---
date: '2022-11-28T11:34:45'
hypothesis-meta:
  created: '2022-11-28T11:34:45.963292+00:00'
  document:
    title:
    - 1809.09672.pdf
  flagged: false
  group: __world__
  hidden: false
  id: qMPVfG8QEe2WJWufCDu9ww
  links:
    html: https://hypothes.is/a/qMPVfG8QEe2WJWufCDu9ww
    incontext: https://hyp.is/qMPVfG8QEe2WJWufCDu9ww/arxiv.org/pdf/1809.09672.pdf
    json: https://hypothes.is/api/annotations/qMPVfG8QEe2WJWufCDu9ww
  permissions:
    admin:
    - acct:ravenscroftj@hypothes.is
    delete:
    - acct:ravenscroftj@hypothes.is
    read:
    - group:__world__
    update:
    - acct:ravenscroftj@hypothes.is
  tags:
  - rl
  - bandit
  - nlproc
  - summarization
  target:
  - selector:
    - end: 10089
      start: 9945
      type: TextPositionSelector
    - exact: andit is a decision-making formal-ization in which an agent repeatedly
        chooses oneof several actions, and receives a reward based onthis choice.
      prefix: dient reinforcementlearning. A b
      suffix: " The agent\u2019s goal is to quickly "
      type: TextQuoteSelector
    source: https://arxiv.org/pdf/1809.09672.pdf
  text: 'Definition for contextual bandit: an agent that repeatedly choses one of
    several actions and receives a reward based on this choice.'
  updated: '2022-11-28T11:34:45.963292+00:00'
  uri: https://arxiv.org/pdf/1809.09672.pdf
  user: acct:ravenscroftj@hypothes.is
  user_info:
    display_name: James Ravenscroft
in-reply-to: https://arxiv.org/pdf/1809.09672.pdf
tags:
- rl
- bandit
- nlproc
- summarization
- hypothesis
type: annotation
url: /annotations/2022/11/28/1669635285

---



 <blockquote>andit is a decision-making formal-ization in which an agent repeatedly chooses oneof several actions, and receives a reward based onthis choice.</blockquote>Definition for contextual bandit: an agent that repeatedly choses one of several actions and receives a reward based on this choice.