AI Paper Atlas

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

Noisy Derivative-Free Optimization With Value Suppression

Hong Wang, Hong Qian, Yang Yu

AAAI 2018 · Reinforcement learning › Policy gradient and actor-critic · approach: Tree search and policy optimization · 12 citations (OpenAlex)

Read the paper

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 value suppression to SRACOS (VS vs MPS baseline)SRACOS · Ackley n=100 sigma=0.1true function value (lower better): 2.95 -> 0.93Improved
add value suppression to SRACOS (VS vs MPS baseline)SRACOS · Sphere n=1000 sigma=1true function value (lower better): 97.16 -> 72.41Improved
add value suppression to SRACOS with single positive solution (VS+NO MPS vs NO MPS) (ablation)SRACOS · Sphere n=100 sigma=1true function value (lower better): 15.41 -> 7.41Improved
use multiple positive solutions (MPS) instead of one (ablation)SRACOS · Ackley n=100 sigma=0.1true function value (lower better): 3.69 -> 2.95Improved
add re-evaluation, threshold selection, or both to SRACOSSRACOS · Sphere n=100 sigma=1true function value (lower better): 15.41 (NO MPS) -> 24.07 (REEVAL), 24.88 (TS), 20.65 (REEVAL+TS)Hurt
add sampling (10 samples) to SRACOSSRACOS · Sphere n=100 sigma=1true function value (lower better): 15.41 -> 6.53Improved
value suppression vs MPS baseline on OpenAI GymSRACOS · HalfCheetah-v1accumulated reward: 1388.27 -> 1924.60Improved
value suppression vs MPS baseline on OpenAI GymSRACOS · LunarLander-v2accumulated reward: -187.70 -> 80.40Improved
add extra Gaussian noise (1x noise level)VS · HalfCheetah-v1accumulated reward: 1924.60 -> 1286.29Hurt
change max non-update iterations u from 500 to 100 or 1000 (ablation)VS · OpenAI Gym tasksaccumulated reward: HalfCheetah-v1 1924.60 (u=500) -> 1554.27 (u=100), 1773.89 (u=1000)No 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