How I Study AI - Learn AI Papers & Lectures the Easy Way

E-GRPO: High Entropy Steps Drive Effective Reinforcement Learning for Flow Models

Intermediate

Shengjun Zhang, Zhang Zhang et al.Jan 1arXiv

This paper shows that when teaching image generators with reinforcement learning, only a few early, very noisy steps actually help the model learn what people like.

#E-GRPO#Group Relative Policy Optimization#Flow Matching

Differentiable Evolutionary Reinforcement Learning

Intermediate

Sitao Cheng, Tianle Li et al.Dec 15arXiv

This paper introduces DERL, a two-level learning system that automatically builds better reward functions for reinforcement learning agents.

#Differentiable Evolutionary Reinforcement Learning#Meta-Optimizer#Meta-Reward

SPARK: Stepwise Process-Aware Rewards for Reference-Free Reinforcement Learning

Intermediate

Salman Rahman, Sruthi Gorantla et al.Dec 2arXiv

SPARK teaches AI to grade its own steps without needing the right answers written down anywhere.

#SPARK#Process Reward Model#PRM-CoT

Papers3

E-GRPO: High Entropy Steps Drive Effective Reinforcement Learning for Flow Models

Differentiable Evolutionary Reinforcement Learning

SPARK: Stepwise Process-Aware Rewards for Reference-Free Reinforcement Learning