AI Paper Atlas

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

An Efficient Asynchronous Method for Integrating Evolutionary and Gradient-based Policy Search

Kyunghyun Lee, Byeong-Uk Lee, Ukcheol Shin, In So Kweon

NeurIPS 2020 · Reinforcement learning › Policy gradient and actor-critic · approach: Alternative policy update rules · 6 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
replace synchronous CEM-RL with AES-RLCEM-RL · HalfCheetah-v2mean score: 10725 -> 12550Improved
replace synchronous CEM-RL with AES-RLCEM-RL · Hopper-v2mean score: 3613 -> 3751Improved
replace synchronous CEM-RL with AES-RLCEM-RL · Walker2D-v2mean score: 4711 -> 5474Improved
replace synchronous CEM-RL with AES-RLCEM-RL · Ant-v2mean score: 4251 -> 5120; SAC 5985Mixed
replace synchronous CEM-RL with AES-RLCEM-RL · Swimmer-v2mean score: 75 -> 161Improved
replace synchronous CEM-RL with AES-RLCEM-RL · Humanoid-v2mean score: 5579 -> 6136Improved
use five-worker parallel asynchronous execution instead of serial synchronous executionCEM-RL · HalfCheetah-v2training time: 467 -> 83 minImproved
use five-worker parallel asynchronous execution instead of serial synchronous executionCEM-RL · Walker2d-v2training time: 487 -> 105 minImproved
use five-worker parallel asynchronous execution instead of serial synchronous executionCEM-RL · Hopper-v2training time: 505 -> 133 minImproved
add asynchronous updates without the proposed mean and variance update rules (ablation)CEM-RL · HalfCheetah-v2mean score: 10725 -> 10010Hurt
add asynchronous updates without the proposed mean and variance update rules (ablation)CEM-RL · Walker2D-v2mean score: 4711 -> 4230Hurt
use the proposed variance update instead of fixing variance at 0.0001 (ablation)AES-RL · HalfCheetah-v2mean score: 11636 -> 12550Improved

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