Independent publisher

Nakamoto

Infatoshi

Models in Library0

Datasets in Library1

Models on Hugging Face12

Followers70

Compare the published evidence

This profile connects the 1 model and dataset record shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.

Published tasks: Reinforcement learning.

Reported licenses: other. Open a record to review its specific license and conditions.

Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.

Datasets

Dataset · Reinforcement learning

mcsr-ranked-vods

Nakamoto

Twitch VODs of MCSR Ranked matches (Minecraft 1.16.1 random-seed any% speedruns, Diamond+ players), collected for a pixels-to-keyboard speedrun agent. Each VOD comes with its inverse-dynamics-model targets. - vods/ /.mp4: the VOD (360p30 as downloaded), sharded by the 2nd and 3rd characters of the name. - vods/ /.idmtargets.npz: per-frame targets aligned to the VOD (from the match replay, see Infatoshi/mcsr-speedrun-train). - raw/: a few full downloads that were not yet processed. Source: the MCSR Ranked API (match index, VOD links) and Twitch. The footage belongs to its streamers; this is a research mirror. Companion repos: Infatoshi/mcsr-speedrun-train (training shards, replays…

Publicly accessible other

View dataset