AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

The NetHack Learning Environment

Heinrich Küttler, Nantas Nardelli, Alexander Miller, Roberta Raileanu, Marco Selvatici, Edward Grefenstette, Tim Rocktäschel

NeurIPS 2020 · Reinforcement learning › Visual and representation RL · approach: Scalable RL systems and environments · 44 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add RND explorationIMPALA CNN · Staircase, monksuccess rate: +13.58ppImproved
add RND explorationIMPALA CNN · Staircase, touristsuccess rate: +6.52ppImproved
add RND explorationIMPALA CNN · Staircase, valkyriesuccess rate: +16.34ppImproved
add RND explorationIMPALA CNN · Staircase, wizardsuccess rate: -12.96ppHurt
add RND explorationIMPALA CNN · Pet tasksuccess rateImproved
add RND explorationIMPALA CNN · Eat taskreturnHurt
add RND explorationIMPALA CNN · Gold, monkaverage dungeon level: 4.2 -> 5.0Improved
add RND explorationIMPALA CNN · Score, monkaverage score: 748 -> 780Improved
use RND intrinsic reward only, without extrinsic reward (ablation)IMPALA CNN with RND · NetHack dungeon progress, fixed seeddungeon progressHurt
replace the symbolic feature extractor with the original RND architecture using a random 8-dimensional symbolic embedding (ablation)IMPALA CNN with RND · NetHack taskstask performanceNo clear effect
use only full-display glyph embeddings or only agent-centered crop embeddings (ablation)IMPALA CNN with RND · NetHack taskstask performanceNo clear effect
train with more environment seedsIMPALA CNN · Score and Staircasetest performanceImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy