AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

NovelD: A Simple yet Effective Exploration Criterion

Tianjun Zhang, Huazhe Xu, Xiaolong Wang, Yi Wu, Kurt Keutzer, Joseph E. Gonzalez, Yuandong Tian

NeurIPS 2021 · Reinforcement learning › Visual and representation RL · approach: Novelty and impact-driven exploration · 19 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
use NovelD (novelty difference) instead of RND as intrinsic rewardPPO agent · MiniGrid hard exploration (MR, KC, OM)task successImproved
use NovelD instead of RNDPPO agent · Montezuma's Revenge CNNextrinsic reward: 6700 -> 10000Improved
use NovelD instead of RNDPPO agent · Montezuma's Revenge RNNextrinsic reward: 4400 -> 13000Improved
use NovelD instead of RNDPPO agent · NetHack tasksrewardImproved
use NovelD instead of RND for state coverageintrinsic reward · Toy corridorvisitation entropy: 0.24 -> 1.96Improved
add episodic restriction on intrinsic reward (ERIR) to NovelD (ablation)NovelD · MiniGridperformanceImproved
add ERIR to RND (RND+ERIR) (ablation)RND · MiniGridperformanceImproved
set scaling alpha=0.5 and clipping beta=0 vs other values (ablation)NovelD · MiniGridperformanceImproved
replace random embedding with ICM or DBC representation (ablation)NovelD · MiniGridrewardHurt
replace random embedding with successor representation (ablation)NovelD · MiniGrid KC and MR mapsrewardMixed

Later papers that compared with this method

3 later accepted papers report NovelD as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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