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 2128 of 28 papers

TitleStatusHype
SILG: The Multi-domain Symbolic Interactive Language Grounding Benchmark0
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
MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning ResearchCode0
BeBold: Exploration Beyond the Boundary of Explored RegionsCode1
The NetHack Learning EnvironmentCode1
Exploration in NetHack With Secret Discovery0
Show:102550
← PrevPage 3 of 3Next →

No leaderboard results yet.