Great to see the next keynote by Pierluca D'Oro at the AutoRL workshop also using The NetHack Learning Environment. Motif (arxiv.org/abs/2310.00166) uses LLMs to intrinsically motivate agents, leading to better score in NetHack than training on the environment's extrinsic reward 🤯

What's stopping you from working like this?

does anyone know how to prevent this from happening?? help

Most video games kill your potential. In NetHack, it gets killed by a random monster first.

Steve Strickland ARC will be solved before Nethack

💯‼️ That's why Davide Paglieri created balrogai.com

Yearly reminder

cc Tim Rocktäschel

In the meantime, The NetHack Learning Environment and balrogai.com...

💯 For me this is NetHack (see The NetHack Learning Environment and balrogai.com). I am still holding my breath.

Can AI agents adapt zero-shot, to complex multi-step language instructions in open-ended environments? We present MaestroMotif, a method for AI-assisted skill design that produces highly capable and steerable hierarchical agents. To the best of our knowledge, it is the first

⚔️ MiniHack Updates! ⚔️ 1️⃣ MiniHack 1.0.0 is here! Following popular demand, it now supports the new Gymnasium API and is built on NLE 1.1.0. Huge thanks to @Stephen_Oman (maintainer of The NetHack Learning Environment ) for his outstanding contribution! 🙌

All part of the Pokémon to The NetHack Learning Environment pipeline… all we need is a cute soundtrack heiner Tim Rocktäschel

Happy to announce the latest release of The NetHack Learning Environment (version 1.2.0). You can now use the seed function to make the dungeon layout reproducible across training episodes. The in-level interaction and combat is still randomly determined and doesn't impact lower level layouts.

A couple bits of news: 1. Happy to share my first (human) NetHack ascension-next step is RL agents :) 2. I wrote a post discussing some The NetHack Learning Environment challenges & how they map to open problems in RL & agentic AI. Still the best RL benchmark imo. mikaelhenaff.substack.com/p/first-nethac…

Happy "The NetHack Learning Environment is still completely unsolved" day for those of you who are celebrating it. We released The NetHack Learning Environment (arxiv.org/abs/2006.13760) on this day five years ago. Current frontier models achieve only ~1.7% progression (see balrogai.com).

💯 Who knew that the International Math Olympiad (IMO) is much easier than The NetHack Learning Environment for AI.

1 43.6 Grok-4-Wiz-AI-Cha died in The Dungeons of Doom on level 1. Killed by a housecat.