AI Paper Atlas

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

ResAct: Reinforcing Long-term Engagement in Sequential Recommendation with Residual Actor

Wanqi Xue, Qingpeng Cai, Ruohan Zhan, Dong Zheng, Peng Jiang, Kun Gai, Bo An

ICLR 2023 · Reinforcement learning › Policy gradient and actor-critic · approach: Regularized scalable deep value learning

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 a residual actor to improve reconstructed online-policy actionsimitation learning policy · RecL-25m Return TimeNCIS: 0.6404 -> 0.7980Improved
add a residual actor to improve reconstructed online-policy actionsimitation learning policy · RecL-25m Session LengthNCIS: 0.3186 -> 0.5433Improved
add a residual actor to improve reconstructed online-policy actionsimitation learning policy · RecL-25m BothNCIS: 0.5345 -> 0.6675Improved
use CVAE reconstruction instead of a deterministic behavior reconstructor (ablation)ResAct · RecL-25mNCISImproved
increase the number of online-behavior estimators (ablation)ResAct · RecL-25m Return Time, Session Length, and BothNCISImproved
use behavior-like CVAE candidates instead of adding 20 uniform candidates (ablation)ResAct · RecL-25m Return TimeNCIS: 0.5501 -> 0.7980Improved
use behavior-like CVAE candidates instead of adding 20 uniform candidates (ablation)ResAct · RecL-25m Session LengthNCIS: 0.3489 -> 0.5433Improved
use behavior-like CVAE candidates instead of adding 20 uniform candidates (ablation)ResAct · RecL-25m BothNCIS: 0.4839 -> 0.6675Improved
add the expressiveness regularizer (ablation)ResAct · RecL-25m Return TimeNCIS: 0.6610 -> 0.7980Improved
add the expressiveness regularizer (ablation)ResAct · RecL-25m Session LengthNCIS: 0.3895 -> 0.5433Improved
add the expressiveness regularizer (ablation)ResAct · RecL-25m BothNCIS: 0.6074 -> 0.6675Improved
add the conciseness regularizer (ablation)ResAct · RecL-25m Return TimeNCIS: 0.6944 -> 0.7980Improved

Later papers that compared with this method

2 later accepted papers report Resact as a baseline in their results tables; 2 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