Claim · 2015 · publication · Stated in source · Supported

The paper states that its agent is the first artificial agent capable of learning to excel at a diverse array of challenging tasks.

One recorded claim. The claim panel gives its qualification, the source passages with their place in each source, and how it was checked.

What it connects

Human-level control through deep reinforcement learning → states its contribution → The paper states that its agent is the first artificial agent capable of learning to excel at a diverse array of challenging tasks.

Where it appears

No collection page holds this claim. It is listed with its records in the explorer.

Claim and evidence

Human-level control through deep reinforcement learningstates its contribution ↓The paper states that its agent is the first artificial agent capable of learning to excel at a diverse array of challenging tasks.

Machine-checked, not reviewed by an editorStated in sourceSupported

Supporting evidence: primary · 1 source

Date: 2015 · publication Records dated 2015 →
Priority claim: The passage includes the document’s own claim of priority or novelty. It is the document’s claim; Selekoa does not assess it.

Scope and limitsThe paper's own statement, including its claim of priority or novelty; Selekoa does not assess the claim.

The evidence 01

primary sourceSupports the claim

Human-level control through deep reinforcement learning

Nature · 2015

Cite the original source

Cite the original document, not Selekoa. Check these details against it.

Source excerpt

“This work bridges the divide between high-dimensional sensory inputs and actions, resulting in the first artificial agent that is capable of learning to excel at a diverse array of challenging tasks.”

Location in source Nature article page, abstract

Machine-checked · 2026-10-31

Source details and check notes

Authors: Volodymyr Mnih; Koray Kavukcuoglu; David Silver; Andrei A. Rusu; Joel Veness; Marc G. Bellemare; Alex Graves; Martin Riedmiller; Andreas K. Fidjeland; Georg Ostrovski; Stig Petersen; Charles Beattie; Amir Sadik; Ioannis Antonoglou; Helen King; Dharshan Kumaran; Daan Wierstra; Shane Legg; Demis Hassabis
Version: Publisher’s article page (abstract only; the article text is not open). Year from Crossref. Retrieved for the candidate pack on 2026-10-28 (SHA-256 171622170256d1bfa2a5675a8b4c2854d6f38d6c009922cc1b243729b3269e87). The author list is the byline as printed on the first page.
Canonical address: Open the canonical source ↗
Accessed: 2026-10-28
Language: English (en)
Attribution: Volodymyr Mnih and others, “Human-level control through deep reinforcement learning”, 2015.
Reuse: No open redistribution licence asserted. Bibliographic metadata, editorial paraphrases and short attributed quotations (at most 50 words each). Recheck terms before wider redistribution.
Check notes: Candidate pack passage, key papers (research/key-papers). The quotation (31 words) matched the text retrieved for the candidate pack on 2026-10-28 (research/key-papers/verification.json). Matching ignored differences of whitespace, case, quotation marks, dashes and line-break hyphens, so the source’s typography can differ. A cross-family machine check (2026-10-30, item B029) found the quotation at its locator. No human editorial review.

Status and meaning

Editorial status. Not reviewed by an editor. An exploratory record that no editor has accepted. This status does not say whether a person has read any linked passage. Each evidence record above shows how it was checked.

Relation. A paper or other publication describes its own contribution, quoted from the expression the record names, usually its abstract or introduction. The record is the document’s own description, not an assessment: a claim of priority or novelty it contains is the document’s claim, flagged as such, and says nothing about earlier or later work.

Date. Date of the version quoted, as its source gives it (2015); other versions may word it differently.

Record ID kp-states-human-level-control-through-deep-2015-2