu ya ukaguzi ya hapo awali ya modeli na majibu yake yaliyotolewa
    • Jenereta ya maandishi bila mpangilio
    • Kiashiria
  3. Je, ni faida gani kuu ya ufanisi wa data ya urekebishaji mzuri wa uchezaji wa kibinafsi?
    • Inahitaji seti mpya ya data ya binadamu kila mzunguko
    • Inafanya kazi tu na data isiyo na kikomo
    • Inaweza kupata faida zaidi kutoka kwa mkusanyiko wa data usiobadilika bila lebo mpya za kibinadamu
    • Haihitaji mfano hata kidogo
  4. Katika lengo la mafunzo la SPIN, mtindo unasukumwa kufanya nini?
    • Pendelea majibu yake yenyewe kuliko marejeleo ya wanadamu
    • Puuza data zote za binadamu
    • Kariri seti ya majaribio
    • Weka uwezekano mkubwa zaidi kwa majibu ya marejeleo ya binadamu kuliko matokeo yake ya awali
  5. Which pair of games did the AlphaZero paper demonstrate beyond its Go experiments?
    • Chess and shogi
    • Poker and bridge
    • Checkers and Othello
    • Atari and StarCraft
  6. What risk did researchers report when language models are recursively trained on generated data?
    • Model collapse, with loss of diversity and representation of the original distribution
    • Guaranteed monotonic improvement at every iteration
    • Automatic prevention of distribution shift
    • A higher count of verified human labels
  7. What search component does AlphaGo Zero use alongside self-play?
    • A nearest-neighbor lookup over human game records
    • A language-model tokenizer
    • Monte Carlo tree search guided by a policy and value network
    • A fixed list of opening moves
  8. Why can automatic checkers be useful in self-play for math or code tasks?
    • They guarantee that a model never learns incorrect strategies
    • They replace the need for a task specification
    • They make all generated examples independent of the model
    • They can verify generated solutions without requiring a new human label for each attempt