DeepAI AI Chat
Log In Sign Up

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

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.

READ FULL TEXT

page 10

page 19

06/24/2020

The NetHack Learning Environment

Progress in Reinforcement Learning (RL) algorithms goes hand-in-hand wit...
02/11/2019

The StarCraft Multi-Agent Challenge

In the last few years, deep multi-agent reinforcement learning (RL) has ...
12/12/2019

The PlayStation Reinforcement Learning Environment (PSXLE)

We propose a new benchmark environment for evaluating Reinforcement Lear...
09/11/2020

Physically Embedded Planning Problems: New Challenges for Reinforcement Learning

Recent work in deep reinforcement learning (RL) has produced algorithms ...
05/03/2021

Robotic Surgery With Lean Reinforcement Learning

As surgical robots become more common, automating away some of the burde...
07/26/2021

Playtesting: What is Beyond Personas

Playtesting is an essential step in the game design process. Game design...
08/17/2020

Playing Catan with Cross-dimensional Neural Network

Catan is a strategic board game having interesting properties, including...