Reward-Free Model-based Maximalist. High-dimensional Empowerment. Self-Preserving Autonomous Agents. Theories of intelligence grounded in compositional control.https://bsky.app/profile/noreward4u.bsky.socialhttps://bsky.app/profile/noreward4u.bsky.social/post/3llgyaagmak2dFirst time seeing a wild giraffe. Just chillin’ on the side of the road.28 Mar 2025 14:04 +0000at://did:plc:coaoduvjg2oebnjnjpzm4mcn/app.bsky.feed.post/3llgyaagmak2dhttps://bsky.app/profile/noreward4u.bsky.social/post/3ll5okbte4c2aThey say don’t meet your heroes, but I traveled to South Africa and met mine and it was worth it. Stoffel the Honey Badger became a major inspiration for my PhD thesis when my advisor showed our lab a BBC show on clever animals who can solve long horizon tasks, presumably for abstract reasons.24 Mar 2025 21:17 +0000at://did:plc:coaoduvjg2oebnjnjpzm4mcn/app.bsky.feed.post/3ll5okbte4c2ahttps://bsky.app/profile/noreward4u.bsky.social/post/3lf3pbjgsls2pUnfortunately for SlipFrosty, a theory of instrumental intelligence is inseparable from a theory of normative intelligence. Abolish the value function!06 Jan 2025 17:53 +0000at://did:plc:coaoduvjg2oebnjnjpzm4mcn/app.bsky.feed.post/3lf3pbjgsls2phttps://bsky.app/profile/noreward4u.bsky.social/post/3lekxskymns2iMy favorite interview from the past year, of philosopher Pete Wolfendale. Recommended to anyone interested in AI, the relationship between value, aesthetics and ethics, or anyone who wants a reason to abandon "rationality as Bayes + Utility". https://www.youtube.com/watch?v=0xMc9OAYm5Q&t=0s&ab_channel=TheGradient31 Dec 2024 02:11 +0000at://did:plc:coaoduvjg2oebnjnjpzm4mcn/app.bsky.feed.post/3lekxskymns2ihttps://bsky.app/profile/noreward4u.bsky.social/post/3le7xmw477k2uIMO, A problem with RL is that, in sparse-reward problems, value functions don’t have a general decomposition over high-dimensional transition kernels so people are trying to learn neural-net approximations to difficult-to-generalize functions from a lot of experience. Fun ep. [contains quote post or other embedded content]26 Dec 2024 17:08 +0000at://did:plc:coaoduvjg2oebnjnjpzm4mcn/app.bsky.feed.post/3le7xmw477k2uhttps://bsky.app/profile/noreward4u.bsky.social/post/3ldixgku7qc2j17 Dec 2024 13:33 +0000at://did:plc:coaoduvjg2oebnjnjpzm4mcn/app.bsky.feed.post/3ldixgku7qc2jhttps://bsky.app/profile/noreward4u.bsky.social/post/3lb64hhxqsc2yBSKY academics, lets get to know each other! Quote this & tell me: 1) a project you are working on & 2) an odd idea/theory you aren’t working on but keep thinking about 1. High-dim planning 2. What are the minimal requirements for two agents to recognize each other as acting on behalf of reasons. [contains quote post or other embedded content]17 Nov 2024 19:14 +0000at://did:plc:coaoduvjg2oebnjnjpzm4mcn/app.bsky.feed.post/3lb64hhxqsc2yhttps://bsky.app/profile/noreward4u.bsky.social/post/3lauayrqkm22dComing over from twitter, please give me a follow! My thesis below is on the connection between compositional planning and intrinsic motivation for self-preserving agents 🙂 https://drive.google.com/file/d/1peG7ZMPBDgmTmw0nUqgdHTvh09Vy90pk/view13 Nov 2024 21:08 +0000at://did:plc:coaoduvjg2oebnjnjpzm4mcn/app.bsky.feed.post/3lauayrqkm22d