Hambro, E;
Mohanty, S;
Babaev, D;
Byeon, M;
Chakraborty, D;
Grefenstette, E;
Jiang, M;
... Sypetkowski, M; + view all
(2022)
Insights from the NeurIPS 2021 NetHack Challenge.
In:
Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track.
(pp. pp. 41-52).
Proceedings of Machine Learning Research (PMLR)
Preview |
Text
hambro22a.pdf - Published Version Download (2MB) | Preview |
Abstract
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.
| Type: | Proceedings paper |
|---|---|
| Title: | Insights from the NeurIPS 2021 NetHack Challenge |
| Event: | NeurIPS 2021 Competitions and Demonstrations Track |
| Open access status: | An open access version is available from UCL Discovery |
| Publisher version: | https://proceedings.mlr.press/v176/hambro22a.html |
| Language: | English |
| Additional information: | This version is the version of record. For information on re-use, please refer to the publisher’s terms and conditions. |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10177325 |
Archive Staff Only
 |
View Item |
