Insights From the NeurIPS 2021 NetHack Challenge

03/22/2022

∙

by   Eric Hambro, et al.

∙

University of Eastern Finland

∙

University of Oxford

∙

Facebook

∙

Kakao Corp.

∙

Sberbank

∙

UCL

∙

9

∙

share

In this report, we summarize the takeaways from the first NeurIPS 2021 NetHack Challenge. Participants were tasked with developing a program or agent that can win (i.e., 'ascend' in) the popular dungeon-crawler game of NetHack by interacting with the NetHack Learning Environment (NLE), a scalable, procedurally generated, and challenging Gym environment for reinforcement learning (RL). The challenge showcased community-driven progress in AI with many diverse approaches significantly beating the previously best results on NetHack. Furthermore, it served as a direct comparison between neural (e.g., deep RL) and symbolic AI, as well as hybrid systems, demonstrating that on NetHack symbolic bots currently outperform deep RL by a large margin. Lastly, no agent got close to winning the game, illustrating NetHack's suitability as a long-term benchmark for AI research.