AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Pearl: A Production-Ready Reinforcement Learning Agent

Zheqing Zhu, Rodrigo de Salvo Braz, Jalaj Bhandari, Daniel Jiang, Yi Wan, Yonathan Efroni, Liyuan Wang, Ruiyang Xu, Hongbo Guo, Alex Nikulkov, Dmytro Korenkevych, Urun Dogan and 3 more

JMLR 2024 · Reinforcement learning › Visual and representation RL · approach: Probabilistic and autonomous RL · 7 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
use Pearl's modular implementation instead of CleanRL's single-file implementationSAC · HalfCheetah-v4 (10,000 steps)training time: 123 -> 145 secondsHurt
allocate replay buffer dynamically (Pearl) instead of pre-filling with zeros (CleanRL)SAC · HalfCheetah-v4 (10,000 steps)memory (GB): 4.2 -> 1.0 GBImproved
Pearl replay buffer stores extra attributes (available actions, costs) versus CleanRLSAC · HalfCheetah-v4 (full replay buffer)memory (GB): 4.4 -> 5.7 GBHurt

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