AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Dynamic allocation of limited memory resources in reinforcement learning

Nisheet Patel, Luigi Acerbi, Alexandre Pouget

NeurIPS 2020 · Reinforcement learning › Visual and representation RL · approach: Inferring decision-making from behavior · 2 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
allocate memory precision flexibly (DRA) instead of equal precision for all memories (ablation)DRA · 2D grid-worldobjective: 2× improvementImproved
set lambda to 0 so DRA reduces to SARSA (ablation)DRA · 2D grid-worldepisodes to converge: 1.5×Mixed
allocate memory precision flexibly instead of equal precision (ablation)DRA · Mountain carobjective: 1.3× improvementImproved
set lambda to 0 baseline (ablation)DRA · Mountain carepisodes to converge: 1.3×Mixed
start with more memory resources (lower initial sigma0)DRA · 2D grid-worldlearning speedImproved
use advantage gradient instead of alternative gradients (Eq. 4) (ablation)DRA · Mountain carobjectiveImproved
increase search budget toward 100%DRA vs equal-precision · Planning taskperformance advantage of flexible allocationHurt

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