AI Paper Atlas

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

The Choice Function Framework for Online Policy Improvement

Murugeswari Issakkimuthu, Alan Fern, Prasad Tadepalli

AAAI 2020 · Reinforcement learning › Policy gradient and actor-critic · approach: Tree search and policy optimization · 0 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
apply best LDCF online search on top of linear base policyPolicy 1 (linear) · Game-of-Life problem 1normalized reward: 2.57Improved
apply best LDCF online search on top of linear base policyPolicy 1 (linear) · Game-of-Life problem 10normalized reward: 2.11Improved
apply best LDCF online search on top of linear base policyPolicy 1 (linear) · Game-of-Life problem 6normalized reward: 1.05Improved
apply best LDCF online search on top of non-linear base policyPolicy 2 (3 hidden layers) · Game-of-Life problem 10normalized reward: 1.23Improved
apply best LDCF online search on top of non-linear base policyPolicy 2 (3 hidden layers) · Game-of-Life problems 2, 3, 6, 9normalized reward: 0.95Hurt
apply best LDCF online search on top of non-linear base policyPolicy 2 (3 hidden layers) · Game-of-Life problem 5normalized reward: 1.00No clear effect
use stronger base policy (non-linear instead of linear)LDCF online search · Game-of-Life problem 1normalized reward gain: 2.57 -> 1.08Hurt
allow longer decision time per stepLDCF configurations · Game-of-Lifenormalized rewardMixed
small FSSS sampling width C=3 on highly stochastic problemsLDCF with FSSS · Game-of-Life stochastic problemsnormalized rewardHurt

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