A field guide to AI positions

Reinforcement learning

Inside a model.

Sources are over 18 months old.

Publication dates and source age

Sources counted: 3

Newest dated source: 2022-03-04

Assessed at this edition's evidence cutoff: 2026-09-15. 18-month boundary: 2025-03-15.

Publication age does not tell us whether a claim is still valid. Reading an old source again does not make its publication date newer. An update date does not establish that the passage we used was updated.

Open in the glossary Reading notes · Structured record

Prepared with AI assistance. Not independently fact-checked. Original sources and qualifications are below.

In plain language

Training that uses rewards from attempted actions to adjust which actions a system selects. [1]

Reference this explanation or suggest a correction

Explanation based on the linked sources. Claim ID: claim-term-reinforcement-learning-1a5192ba3d7825ca26b24a72. Edition 0.20.0.

Link to this explanation · Suggest a correction · How corrections work

Limits & distinctions

A higher reward can miss the outcome people intended. RLHF is a specific approach using human feedback, not a name for all reinforcement learning. [2] [3]

Reference this explanation or suggest a correction

Explanation based on the linked sources. Claim ID: claim-term-reinforcement-learning-09422ce4d5c74cb753a9bb98. Edition 0.20.0.

Link to this explanation · Suggest a correction · How corrections work

A fuller explanation

A system tries actions in an environment and receives numerical feedback. Training aims for more reward over time. A game score can supply feedback; other tasks need other reward rules. [1]

Reference this explanation or suggest a correction

Explanation based on the linked sources. Claim ID: claim-term-reinforcement-learning-1e4c26398ee834b2e16dc7b8. Edition 0.20.0.

Link to this explanation · Suggest a correction · How corrections work

How it relates to the map

Examine what earns a reward before interpreting claims that training improved behavior. [2]

Reference this explanation or suggest a correction

Editorial interpretation or qualification. Claim ID: claim-term-reinforcement-learning-25f52a21ad9f2e54a62ed1b2. Edition 0.20.0.

Link to this explanation · Suggest a correction · How corrections work

Share this page

https://theaiatlas.org/ideas/reinforcement-learning/

Download a share image · Vector image

Image previews are summaries. Keep the page link so readers can check the evidence.

Sources and what we read

  1. 1. Deep Reinforcement Learning

    David Silver / Google DeepMind · First-hand source · Published 2016-06-17 · Material last read 2026-09-15

    Source is over 18 months old.

    Publication dates and source age

    Sources counted: 1

    Newest dated source: 2016-06-17

    Assessed at this edition's evidence cutoff: 2026-09-15. 18-month boundary: 2025-03-15.

    Publication age does not tell us whether a claim is still valid. Reading an old source again does not make its publication date newer. An update date does not establish that the passage we used was updated.

    Read scope is described in the source note.

    No archive check recorded.

    Read the introduction defining reinforcement learning through trial, feedback and long-term rewards. Used for the training setup, without adopting human comparisons or generality claims.

    Source ID: glossary-model-reinforcement

  2. 2. Concrete Problems in AI Safety

    Dario Amodei and coauthors / arXiv · First-hand source · Published 2016-06-21 · Updated 2016-07-25 · Material last read 2026-09-15

    Source is over 18 months old.

    Publication dates and source age

    Sources counted: 1

    Newest dated source: 2016-06-21

    Assessed at this edition's evidence cutoff: 2026-09-15. 18-month boundary: 2025-03-15.

    Publication age does not tell us whether a claim is still valid. Reading an old source again does not make its publication date newer. An update date does not establish that the passage we used was updated.

    Read scope is described in the source note.

    No archive check recorded.

    Read the abstract's five accident-risk problems including reward hacking and distributional shift. Does not give a general catastrophe probability.

    Source ID: concrete-safety

  3. 3. Training language models to follow instructions with human feedback

    Long Ouyang and coauthors / arXiv · First-hand source · Published 2022-03-04 · Material last read 2026-09-15

    Source is over 18 months old.

    Publication dates and source age

    Sources counted: 1

    Newest dated source: 2022-03-04

    Assessed at this edition's evidence cutoff: 2026-09-15. 18-month boundary: 2025-03-15.

    Publication age does not tell us whether a claim is still valid. Reading an old source again does not make its publication date newer. An update date does not establish that the passage we used was updated.

    Read scope is described in the source note.

    No archive check recorded.

    Read abstract, section 3.1's demonstrations/comparisons/reward-model procedure and section 5.3's limitations. Human preference judgments and improved results on the authors' tasks do not establish universal alignment or safety. Publication date checked on the arXiv abstract page.

    Source ID: instructgpt-paper

Edition and machine-readable evidence

Content version 0.20.0. Evidence cutoff 2026-09-15; this does not mean every source was read on that day.

Pinned complete dataset · Complete evidence page · Agent consumption guide