AI Paper Atlas

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

ProRL: Effective Reinforcement Learning for Proactive Recommendation via Rectified Policy Gradient Estimation

Hongru Hou, Tiehua Mei, Denghui Geng, Jinhui Huang, Ao Xu, Hengrui Chen, Jiaqing Liang, Deqing Yang

ICML 2026 · Reinforcement learning › Policy gradient and actor-critic · approach: Policy gradients for special settings · 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
add Stepwise Reward Centering (ablation)ProRL · MovieLens-1MIoI: 1.2373 -> 2.8504Improved
add Stepwise Reward Centering (ablation)ProRL · MovieLens-1MCTR: 0.9731 -> 0.8543Hurt
add Stepwise Reward Centering (ablation)ProRL · SteamIoR: 198.30 -> 340.18Improved
add Position-Specific Advantage Estimation (ablation)ProRL · MovieLens-1MIoI: 2.5556 -> 2.8504Improved
add Position-Specific Advantage Estimation (ablation)ProRL · SteamIoI: 0.7280 -> 1.1188Improved
add Position-Specific Advantage Estimation (ablation)ProRL · Amazon-BookIoR: 1223.78 -> 1383.41Improved
add IoR reward term (ablation)ProRL · Amazon-BookIoR: 125.94 -> 1383.41Improved
add IoI reward term (ablation)ProRL · SteamIoI: 0.2856 -> 1.1188Improved
add CTR reward term (ablation)ProRL · MovieLens-1MCTR: 0.7722 -> 0.8543Improved
use position-specific advantage instead of REINFORCE (ablation)policy gradient · MovieLens-1MIoI: 1.626 -> 2.850Improved
use position-specific advantage instead of GRPO (ablation)policy gradient · MovieLens-1MIoI: 1.483 -> 2.850Improved
use analytic position-specific baseline instead of learned critic A2C (ablation)policy gradient · MovieLens-1MIoR: 527.5 -> 728.2Improved

Later papers that compared with this method

1 later accepted paper reports ProRL as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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