ProRL: Effective Reinforcement Learning for Proactive Recommendation via Rectified Policy Gradient Estimation
Paper • 2605.28293 • Published • 76
CyLower
CyLower
AI & ML interests
None yet
Recent Activity
upvoted a paper about 14 hours ago
ProRL: Effective Reinforcement Learning for Proactive Recommendation via Rectified Policy Gradient EstimationOrganizations
None yet
upvoted a paper about 14 hours ago