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

ACL
Prompt Me One More Time: A Two-Step Knowledge Extraction Pipeline with Ontology-Based Verification, Workshop TextGraphs-17: Graph-based Methods for Natural Language Processing
Alla Chepurova, Yuri Kuratov, Aydar Bulatov, Mikhail Burtsev
SOURCE
Biomedical Signal Processing and Control
Negligible effect of brain MRI data preprocessing for tumor segmentation
Ekaterina Kondratyeva , Polina Druzhinina, Alexandra Dalechina, Svetlana Zolotova, Andrey Golanov, Boris Shirokikh, Mikhail Belyaev, Anvar Kurmukov
SOURCE
User Modeling and User-Adapted Interaction
Federated privacy-preserving collaborative filtering for on-device next app prediction
Albert Sayapin, Gleb Balitskiy, Daniel Bershatsky, Aleksandr Katrutsa, Evgeny Frolov, Alexey Frolov, Ivan Oseledets, Vitaliy Kharin
SOURCE
CVPR
Weak-to-Strong 3D Object Detection with X-Ray Distillation
Alexander Gambashidze , Aleksandr Dadukin, Maksim Golyadkin, Maria Razzhivina, Ilya Makarov
SOURCE
ECIR
BioASQ at CLEF2024: The Twelfth Edition of the Large-Scale Biomedical Semantic Indexing and Question Answering Challenge
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
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