GRPO
Group Relative Policy Optimization (GRPO) is a reinforcement learning algorithm for fine-tuning large language models that eliminates the separate critic (value) network used by PPO
Reasoning Models
Explore Reasoning Models through related topics and the articles other pages reference most.
Explore articles
Browse subtopics: Reinforcement Learning
Articles that also belong to these categories. Counts cover all of Reasoning Models.
All articles (70)Large Language Models (39)AI Models (18)Chinese AI (14)AI Benchmarks (13)OpenAI (12)Open Source AI (11)Artificial Intelligence (9)Google DeepMind (5)AI Agents (4)AI Inference (4)Anthropic (4)Model Evaluation (4)Machine Learning (3)Multimodal AI (3)NVIDIA (3)Natural Language Processing (3)Prompt Engineering (3)Training & Optimization (3)AI Companies (2)AI Research (2)AI for Science (2)Generative AI (2)Mixture of Experts (2)Reinforcement Learning (2)AI History (1)AI Tools & Products (1)Data Science (1)Mathematics (1)Meta AI (1)Microsoft (1)Research Organizations (1)Small Language Models (1)
Showing 1-2 of 2 articles
RLVR
Reinforcement Learning with Verifiable Rewards (RLVR) is a post-training paradigm for large language models in which the reward signal comes from a deterministic