AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Generalization of Reinforcement Learners with Working and Episodic Memory

Meire Fortunato, Melissa Tan, Ryan Faulkner, Steven Hansen, Adrià Puigdomènech Badia, Gavin Buttimore, Charles Deck, Joel Z. Leibo, Charles Blundell

NeurIPS 2019 · Reinforcement learning › Visual and representation RL · approach: Curriculum and environment design · 25 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 episodic memory (MEM) + CPC to LSTM (ablation)LSTM (IMPALA) · Memory Task Suite avg, Holdout-Extrapolatehuman-normalized score: 35.6 -> 52.6Improved
add MEM to LSTM (ablation)LSTM · Memory Task Suite avg, Holdout-Interpolatehuman-normalized score: 40.2 -> 50.0Improved
add CPC to LSTM + MEM (ablation)LSTM + MEM · Memory Task Suite avg, Trainhuman-normalized score: 78.7 -> 92.9Improved
add MEM to FF controller (ablation)FF · Memory Task Suite avg, Trainhuman-normalized score: 33.9 -> 42.3Improved
add MEM + CPC to FF controller (ablation)FF · Memory Task Suite avg, Trainhuman-normalized score: 33.9 -> 62.6Improved
replace CPC with reconstruction loss (REC) (ablation)LSTM + MEM · Memory Task Suite avg, Trainhuman-normalized score: 92.9 -> 82.2Hurt
remove jumpy backpropagation from MRA (ablation)MRA · Memory Suite taskstask performanceMixed
add MEM alone to FF controller (ablation)FF · Change Detection Trainepisode reward: 26.40 -> 25.76No clear effect
add MEM alone to FF controller (ablation)FF · Continuous Recognition Trainepisode reward: 26.90 -> 26.51No clear effect
add CPC to FF + MEM (ablation)FF + MEM · Continuous Recognition Trainepisode reward: 26.51 -> 49.60Improved
add CPC to FF + MEM (ablation)FF + MEM · Change Detection Trainepisode reward: 25.76 -> 44.76Improved
use REC instead of CPC with FF + MEM (ablation)FF + MEM · Change Detection Trainepisode reward: 44.76 -> 25.82Hurt

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