AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Exploration via Elliptical Episodic Bonuses

Mikael Henaff, Roberta Raileanu, Minqi Jiang, Tim Rocktäschel

NeurIPS 2022 · Reinforcement learning › Visual and representation RL · approach: Novelty and impact-driven exploration

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 rank-1 inverse covariance updates instead of full matrix inversion (ablation)E3B · MiniHack-Freeze-Random-Restricted-v0FPS: 256 FPS -> 767 FPSImproved
replace the learned inverse-dynamics encoder with a random fixed encoder (ablation)E3B · MiniHack (16 tasks)aggregate performanceHurt
tie the feature encoder to the policy network (ablation)E3B · MiniHack (16 tasks)aggregate performanceHurt
compute the elliptical bonus across the agent's whole lifetime (non-episodic) (ablation)E3B · MiniHack (16 tasks)aggregate performanceHurt
use the full state for the count-based episodic bonus (original NovelD) (ablation)NovelD · MiniHack (16 tasks)aggregate performanceHurt
restrict NovelD count bonus to agent (x,y) position (ablation)NovelD-position · MiniHack navigation tasksaggregate performanceImproved
restrict NovelD count bonus to agent (x,y) position (ablation)NovelD-position · MiniHack skill-based tasksaggregate performanceHurt
restrict NovelD count bonus to message only (ablation)NovelD-message · MiniHack skill-based tasksaggregate performanceImproved
restrict NovelD count bonus to message only (ablation)NovelD-message · MiniHack navigation tasksaggregate performanceHurt
use E3B on raw full state instead of NovelD variants with hand-chosen features (ablation)E3B · MiniHack (16 tasks)aggregate performanceImproved
remove the count-based episodic term (ablation)RIDE, AGAC, NovelD · additional MiniGrid environmentsreturnHurt
restrict the 78-action space to task-relevant actions (ablation)all methods · MiniHack skill-based taskstask success: 78 actions -> restrictedImproved

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