SOTAVerified

NetHack

Mean in-game score over 1000 episodes with random seeds not seen during training. See https://arxiv.org/abs/2006.13760 (Section 2.4 Evaluation Protocol) for details.

Papers

Showing 1120 of 28 papers

TitleStatusHype
LuckyMera: a Modular AI Framework for Building Hybrid NetHack AgentsCode1
Katakomba: Tools and Benchmarks for Data-Driven NetHackCode1
Hierarchical Kickstarting for Skill Transfer in Reinforcement LearningCode1
NovelD: A Simple yet Effective Exploration CriterionCode1
SILG: The Multi-environment Symbolic Interactive Language Grounding BenchmarkCode1
CORA: Benchmarks, Baselines, and Metrics as a Platform for Continual Reinforcement Learning AgentsCode1
BeBold: Exploration Beyond the Boundary of Explored RegionsCode1
The NetHack Learning EnvironmentCode1
MaestroMotif: Skill Design from Artificial Intelligence Feedback0
BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games0
Show:102550
← PrevPage 2 of 3Next →

No leaderboard results yet.