AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Multi-Objective Intrinsic Reward Learning for Conversational Recommender Systems

Zhendong Chu, Nan Wang, Hongning Wang

NeurIPS 2023 · Reinforcement learning › Visual and representation RL · approach: Reward shaping for sparse rewards · 2 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 intrinsic-reward fine-tuning (CRSIRL) over policy-gradient pretraining (ablation)CRSIRL · LastFMsuccess rate SR@15: 0.724 -> 0.772Improved
add intrinsic-reward fine-tuning (CRSIRL) over policy-gradient pretraining (ablation)CRSIRL · Yelp*success rate SR@15: 0.598 -> 0.622Improved
add intrinsic-reward fine-tuning (CRSIRL) over policy-gradient pretraining (ablation)CRSIRL · LastFM*hDCG@(15,10): 0.401 -> 0.431Improved
add hindsight reward shaping (HRS) (ablation)CRSIRL · LastFMaverage turns: 10.58 -> 10.12Improved
add hindsight reward shaping (HRS) (ablation)CRSIRL · Yelp*average turns: 11.21 -> 10.61Improved
add recommendation preference matching (RPM) (ablation)CRSIRL · Yelp*hDCG@(15,10): 0.213 -> 0.228Improved
add recommendation preference matching (RPM) (ablation)CRSIRL · LastFMsuccess rate SR@15: 0.754 -> 0.772Improved
use multi-objective optimization instead of equal-weight multi-task learning (ablation)CRSIRL · Yelp*hDCG@(15,10): 0.207 -> 0.228Improved
use multi-objective optimization instead of equal-weight multi-task learning (ablation)CRSIRL · LastFMaverage turns: 10.09 vs 10.12No clear effect
equal-weight multi-task learning over policy gradient only (ablation)PG · LastFMsuccess rate SR@15: 0.724 -> 0.768Improved
intrinsic reward coefficient lambda too smallCRSIRL · LastFMperformanceHurt
intrinsic reward coefficient lambda too largeCRSIRL · LastFMperformanceHurt

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