AI Paper Atlas

Research map / Reinforcement learning / Policy gradient and actor-critic

Experimental design for MRI by greedy policy search

Tim Bakker, Herke van Hoof, Max Welling

NeurIPS 2020 · Reinforcement learning › Policy gradient and actor-critic · approach: Alternative policy update rules

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 greedy one-step reward objective instead of non-greedy (gamma 1.0) (ablation)policy-gradient MRI sampler · Knee long horizonSSIM: 0.7421 -> 0.7442Improved
use greedy objective instead of non-greedy (ablation)policy-gradient MRI sampler · Brain long horizonSSIM: 0.8886 -> 0.8917Improved
use greedy objective instead of non-greedy (ablation)policy-gradient MRI sampler · Knee base horizonSSIM: 0.7223 -> 0.7230Improved
discount rewards with gamma 0.9 instead of 1.0 (ablation)non-greedy policy · Knee long horizonSSIM: 0.7421 -> 0.7449Improved
gamma 0.9 versus greedy (ablation)policy-gradient MRI sampler · Knee base horizonSSIM: 0.7230 -> 0.7232No clear effect
adaptive greedy policy versus non-adaptive oracleGreedy policy · Knee long horizonSSIM: 0.7421 -> 0.7442Improved
non-greedy policy versus non-adaptive oracleNGreedy policy · Brain long horizonSSIM: 0.8909 -> 0.8886Hurt
greedy objective instead of non-greedypolicy gradient · Knee long horizon, epoch 20gradient SNR: 1.04 -> 3.49Improved
longer horizon for non-greedy estimatorNGreedy · Knee epoch 20gradient SNR: 1.24 -> 1.04Hurt
gamma 0.9 instead of 1.0 on long horizon (ablation)non-greedy estimator · Brain long epoch 20gradient SNR: 1.18 -> 7.22Improved
AlphaZero search policy versus NGreedyAlphaZero baseline · Knee base horizonSSIM: 0.7223 -> 0.7203Hurt
larger or smaller policy architecture (ablation)Greedy and NGreedy policies · KneeSSIMNo clear effect

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