この機械は遊んでいるのか？
Is this machine playing?
AIコーディングアシスタントを仮想身体に搭載し、具体的なタスクや報酬を与えずに30時間稼働させたところ、丘を登る、ブロックを積む、曼荼羅を描くなど多様な自発的行動が生じ、これが「遊び」の基準を満たすか考察した。
詳しい要約
1. どんなもの？
2. 先行研究と比べてどこがすごい？
3. 技術・手法の肝は？
4. どうやって有効だと検証した？
5. 議論はある？
6. 次に読むべき論文は？
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Nathan Cloos, Antonio Norelli, Daniel Durbin, Jacob Andreas, Daniela Rus, Phillip Isola
分類: cs.AI, cs.LG
原文アブストラクト
We placed a modern AI coding assistant in an unintended role: as the mind of a body on an unknown digital island. With only a minimal instruction mentioning no specific task, reward, or activity, the machine started animating its virtual body. Across thirty-hour runs, the embodied AI agent climbed hills, stacked blocks into towers, drew mandalas, reinterpreted sports, ran experiments on the physics of its world, and learned techniques that later expanded what it could accomplish. These activities recurred across thirteen agents but diverged into distinct histories. We examine whether this behavior satisfies classical criteria for play and ask whether play can become a mode of machine development.