ProRL: Effective Reinforcement Learning for Proactive Recommendation via Rectified Policy Gradient Estimation
Paper • 2605.28293 • Published • 80
songen gu
gusongen
·
AI & ML interests
None yet
Recent Activity
upvoted a paper 2 months ago
Kinema4D: Kinematic 4D World Modeling for Spatiotemporal Embodied Simulation upvoted a paper 3 months ago
SenCache: Accelerating Diffusion Model Inference via Sensitivity-Aware CachingOrganizations
None yet