Skip to Content
logologo
AI Incident Database
Open TwitterOpen RSS FeedOpen FacebookOpen LinkedInOpen GitHub
Open Menu
発見する
投稿する
  • ようこそAIIDへ
  • インシデントを発見
  • 空間ビュー
  • テーブル表示
  • リスト表示
  • 組織
  • 分類法
  • インシデントレポートを投稿
  • 投稿ランキング
  • ブログ
  • AIニュースダイジェスト
  • リスクチェックリスト
  • おまかせ表示
  • サインアップ
閉じる
発見する
投稿する
  • ようこそAIIDへ
  • インシデントを発見
  • 空間ビュー
  • テーブル表示
  • リスト表示
  • 組織
  • 分類法
  • インシデントレポートを投稿
  • 投稿ランキング
  • ブログ
  • AIニュースダイジェスト
  • リスクチェックリスト
  • おまかせ表示
  • サインアップ
閉じる

インシデント 65: Reinforcement Learning Reward Functions in Video Games

概要: OpenAI published a post about its findings when using Universe, a software for measuring and training AI agents to conduct reinforcement learning experiments, showing that the AI agent did not act in the way intended to complete a videogame.

ツール

新しいレポート新しいレポート新しいレスポンス新しいレスポンス発見する発見する履歴を表示履歴を表示

組織

すべての組織を表示
推定: OpenAIが開発し提供したAIシステムで、OpenAIに影響を与えた

インシデントのステータス

インシデントID
65
レポート数
1
インシデント発生日
2016-12-22
エディタ
Sean McGregor
Applied Taxonomies
CSETv0, CSETv1, GMF, MIT

CSETv1 分類法のクラス

分類法の詳細

Incident Number

The number of the incident in the AI Incident Database.
 

65

Special Interest Intangible Harm

An assessment of whether a special interest intangible harm occurred. This assessment does not consider the context of the intangible harm, if an AI was involved, or if there is characterizable class or subgroup of harmed entities. It is also not assessing if an intangible harm occurred. It is only asking if a special interest intangible harm occurred.
 

no

Date of Incident Year

The year in which the incident occurred. If there are multiple harms or occurrences of the incident, list the earliest. If a precise date is unavailable, but the available sources provide a basis for estimating the year, estimate. Otherwise, leave blank. Enter in the format of YYYY
 

2016

Date of Incident Month

The month in which the incident occurred. If there are multiple harms or occurrences of the incident, list the earliest. If a precise date is unavailable, but the available sources provide a basis for estimating the month, estimate. Otherwise, leave blank. Enter in the format of MM
 

12

Date of Incident Day

The day on which the incident occurred. If a precise date is unavailable, leave blank. Enter in the format of DD
 

21

Estimated Date

“Yes” if the data was estimated. “No” otherwise.
 

Yes

CSETv0 分類法のクラス

分類法の詳細

Problem Nature

Indicates which, if any, of the following types of AI failure describe the incident: "Specification," i.e. the system's behavior did not align with the true intentions of its designer, operator, etc; "Robustness," i.e. the system operated unsafely because of features or changes in its environment, or in the inputs the system received; "Assurance," i.e. the system could not be adequately monitored or controlled during operation.
 

Specification

Physical System

Where relevant, indicates whether the AI system(s) was embedded into or tightly associated with specific types of hardware.
 

Software only

Level of Autonomy

The degree to which the AI system(s) functions independently from human intervention. "High" means there is no human involved in the system action execution; "Medium" means the system generates a decision and a human oversees the resulting action; "low" means the system generates decision-support output and a human makes a decision and executes an action.
 

Unclear/unknown

Nature of End User

"Expert" if users with special training or technical expertise were the ones meant to benefit from the AI system(s)’ operation; "Amateur" if the AI systems were primarily meant to benefit the general public or untrained users.
 

Expert

Public Sector Deployment

"Yes" if the AI system(s) involved in the accident were being used by the public sector or for the administration of public goods (for example, public transportation). "No" if the system(s) were being used in the private sector or for commercial purposes (for example, a ride-sharing company), on the other.
 

No

Data Inputs

A brief description of the data that the AI system(s) used or were trained on.
 

Universe software training

MIT 分類法のクラス

Machine-Classified
分類法の詳細

Risk Subdomain

A further 23 subdomains create an accessible and understandable classification of hazards and harms associated with AI
 

7.1. AI pursuing its own goals in conflict with human goals or values

Risk Domain

The Domain Taxonomy of AI Risks classifies risks into seven AI risk domains: (1) Discrimination & toxicity, (2) Privacy & security, (3) Misinformation, (4) Malicious actors & misuse, (5) Human-computer interaction, (6) Socioeconomic & environmental harms, and (7) AI system safety, failures & limitations.
 
  1. AI system safety, failures, and limitations

Entity

Which, if any, entity is presented as the main cause of the risk
 

AI

Timing

The stage in the AI lifecycle at which the risk is presented as occurring
 

Post-deployment

Intent

Whether the risk is presented as occurring as an expected or unexpected outcome from pursuing a goal
 

Unintentional

インシデントレポート

レポートタイムライン

+1
Faulty Reward Functions in the Wild
Faulty Reward Functions in the Wild

Faulty Reward Functions in the Wild

blog.openai.com

Faulty Reward Functions in the Wild
blog.openai.com · 2016

At OpenAI, we've recently started using Universe, our software for measuring and training AI agents, to conduct new RL experiments. Sometimes these experiments illustrate some of the issues with RL as currently practiced. In the following e…

バリアント

「バリアント」は既存のAIインシデントと同じ原因要素を共有し、同様な被害を引き起こし、同じ知的システムを含んだインシデントです。バリアントは完全に独立したインシデントとしてインデックスするのではなく、データベースに最初に投稿された同様なインシデントの元にインシデントのバリエーションとして一覧します。インシデントデータベースの他の投稿タイプとは違い、バリアントではインシデントデータベース以外の根拠のレポートは要求されません。詳細についてはこの研究論文を参照してください

よく似たインシデント

テキスト類似度による

Did our AI mess up? Flag the unrelated incidents

Biased Sentiment Analysis

Google's sentiment analysis API is just as biased as humans

Oct 2017 · 7 レポート
Gender Biases in Google Translate

Semantics derived automatically from language corpora contain human-like biases

Apr 2017 · 10 レポート
Tesla Autopilot’s Lane Recognition Allegedly Vulnerable to Adversarial Attacks

AI Incident Database Incidents Converted to Issues

Mar 2019 · 1 レポート
前のインシデント次のインシデント

よく似たインシデント

テキスト類似度による

Did our AI mess up? Flag the unrelated incidents

Biased Sentiment Analysis

Google's sentiment analysis API is just as biased as humans

Oct 2017 · 7 レポート
Gender Biases in Google Translate

Semantics derived automatically from language corpora contain human-like biases

Apr 2017 · 10 レポート
Tesla Autopilot’s Lane Recognition Allegedly Vulnerable to Adversarial Attacks

AI Incident Database Incidents Converted to Issues

Mar 2019 · 1 レポート

リサーチ

  • “AIインシデント”の定義
  • “AIインシデントレスポンス”の定義
  • データベースのロードマップ
  • 関連研究
  • 全データベースのダウンロード

プロジェクトとコミュニティ

  • AIIDについて
  • コンタクトとフォロー
  • アプリと要約
  • エディタのためのガイド

インシデント

  • 全インシデントの一覧
  • フラグの立ったインシデント
  • 登録待ち一覧
  • クラスごとの表示
  • 分類法

2024 - AI Incident Database

  • 利用規約
  • プライバシーポリシー
  • Open twitterOpen githubOpen rssOpen facebookOpen linkedin
  • 1420c8e