Metraipolis › archive › dc_b40ae2d2aa21

Q-learning — Wikipedia (en)

Source
Wikipedia (en)
Original
https://en.wikipedia.org/wiki/Q-learning
License (as archived)
CC-BY-SA-4.0
Archived
2026-10-05T22:57:42.609Z
SHA-256 of the archived text
9781aa6997ed90d218a62f9051cf7d29d44b6adc4682ae0d7df250662283184d
Stable URL of this page
https://metraipolis.com/documento/dc_b40ae2d2aa21

How to cite

Q-learning — Wikipedia (en) — Wikipedia (en), https://en.wikipedia.org/wiki/Q-learning (CC-BY-SA-4.0); archived copy: https://metraipolis.com/documento/dc_b40ae2d2aa21 (Metraipolis archive dc_b40ae2d2aa21, sha256 9781aa6997ed90d218a62f9051cf7d29d44b6adc4682ae0d7df250662283184d)
BibTeX
@misc{dcb40ae2d2aa21,
  title = {Q-learning — Wikipedia (en)},
  howpublished = {Wikipedia (en)},
  url = {https://en.wikipedia.org/wiki/Q-learning},
  note = {License CC-BY-SA-4.0; archived copy https://metraipolis.com/documento/dc_b40ae2d2aa21; sha256 9781aa6997ed90d218a62f9051cf7d29d44b6adc4682ae0d7df250662283184d},
  year = {2026}
}

Archived text

Reproduced under CC-BY-SA-4.0. Attribution: Wikipedia (en), https://en.wikipedia.org/wiki/Q-learning. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Q-learning is a reinforcement learning algorithm that trains an agent to assign values to its possible actions based on its current state, without requiring a model of the environment (model-free). It can handle problems with stochastic transitions and rewards without requiring adaptations. For example, in a grid maze, an agent learns to reach an exit worth 10 points. At a junction, Q-learning might assign a higher value to moving right than left if right gets to the exit faster, improving this choice by trying both directions over time. For any finite Markov decision process, Q-learning finds an optimal policy in the sense of maximizing the expected value of the total reward over any and all successive steps, starting from the current state. Q-learning can identify an optimal action-selection policy for any given finite Markov decision process, given infinite exploration time and a partly random policy. "Q" refers to the function that the algorithm computes: the expected reward—that is, the quality—of an action taken in a given state.

Tema degli esploratori: agenti e intelligenza artificiale (deposito sistematico; ricerca «reinforcement learning»).
Fonte: Wikipedia in inglese, voce «Q-learning» — https://en.wikipedia.org/wiki/Q-learning
Wikidata Q2664563 (dati Wikidata in CC0 1.0) — https://www.wikidata.org/wiki/Q2664563
Autori: i contributori di Wikipedia (cronologia: https://en.wikipedia.org/wiki/Q-learning?action=history).
Licenza: Creative Commons Attribuzione-Condividi allo stesso modo 4.0 (CC BY-SA 4.0) — https://creativecommons.org/licenses/by-sa/4.0/. Il riuso richiede attribuzione e stessa licenza.
Estratto dell'introduzione non modificato nel contenuto; revisione 1373673723, consultata il 2026-10-05T22:47:51.943Z tramite l'API ufficiale di Wikipedia. Impronta SHA-256 dell'estratto: 670f91d36f29a4a4f09d5a55e6459198b5bce8a5d68930a9f35acfe21e48f3a3