$\"Screenshot$

\n","updatedAt":"2025-02-10T04:11:57.978Z","author":{"_id":"60f1abe7544c2adfd699860c","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674929746905-60f1abe7544c2adfd699860c.jpeg","fullname":"AK","name":"akhaliq","type":"user","isPro":false,"isHf":true,"isHfAdmin":false,"isMod":false,"followerCount":9179,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.3187815546989441},"editors":["akhaliq"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674929746905-60f1abe7544c2adfd699860c.jpeg"],"reactions":[{"reaction":"👍","users":["search-facility"],"count":1}],"isReport":false}},{"id":"67aa5cc04b9351c4dad21fe8","author":{"_id":"66a09e3a7bcf5121db528ac5","avatarUrl":"/avatars/edf5cb4f8a90ce06dc2cf1ce272eb3f0.svg","fullname":"uğur ismail","name":"uiaT","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false},"createdAt":"2025-02-10T20:08:32.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"vaov shittiest paper i have ever read. Computer guys should stay in their place and try to read more Michael Levin.","html":"

vaov shittiest paper i have ever read. Computer guys should stay in their place and try to read more Michael Levin.

\n","updatedAt":"2025-02-10T20:08:32.120Z","author":{"_id":"66a09e3a7bcf5121db528ac5","avatarUrl":"/avatars/edf5cb4f8a90ce06dc2cf1ce272eb3f0.svg","fullname":"uğur ismail","name":"uiaT","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.9609435796737671},"editors":["uiaT"],"editorAvatarUrls":["/avatars/edf5cb4f8a90ce06dc2cf1ce272eb3f0.svg"],"reactions":[],"isReport":false},"replies":[{"id":"67ab7f70b8d7fe3b963e90fa","author":{"_id":"64417598cea37249a0fee365","avatarUrl":"/avatars/5a73b8f45a167a0577d109d044bf0438.svg","fullname":"Jesse Fagan","name":"jfagan","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false},"createdAt":"2025-02-11T16:48:48.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"Should have been a blog post.","html":"

Should have been a blog post.

\n","updatedAt":"2025-02-11T16:48:48.349Z","author":{"_id":"64417598cea37249a0fee365","avatarUrl":"/avatars/5a73b8f45a167a0577d109d044bf0438.svg","fullname":"Jesse Fagan","name":"jfagan","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.9797872304916382},"editors":["jfagan"],"editorAvatarUrls":["/avatars/5a73b8f45a167a0577d109d044bf0438.svg"],"reactions":[{"reaction":"👍","users":["hestu"],"count":1}],"isReport":false,"parentCommentId":"67aa5cc04b9351c4dad21fe8"}}]},{"id":"67aaa9193c8dbf552779bcaf","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":318,"isUserFollowing":false},"createdAt":"2025-02-11T01:34:17.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"This is an automated message from the [Librarian Bot](https://huggingface.co/librarian-bots). I found the following papers similar to this paper. \n\nThe following papers were recommended by the Semantic Scholar API \n\n* [The Meta-Representation Hypothesis](https://huggingface.co/papers/2501.02481) (2025)\n* [A Basis for Human Responsibility in Artificial Intelligence Computation](https://huggingface.co/papers/2501.12498) (2025)\n\n\n Please give a thumbs up to this comment if you found it helpful!\n\n If you want recommendations for any Paper on Hugging Face checkout [this](https://huggingface.co/spaces/librarian-bots/recommend_similar_papers) Space\n\n You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: `@librarian-bot recommend`","html":"

This is an automated message from the Librarian Bot. I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API

The Meta-Representation Hypothesis (2025)
A Basis for Human Responsibility in Artificial Intelligence Computation (2025)

Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on Hugging Face checkout this Space

You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: \n\n@librarian-bot\n\t recommend

\n","updatedAt":"2025-02-11T01:34:17.231Z","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":318,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8112123608589172},"editors":["librarian-bot"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2502.04403","authors":[{"_id":"67a97c7542d4d2f92ee57d20","name":"David Abel","hidden":false},{"_id":"67a97c7542d4d2f92ee57d21","user":{"_id":"6602bfb4a44fc523256912b0","avatarUrl":"/avatars/d23fd4d654fa490389dd6dfb37c0e834.svg","isPro":false,"fullname":"Andre Barreto","user":"andrebarreto","type":"user"},"name":"André Barreto","status":"admin_assigned","statusLastChangedAt":"2025-02-10T16:12:50.057Z","hidden":false},{"_id":"67a97c7542d4d2f92ee57d22","user":{"_id":"64929b5d53b71f9cf934dcb8","avatarUrl":"/avatars/462add1d4f423f831481acf53217f900.svg","isPro":false,"fullname":"Michael Bowling","user":"Alkaroth","type":"user"},"name":"Michael Bowling","status":"admin_assigned","statusLastChangedAt":"2025-02-10T16:13:08.978Z","hidden":false},{"_id":"67a97c7542d4d2f92ee57d23","name":"Will Dabney","hidden":false},{"_id":"67a97c7542d4d2f92ee57d24","name":"Shi Dong","hidden":false},{"_id":"67a97c7542d4d2f92ee57d25","name":"Steven Hansen","hidden":false},{"_id":"67a97c7542d4d2f92ee57d26","name":"Anna Harutyunyan","hidden":false},{"_id":"67a97c7542d4d2f92ee57d27","name":"Khimya Khetarpal","hidden":false},{"_id":"67a97c7542d4d2f92ee57d28","user":{"_id":"6313f69d54e6e5d9f0fb9f10","avatarUrl":"/avatars/12114d479bb6dc394d29f988944f6d47.svg","isPro":false,"fullname":"Clare Lyle","user":"justclarifying","type":"user"},"name":"Clare Lyle","status":"admin_assigned","statusLastChangedAt":"2025-02-10T16:13:37.970Z","hidden":false},{"_id":"67a97c7542d4d2f92ee57d29","user":{"_id":"64b9310403124195cd9778ec","avatarUrl":"/avatars/57c594d3d0f97d3010b15b6a0806451c.svg","isPro":false,"fullname":"Razvan Pascanu","user":"razp","type":"user"},"name":"Razvan Pascanu","status":"admin_assigned","statusLastChangedAt":"2025-02-10T16:13:44.165Z","hidden":false},{"_id":"67a97c7542d4d2f92ee57d2a","name":"Georgios Piliouras","hidden":false},{"_id":"67a97c7542d4d2f92ee57d2b","name":"Doina Precup","hidden":false},{"_id":"67a97c7542d4d2f92ee57d2c","name":"Jonathan Richens","hidden":false},{"_id":"67a97c7542d4d2f92ee57d2d","name":"Mark Rowland","hidden":false},{"_id":"67a97c7542d4d2f92ee57d2e","name":"Tom Schaul","hidden":false},{"_id":"67a97c7542d4d2f92ee57d2f","name":"Satinder Singh","hidden":false}],"publishedAt":"2025-02-06T08:34:57.000Z","submittedOnDailyAt":"2025-02-10T01:41:57.959Z","title":"Agency Is Frame-Dependent","submittedOnDailyBy":{"_id":"60f1abe7544c2adfd699860c","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674929746905-60f1abe7544c2adfd699860c.jpeg","isPro":false,"fullname":"AK","user":"akhaliq","type":"user"},"summary":"Agency is a system's capacity to steer outcomes toward a goal, and is a\ncentral topic of study across biology, philosophy, cognitive science, and\nartificial intelligence. Determining if a system exhibits agency is a\nnotoriously difficult question: Dennett (1989), for instance, highlights the\npuzzle of determining which principles can decide whether a rock, a thermostat,\nor a robot each possess agency. We here address this puzzle from the viewpoint\nof reinforcement learning by arguing that agency is fundamentally\nframe-dependent: Any measurement of a system's agency must be made relative to\na reference frame. We support this claim by presenting a philosophical argument\nthat each of the essential properties of agency proposed by Barandiaran et al.\n(2009) and Moreno (2018) are themselves frame-dependent. We conclude that any\nbasic science of agency requires frame-dependence, and discuss the implications\nof this claim for reinforcement learning.","upvotes":23,"discussionId":"67a97c7642d4d2f92ee57d77","ai_summary":"The puzzle of determining agency in systems is explored through the lens of reinforcement learning, establishing that agency is inherently frame-dependent.","ai_keywords":["reinforcement learning","agency","frame-dependent"]},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"6039478ab3ecf716b1a5fd4d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6039478ab3ecf716b1a5fd4d/_Thy4E7taiSYBLKxEKJbT.jpeg","isPro":true,"fullname":"taesiri","user":"taesiri","type":"user"},{"_id":"645a07c5268f478c25b5ef40","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/645a07c5268f478c25b5ef40/GzSF_DLhY-xN4kNvZ4UJz.png","isPro":false,"fullname":"Xingye","user":"PlanetMoon","type":"user"},{"_id":"6093a02dc4a92d63a91c5236","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6093a02dc4a92d63a91c5236/yUte6V0FU0BvVFAbON-9n.jpeg","isPro":true,"fullname":"Diwank Tomer","user":"diwank","type":"user"},{"_id":"66f612b934b8ac9ffa44f084","avatarUrl":"/avatars/6836c122e19c66c90f1673f28b30d7f0.svg","isPro":false,"fullname":"Tang","user":"tommysally","type":"user"},{"_id":"633a00248f27255b6b54ea5f","avatarUrl":"/avatars/8ad54c2d8a42093923cbdd6f15e0d7a7.svg","isPro":false,"fullname":"dfuhoiysOHSVFh82934gfjklb","user":"huba-buba","type":"user"},{"_id":"627e0db3f075a64a8e7c8c8b","avatarUrl":"/avatars/0d3de3a8c02c2388017d3bc1665bc101.svg","isPro":false,"fullname":"Kelvin","user":"kh","type":"user"},{"_id":"6471ce7f021b8f492f062181","avatarUrl":"/avatars/d9ac851fd6810dd7862eaea47a8a9477.svg","isPro":false,"fullname":"Falcon","user":"FalconLlamalpaca","type":"user"},{"_id":"648eb1eb59c4e5c87dc116e0","avatarUrl":"/avatars/c636cea39c2c0937f01398c94ead5dad.svg","isPro":false,"fullname":"fdsqefsgergd","user":"T-representer","type":"user"},{"_id":"651c80a26ba9ab9b9582c273","avatarUrl":"/avatars/e963452eafd21f517d800f2e58e0f918.svg","isPro":false,"fullname":"siyeng feng","user":"siyengfeng","type":"user"},{"_id":"61ca43f194afcb20ceb764d7","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1640645587885-noauth.jpeg","isPro":false,"fullname":"Raúl Garrido","user":"happybydefault","type":"user"},{"_id":"650fcb8dc3b9d8d1eb4e578f","avatarUrl":"/avatars/33ea51a58a18033c74d46b6a61ec529b.svg","isPro":false,"fullname":"Diksha Shrivastava","user":"diksha-shrivastava13","type":"user"},{"_id":"634614a7547c70e4b7d1e2c4","avatarUrl":"/avatars/d2a5f4cce188db7086e7f8f56e284554.svg","isPro":false,"fullname":"Varun Srivastava","user":"varunneal","type":"user"}],"acceptLanguages":["*"],"dailyPaperRank":0}">

Papers

arxiv:2502.04403

Agency Is Frame-Dependent

Published on Feb 6, 2025

· Submitted by

AK on Feb 10, 2025

Upvote

Authors:

André Barreto ,

Michael Bowling ,

Clare Lyle ,

Razvan Pascanu ,

Abstract

The puzzle of determining agency in systems is explored through the lens of reinforcement learning, establishing that agency is inherently frame-dependent.

AI-generated summary

Agency is a system's capacity to steer outcomes toward a goal, and is a central topic of study across biology, philosophy, cognitive science, and artificial intelligence. Determining if a system exhibits agency is a notoriously difficult question: Dennett (1989), for instance, highlights the puzzle of determining which principles can decide whether a rock, a thermostat, or a robot each possess agency. We here address this puzzle from the viewpoint of reinforcement learning by arguing that agency is fundamentally frame-dependent: Any measurement of a system's agency must be made relative to a reference frame. We support this claim by presenting a philosophical argument that each of the essential properties of agency proposed by Barandiaran et al. (2009) and Moreno (2018) are themselves frame-dependent. We conclude that any basic science of agency requires frame-dependence, and discuss the implications of this claim for reinforcement learning.