mlsanityData to 7 Oct 2026

Insights From the NeurIPS 2021 NetHack Challenge

arXiv 2203.11889 ↗First posted 22 Mar 2022cs.LG cs.AI cs.NEcited by 20

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Builds on 7 of its 16 references that are in the map. First posted on arXiv 22 Mar 2022.

Builds on

7 of 16 references.

References · 7

  1. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,303
  2. 2018IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architecturescited by 866
  3. 2019Stabilizing Transformers for Reinforcement Learningcited by 262
  4. 2020The NetHack Learning Environmentcited by 196
  5. 2021MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Researchcited by 96
  6. 2020Sample Factory: Egocentric 3D Control from Pixels at 100000 FPS with Asynchronous Reinforcement Learningcited by 84
  7. 2019TorchBeast: A PyTorch Platform for Distributed RLcited by 41

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 8; 2024: 7; 2025: 1; 2026: 1.

20 papers.

Sort:

By area:

  1. 2024BALROG: Benchmarking Agentic LLM and VLM Reasoning On Gamescited by 141
  2. 2023Motif: Intrinsic Motivation from Artificial Intelligence Feedbackcited by 99
  3. 2024Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learningcited by 80
  4. 2022Deep Surrogate Assisted Generation of Environmentscited by 40
  5. 2025RefactorBench: Evaluating Stateful Reasoning in Language Agents Through Codecited by 28
  6. 2024MaestroMotif: Skill Design from Artificial Intelligence Feedbackcited by 24
  7. 2024Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problemcited by 23
  8. 2024Playing NetHack with LLMs: Potential & Limitations as Zero-Shot Agentscited by 17
  9. 2022Dungeons and Data: A Large-Scale NetHack Datasetcited by 16
  10. 2023NetHack is Hard to Hackcited by 11
  11. 2023Scaling Laws for Imitation Learning in Single-Agent Gamescited by 11
  12. 2023Accelerating exploration and representation learning with offline pre-trainingcited by 7
8 more
  1. 2023diff History for Neural Language Agentscited by 6
  2. 2023Katakomba: Tools and Benchmarks for Data-Driven NetHackcited by 5
  3. 2022GriddlyJS: A Web IDE for Reinforcement Learningcited by 4
  4. 2024Syllabus: Portable Curricula for Reinforcement Learning Agentscited by 2
  5. 2024Probing for Consciousness in Machinescited by 1
  6. 2023LuckyMera: a Modular AI Framework for Building Hybrid NetHack Agentscited by 0
  7. 2023Benchmarking Robustness and Generalization in Multi-Agent Systems: A Case Study on Neural MMOcited by 0
  8. 2026Hierarchical Behaviour Spacescited by 0