Mastering Diverse Domains through World Models · HackerPapers discussions

Mastering Diverse Domains through World Models — mentioned by smokel

Mon, 07 Apr 2025 15:55:24 GMT

Yup, the technical details are described in this paper from early 2023. Seems like Nature takes its time. That used to be a good thing :) https://arxiv.org/abs/2301.04104

Paper and discussion history. A mention is not an endorsement.

Mastering Diverse Domains through World Models — mentioned by notacat

Mon, 03 Jul 2023 15:09:43 GMT

AI Research Residency Program (1 year) | Zug/Zurich area | Full time | On site | 100-200k CHF/annum I am launching a new AI research organisation in the Zug/Zurich area. The goal of the organisation is to make a meaningful contribution towards solving AGI. I am looking for employees number no. 1 and 2. This will ideally be someone with a history of interesting research and a clear agenda for future research. I am personally interested in LLM's, MuZero (https://arxiv.org/abs/1911.08265), Dreamer (https://arxiv.org/pdf/2301.04104v1.pdf) and DreamCoder (https://arxiv.org/abs/2006.08381), and…

Paper and discussion history. A mention is not an endorsement.

Mastering Diverse Domains through World Models — mentioned by O__________O

Mon, 30 Jan 2023 13:08:51 GMT

Paper provides a model based reinforcement learning (MBRL) algorithm that performs well over a wide variety of environments, from 2D to 3D, simple to complex. It can get diamonds in a simplified version of Minecraft and work well out of the box without tuning. ____ Paper: - https://arxiv.org/pdf/2301.04104v1.pdf Third-party review of paper: - https://youtube.com/watch?v=vfpZu0R1s1Y Code: - “Coming Soon”

Paper and discussion history. A mention is not an endorsement.

Mastering Diverse Domains through World Models — HN submission

Wed, 11 Jan 2023 14:25:04 GMT

Mastering diverse domains through world models

76 points; 7 discussion replies on HN. Paper and source history. A submission is not an endorsement.