Recurrent Structural Policy Gradient: A Method for Partially Observable Mean Field Games

Optimistic Thompson Sampling for No-Regret Learning in Unknown Games

Distributed Online Stochastic Convex-Concave Optimization: Dynamic Regret Analyses Under Single and Multiple Consensus Steps

MMR-GRPO: Diversity-Aware Reward Reweighting Accelerates Mathematical Reasoning Model Training

This paper introduces MMR-GRPO, a method that integrates Maximal Marginal Relevance (MMR) into Group Relative Policy Optimization (GRPO) to

Understanding Reinforcement Learning for Model Training, and future directions with GRAPE

ConSPO: A Contrastive Approach to Improving Reinforcement Learning with Verifiable Rewards for LLMs

This paper analyzes Group Relative Policy Optimization (GRPO), a widely used RLVR algorithm for post-training large language models on reaso

Supervised Fine-Tuning as Reinforcement Learning: Introducing Importance-Weighted SFT

The article explores the connection between supervised fine-tuning (SFT) of large language models and reinforcement learning (RL), arguing t