AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

RIDE: Rewarding Impact-Driven Exploration for Procedurally-Generated Environments

Roberta Raileanu, Tim Rocktäschel

ICLR 2020 · Reinforcement learning › Visual and representation RL · approach: Novelty and impact-driven exploration · 31 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 impact-driven intrinsic reward with episodic state-count discountingIMPALA on procedurally generated MiniGrid · MiniGrid hard exploration taskssample efficiency and task successImproved
Use impact-driven reward rather than prediction-error curiosityRIDE versus ICM · Mario, first levellearning performanceImproved
Use RIDE explorationIMPALA on VizDoom · VizDoomtask performanceImproved
Use impact-driven reward with episodic state-count discounting (ablation)RIDE · MiniGrid hard exploration taskstask successImproved
Add impact-driven reward to episodic state counts (ablation)OnlyEpisodicCounts · MiniGrid hard exploration taskstask successImproved
Retain entropy regularization (ablation)NoEpisodicCounts RIDE variant · MiniGrid hard exploration taskstask successImproved
Use learned state embeddings instead of raw observations to compute impact (ablation)RIDE · MiniGrid taskstask successImproved
Keep policy and impact embedding representations separate (ablation)RIDE · MiniGrid taskstask successImproved
Add a noisy, randomly recoloring TV distractorICM · MiniGridN7S4NoisyTVtask performanceHurt
Train with intrinsic and extrinsic rewardsICM · Mario, first levellearning performanceHurt

Later papers that compared with this method

5 later accepted papers report RIDE as a baseline in their results tables; 4 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