Incamake
Q. Nibyiza kuko irashobora kubona imyitwarire myiza itarigeze ibwirwa amategeko yibidukikije.
Q-Kwiga nuburyo bwububiko bwa tekinike bugira ingaruka kumiterere yicyitegererezo, igiciro cyibikorwa remezo, ubukererwe, no kwizerwa mubipimo.
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 ibintu byo kugabanya uburemere bwibihembo 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.
Kumenya Q-Kwiga
Q. Nibyiza kuko irashobora kubona imyitwarire myiza itarigeze ibwirwa amategeko yibidukikije. Q-Kwiga nuburyo bwububiko bwa tekinike bugira ingaruka kumiterere yicyitegererezo, igiciro cyibikorwa remezo, ubukererwe, no kwizerwa mubipimo. Kugirango wubake byimbitse, fata Q-Kwiga nkicyitegererezo gikora, ntabwo ari ikintu kimwe: gusobanura ibyagezweho, gusobanura ibitekerezo, no gutandukanya ibyo sisitemu ishobora gukora byizewe nibisaba guca imanza zinzobere.
Mu myitozo, amakipe akomeye akoresha Q-Kwiga atezimbere imyubakire, amakuru, hamwe nibikorwa remezo birwanya kwizerwa nigiciro. Bandika ibipimo ngenderwaho byerekana intsinzi, bagerageza kurwanya amakuru afatika hamwe nakazi keza, kandi bagasubiramo bashingiye kubikorwa byagaragaye ko batsinzwe aho gutsinda inshuro imwe. Aha niho imyumvire yubumenyi ihinduka mubushobozi burambye kubicuruzwa, politiki, nibikorwa.
Ibyemezo byubwubatsi bitwara imikorere nigiciro cyimikorere kumyaka. Mugihe kimwe, Guhindura igipimo kimwe gishobora guhisha intege nke za sisitemu. Uburyo bukomeye cyane ni uguhuza umuvuduko wikigereranyo hamwe na disipuline yimiyoborere: kuyobora abaderevu, gufata ibimenyetso, gutangaza ibyemezo byicyemezo, no gukomeza kuvugurura uburyo bwo kwirinda nkimyitwarire yicyitegererezo, ibyo abakoresha bategereje, nibisabwa n'amategeko bigenda bihinduka.
Ingaruka z'Ingamba
Ibyemezo byubwubatsi bitwara imikorere nigiciro cyimikorere kumyaka.
Ibyemezo byubwubatsi bitwara imikorere nigiciro cyimikorere kumyaka. Mubikorwa byujuje ubuziranenge, ibi bihindurwa mumategeko agenga imikorere, imipaka nyirubwite, hamwe n'imihango yo gusubiramo kenshi kugirango amakipe ashobore kwigirira ikizere aho gupima ibidasobanutse.
Ubuhanga bwa tekinike bufasha amakipe guhitamo umurongo ukwiye, ntabwo ari shyashya gusa.
Ubuhanga bwa tekinike bufasha amakipe guhitamo umurongo ukwiye, ntabwo ari shyashya gusa. Mubikorwa byujuje ubuziranenge, ibi bihindurwa mumategeko agenga imikorere, imipaka nyirubwite, hamwe n'imihango yo gusubiramo kenshi kugirango amakipe ashobore kwigirira ikizere aho gupima ibidasobanutse.
Guhitamo neza bya injeniyeri bigabanya ibintu byizewe mubikorwa.
Guhitamo neza bya injeniyeri bigabanya ibintu byizewe mubikorwa. Mubikorwa byujuje ubuziranenge, ibi bihindurwa mumategeko agenga imikorere, imipaka nyirubwite, hamwe n'imihango yo gusubiramo kenshi kugirango amakipe ashobore kwigirira ikizere aho gupima ibidasobanutse.
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
Kugendana na robo binyuze muri gride cyangwa maze aho robot yiga inzira ngufi-yogukwirakwiza
Ibiciro bihamye nibyemezo byo kubara aho umukozi yiga ibikorwa byunguka inyungu ndende
Uburyo bwo Gushyira mu bikorwa
Q-Kwiga mubikorwa
Abakinnyi bakina umukino wa Atari (DQN ya DeepMind) biga gukina Breakout na Pong biturutse kuri pigiseli ya ecran.
Abakinnyi bakina umukino wa Atari (DQN ya DeepMind) biga gukina Breakout na Pong biturutse kuri pigiseli ya ecran Amakipe ubusanzwe abona ibisubizo byiza iyo asobanuye ibipimo byimbere imbere, agakomeza inzira yo kuzamura abantu kubibazo byimbere, kandi akurikirana inyungu zibyara umusaruro nibiciro byigihe.
Q-Kwiga mubikorwa
Kunoza igihe cyumucyo-itara kumihanda kugirango ugabanye igihe cyo gutegereza ibinyabiziga.
Gutezimbere igihe cyumucyo-mumihanda kugirango ugabanye igihe cyose cyo gutegereza ibinyabiziga Amakipe akunze kubona umusaruro ushimishije mugihe asobanura ibipimo ngenderwaho byimbere imbere, agakomeza inzira yo kuzamura abantu kubibazo, kandi akurikirana inyungu zibyara umusaruro nibiciro byigihe.
Q-Kwiga mubikorwa
Kugendana na robo binyuze muri gride cyangwa maze aho robot yiga inzira ngufi-yogukwirakwiza.
Kugendana na robo unyuze kuri gride cyangwa maze aho robot yiga inzira ngufi-yogukwirakwiza ibihembo Amakipe ubusanzwe abona ibisubizo byiza iyo asobanuye ibipimo ngenderwaho byimbere imbere, agakomeza inzira yo kuzamura abantu kubibazo byimbitse, kandi agakurikirana inyungu zibyara umusaruro nibiciro byigihe.
Q-Kwiga mubikorwa
Ibiciro bihamye nibyemezo byo kubara aho umukozi yiga ibikorwa byunguka inyungu ndende.
Ibiciro bihamye hamwe nibyemezo byo kubara aho umukozi yiga ibikorwa byunguka inyungu zimaze igihe kinini Amakipe akunze kubona umusaruro ushimishije mugihe asobanuye ibipimo ngenderwaho byimbere, agakomeza inzira yo kuzamura abantu kubibazo byimbitse, kandi agakurikirana inyungu zibyara umusaruro nibiciro byigihe.
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.
Sobanura ubukererwe, ubuziranenge, nigiciro cyibiciro mbere yo kubishyira mubikorwa. Fata buri ntambwe nk irembo ryibimenyetso: niba ibipimo bitujujwe, hagarika kuzenguruka, funga icyuho, hanyuma noneho wagure imikoreshereze.
Ibipimo byerekana umutwaro ufatika hamwe namakuru yimiterere.
Ibipimo byerekana umutwaro ufatika hamwe namakuru yimiterere. Fata buri ntambwe nk irembo ryibimenyetso: niba ibipimo bitujujwe, hagarika kuzenguruka, funga icyuho, hanyuma noneho wagure imikoreshereze.
Gukurikirana ibikoresho kubikosa, drift, ningaruka zabakoresha.
Gukurikirana ibikoresho kubikosa, drift, ningaruka zabakoresha. Fata buri ntambwe nk irembo ryibimenyetso: niba ibipimo bitujujwe, hagarika kuzenguruka, funga icyuho, hanyuma noneho wagure imikoreshereze.
Tegura inzira yo gusubiza ibyabaye mbere yo gupima.
Tegura inzira yo gusubiza ibyabaye mbere yo gupima. Fata buri ntambwe nk irembo ryibimenyetso: niba ibipimo bitujujwe, hagarika kuzenguruka, funga icyuho, hanyuma noneho wagure imikoreshereze.