‹ BackHN Continuity

Thread

Dream-RSI: Recursive Self-Improvement through Evolving Worlds

213 points · 53 comments · bananaflag

  1. benbenben111 · · focus · HN ↗
    FYI; the paper is clearly a reference to Danijar Hafner&#x27;s &#x27;Dreamer&#x27; line of work, which was published in 2019, and which Danijar has continued to iterate on. <a href="https:&#x2F;&#x2F;arxiv.org&#x2F;abs&#x2F;1912.01603" rel="nofollow">https:&#x2F;&#x2F;arxiv.org&#x2F;abs&#x2F;1912.01603

    The TalkRL podcasts on this line of work are reasonable accessible and quite interesting. <a href="https:&#x2F;&#x2F;www.talkrl.com&#x2F;episodes&#x2F;danijar-hafner" rel="nofollow">https:&#x2F;&#x2F;www.talkrl.com&#x2F;episodes&#x2F;danijar-hafner <a href="https:&#x2F;&#x2F;www.talkrl.com&#x2F;episodes&#x2F;danijar-hafner-on-dreamer-v4&#x2F;transcript" rel="nofollow">https:&#x2F;&#x2F;www.talkrl.com&#x2F;episodes&#x2F;danijar-hafner-on-dreamer-v4...

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.