ru
ru
Source
DATE OF PUBLICATION
03/22/2022
Authors
Dmitrii Babaev Nikita Ovsov Ivan Nazarov Minwoo Byeon Dipam Chakraborty Edward Grefenstette Minqi Jiang Daejin Jo Anssi Kanervisto Jongmin Kim Sungwoong Kim Robert Kirk Vitaly Kurin Heinrich K Taehwon Kwon Donghoon Lee Vegard Mella Nantas Nardelli Jack Parker-Holder Roberta Raileanu Karolis Ramanauskas Tim Rockt Danielle Rothermel Mikayel Samvelyan Maciej Sypetkowski Micha l Sypetkowski Eric Hambro Sharada Mohanty Dmitry Sorokin
Share

Insights from the NeurIPS 2021 NetHack Challenge

Reinforcement Learning, Open-ended Learning, Generalization, Procgen, GameAI, NetHack

Abstract

In  this  report,  we  summarize  the  takeaways  from  the  first  NeurIPS  2021  NetHackChallenge.   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 theNetHack Learning Environment (NLE), a scalable, procedurally generated, and challengingGymenvironment for reinforcement learning (RL). The challenge showcased community-driven progress in AI with many diverse approaches significantly beating the previously bestresults 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  NetHacksymbolic bots currently outperform deep RL by a large margin.  Lastly, no agent got closeto winning the game, illustrating NetHack’s suitability as a long-term benchmark for AIresearch

Full text

Similar publications

NAACL
Biomedical Entity Representation with Graph-Augmented Multi-Objective Transformer
Artur Kadurin, Elena Tutubalina
SOURCE
ECIR
BioASQ at CLEF2024: The Twelfth Edition of the Large-Scale Biomedical Semantic Indexing and Question Answering Challeng
Anastasios Nentidis, Anastasia Krithara, Georgios Paliouras, Martin Krallinger, Luis Gasco Sánchez, Salvador Lima, Eulalia Farre, , Natalia Loukachevitch, Vera Davydova, Elena Tutubalina
SOURCE
AAAI
Beyond Attention: Breaking the Limits of Transformer Context Length with Recurrent Memory
Aydar Bulatov, Yuri Kuratov, Yermek Kapushev, Mikhail Burtsev
SOURCE
Scientific Reports
Forest age estimation in northern Arkhangelsk region based on machine learning pipeline on Sentinel-2 and auxiliary data
Alina Smolina, Svetlana Illarionova, Dmitrii Shadrin, Alexander Kedrov, Evgeny Burnaev
SOURCE
EMNLP
LM-Polygraph: Uncertainty Estimation for Language Models
Ekaterina Fadeeva, Roman Vashurin, Akim Tsvigun, Artem Vazhentsev, Sergey Petrakov, Kirill Fedyanin, Daniil Vasilev, Elizaveta Goncharova, Alexander Panchenko, Maxim Panov, Timothy Baldwin, Artem Shelmanov
SOURCE
EMNLP
Better Together: Enhancing Generative Knowledge Graph Completion with Language Models and Neighborhood Information.
Alla Chepurova, Aydar Bulatov, Yuri Kuratov, Mikhail Burtsev
SOURCE
ICCV
RheumaVIT: transformer-based model for Automated Scoring of Hand Joints in Rheumatoid Arthritis
Alexander Stolpovsky, Elizaveta Dakhova, Polina Druzhinina, Polina Postnikova, Daniil Kudinsky, Alexander Smirnov, Anastasia Sukhinina, Alexander Lila, Anvar Kurmukov
SOURCE
Contact us
Join AIRI
You can ask us a question or suggest a joint project in the field of AI

Message sent.

Thank you!

Something went wrong. Try again