AI Paper Atlas

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

Simple random search of static linear policies is competitive for reinforcement learning

Horia Mania, Aurelia Guy, Benjamin Recht

NeurIPS 2018 · Reinforcement learning › Policy gradient and actor-critic · approach: Model-based RL with guarantees · 144 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
add online state normalization (V1 -> V2) (ablation)ARS · Hopper-v1episodes to threshold: 89493 -> 3013Improved
add online state normalization (V1 -> V2) (ablation)ARS · Humanoid-v1episodes to threshold: N/A -> 142600Improved
add online state normalization (V1 -> V2) (ablation)ARS · Walker2d-v1episodes to threshold: 392000 -> 89600Improved
use only top-b directions (V2 -> V2-t) (ablation)ARS · Walker2d-v1episodes to threshold: 89600 -> 24000Improved
use only top-b directions (V2 -> V2-t) (ablation)ARS · Ant-v1episodes to threshold: 60533 -> 20800Improved
use only top-b directions (V2 -> V2-t) (ablation)ARS · Humanoid-v1episodes to threshold: 142600 -> 142600No clear effect
use only top-b directions (V1 -> V1-t) (ablation)ARS · Hopper-v1episodes to threshold: 89493 -> 51840Improved
ARS linear policy instead of TRPO neural policyMuJoCo locomotion · Walker2d-v1episodes to threshold: 14250 -> 24000Hurt
ARS linear policy instead of TRPO neural policyMuJoCo locomotion · HalfCheetah-v1episodes to threshold: 4250 -> 1707Improved
evaluate over 100 random seeds instead of 3ARS · MuJoCo locomotionsuccess rateHurt

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