AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Optimizing Memory Placement using Evolutionary Graph Reinforcement Learning

Shauharda Khadka, Estelle Aflalo, Mattias Marder, Avrech Ben-David, Santiago Miret, Shie Mannor, Tamir Hazan, Hanlin Tang, Somdeb Majumdar

ICLR 2021 · Reinforcement learning › Visual and representation RL · approach: RL for combinatorial routing · 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
Combine evolutionary search and policy-gradient learning with shared replay and policy migrationEGRL memory mapping · ResNet-50speedup: 1.28 vs 1.06 (EA), 0.72 (Greedy-DP), and 0.29 (PG)Improved
Combine evolutionary search and policy-gradient learning with shared replay and policy migrationEGRL memory mapping · ResNet-101speedup: 1.78 vs 1.47 (EA), 1.27 (Greedy-DP), and 0.23 (PG)Improved
Combine evolutionary search and policy-gradient learning with shared replay and policy migrationEGRL memory mapping · BERTspeedup: 1.66 vs 1.64 (EA), 0.67 (Greedy-DP), and 0.21 (PG)Improved
Remove evolutionary search and use policy-gradient learning alone (ablation)EGRL · ResNet-50speedup: 1.28 -> 0.29Hurt
Remove evolutionary search and use policy-gradient learning alone (ablation)EGRL · ResNet-101speedup: 1.78 -> 0.23Hurt
Remove evolutionary search and use policy-gradient learning alone (ablation)EGRL · BERTspeedup: 1.66 -> 0.21Hurt
Remove policy-gradient learning and use evolutionary search alone (ablation)EGRL · ResNet-50speedup: 1.28 -> 1.06Hurt
Remove policy-gradient learning and use evolutionary search alone (ablation)EGRL · ResNet-101speedup: 1.78 -> 1.47Hurt
Remove policy-gradient learning and use evolutionary search alone (ablation)EGRL · BERTspeedup: 1.66 vs 1.64No clear effect
Use layer-wise greedy decisions with a conditional-independence assumptionGreedy-DP memory mapping · BERTspeedup: 0.67Hurt

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