Tag: Proximal Policy Optimization
Browse our exclusive articles!
Discrete Flow Matching Policy Optimization for RL Models
Discover DoMinO, a novel RL framework optimizing discrete flow matching with robust policy gradients and improved sequence generation.
T-STAR: Tree-Based Policy Optimization for Multi-Turn Agents
Discover T-STAR, a novel tree-structured framework enhancing multi-turn agent policy optimization through self-rectification and grafting techniques.
Region-R1: Advanced Query-Side Cropping for Multi-Modal Ranking
Discover how Region-R1 improves multi-modal re-ranking by dynamically cropping query regions, boosting retrieval accuracy on E-VQA and InfoSeek benchmarks.
MC-CPO: Safe Policy Optimization for Adaptive Tutoring
Discover MC-CPO, a mastery-conditioned constrained policy optimization method that enhances safe and effective adaptive tutoring with reduced reward hackin...
LLM Challenges in Adaptive Reward Satellite Scheduling
Explore the switching-stability dilemma in LLM-guided LEO satellite scheduling and how adaptive rewards impact deep reinforcement learning performance.