论文标题
Neurips 2021 Nethack Challenge的见解
Insights From the NeurIPS 2021 NetHack Challenge
论文作者
论文摘要
在本报告中，我们总结了第一个Neurips 2021 Nethack Challenge的收获。参与者的任务是开发一个可以赢得（即“上升”）的计划或代理商，通过与Nethack学习环境（NLE）互动（NLE），这是一种受欢迎的Nethack的Dungeon-Crawler游戏，这是一种可扩展的，程序性生成的，并且具有挑战性的健身房环境，以增强增强学习（RL）。挑战表明，以多种多样的方法在AI中以社区为导向的进步极大地超过了Nethack的最佳成绩。此外，它是神经（例如深RL）和符号AI以及混合系统之间的直接比较，表明在Nethack符号机器人上，当前的符号机器人当前的表现优于深度RL。最后，没有代理人接近赢得比赛，这说明了Nethack作为AI研究的长期基准的适用性。
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.
