Ikibazo
Q.
Incamake
It matters because it can find optimal behavior without ever being told the rules of its environment.
Kwibira cyane
Q-Kwiga biga imikorere yitwa Q (s, a): ibihembo byigihe kirekire byateganijwe byo gufata ingamba 'a' muri leta hanyuma ugakora neza nyuma. Intumwa itangira kumenya ntacyo, igerageza ibikorwa, ikareba ibihembo. Nyuma ya buri ntambwe yerekana Q-agaciro kagereranya kugihembo cyakiriwe hiyongereyeho igiciro cyiza cyagabanijwe giteganijwe muri leta itaha. Icy'ingenzi, ni 'off-politike' na 'moderi-yubusa': irashobora kwiga politiki nziza mugihe ishakisha uko bishakiye, kandi ntizigera ikenera icyitegererezo cyukuntu isi ihinduka. Uhaye ubushakashatsi buhagije kuri buri leta-ibikorwa byombi, Q-indangagaciro zigaragara zihuza indangagaciro nziza, kandi ibikorwa byiza muri leta iyo ari yo yose nimwe gusa ifite Q.
Ubushishozi
Intangiriro ni ivugurura rya Bellman: Q (s, a) <- Q (s, a) + alpha [r + gamma * max_a 'Q (s', a ') - Q (s, a)]. Alpha nigipimo cyo kwiga, gamma igabanywa ripima ibihembo bizaza, kandi ijambo rito ni ikosa-itandukaniro ryigihe gito. 'Max' hejuru y'ibikorwa bizakurikiraho niyo ituma itari politiki kandi ikayireka ikiga politiki nziza yumururumba nubwo ikora ubushakashatsi. Ubushakashatsi busanzwe bukorwa hamwe na epsilon-umururumba ibikorwa byo guhitamo.
Ingaruka z'Ingamba
Igiciro na bije
Ibyemezo byubwubatsi bitwara imikorere nigiciro cyimikorere kumyaka.
Ibyemezo bisobanutse
Ubuhanga bwa tekinike bufasha amakipe guhitamo umurongo ukwiye, ntabwo ari shyashya gusa.
Kugenzura ubuziranenge
Guhitamo neza bya injeniyeri bigabanya ibintu byizewe mubikorwa.
Kazoza ka Q-Kwiga
Imbonerahamwe ya Q-Kwiga biragoye mugihe leta ari nyinshi cyane kubika kumeza. Icyerekezo cyiganje ni ukuyihuza nu miyoboro mvaruganda, nko muri Deep Q-Networks (DQN), igereranya Q-indangagaciro ziva mubintu byinjira nka pigiseli. Ubushakashatsi burakomeza muguhindura ibi hamwe nubunararibonye bwo gusubiramo, imiyoboro igamije, hamwe nibihinduka nka Double DQN hamwe no gukwirakwiza Q-Kwiga bigabanya gukabya gukabya kandi byerekana kugabana byuzuye aho kuba impuzandengo imwe.
Gushyira mu bikorwa Isi
Abakinnyi bakina umukino wa Atari (DQN ya DeepMind) biga gukina Breakout na Pong biturutse kuri pigiseli ya ecran
Gutezimbere igihe-cyumucyo kumihanda kugirango ugabanye igihe cyo gutegereza ibinyabiziga
Kugenda kwa robo unyuze kuri gride cyangwa maze aho robot yiga ibihembo bigufi-byerekana inzira
Ibiciro bihamye nibyemezo byo kubara aho umukozi yiga ibikorwa byunguka inyungu ndende
Ingaruka & Kurinda
Gutezimbere igipimo kimwe gishobora guhisha intege nke za sisitemu.
Ibikorwa Remezo no kubungabunga akenshi usanga bidahabwa agaciro.
Icyuho cyumutekano no kwitegereza birashobora kwiyongera uko sisitemu igenda igorana.
Igishushanyo mbonera
Sobanura ubukererwe, ubuziranenge, nigiciro cyibiciro mbere yo kubishyira mubikorwa.
Ibipimo byerekana umutwaro ufatika hamwe namakuru yimiterere.
Gukurikirana ibikoresho kubikosa, drift, ningaruka zabakoresha.
Tegura inzira yo gusubiza ibyabaye mbere yo gupima.
Komeza Ubushakashatsi
Free newsletter
Get the daily AI briefing
Three verified AI stories every weekday morning, written in plain English. Free forever, no ads.
One email each weekday. Unsubscribe in one click. We never sell or share your address.
Test yourself
Take the Q-Learning quiz
Instant feedback on every answer, and a shareable certificate with a verifiable ID once you pass a course.
Support free AI education. AI Understanding is a 501(c)(3) nonprofit — no ads, no paywall, ever. Make a donation
Ubuyobozi bukurikira
Gahunda yo Kwiga Igipimo
Ibibazo bikunze kubazwa
What is Q-Learning?
Q. Nibyiza kuko irashobora kubona imyitwarire myiza itarigeze ibwirwa amategeko yibidukikije.
Niki Q-agaciro Q (s, a) igereranya?
Ikibazo.
Kuki Q-Kwiga bisobanurwa ngo 'hanze ya politiki'?
Ibyinshi mubikorwa bikurikiraho bisobanura Q-Kwiga yiga agaciro ka politiki yuzuye umururumba nubwo umukozi akora ubushakashatsi hamwe na politiki yimyitwarire itandukanye.
Mu mategeko yo kuvugurura, ni iki kintu cyo kugabanya gamma igenzura?
Gamma (hagati ya 0 na 1) igabanya ibihembo bizaza; indangagaciro hafi ya 1 zituma umukozi ureba kure, indangagaciro hafi 0 zituma zitareba kure.
Ni irihe kosa ry'agateganyo (TD) muri Q-Kwiga?
Ikosa rya TD ni ikinyuranyo hagati yikigereranyo gishya (ibihembo hiyongereyeho igiciro cyiza cyagabanijwe kizaza) hamwe na Q igereranya; ivugurura rigabanya iki cyuho.
Ni ukubera iki imbonerahamwe isanzwe Q-Kwiga irwana nibibazo binini nkimikino ya videwo kuva kuri pigiseli?
Imbonerahamwe yo gushakisha ikenera ibyinjira kuri leta-ibikorwa byombi, ibyo ntibishoboka iyo leta zibarirwa muri miliyari, zitera imiyoboro igereranya imiyoboro nka DQN.