VCRL: Variance-based Curriculum Reinforcement Learning for Large Language Models
Policy-based reinforcement learning currently plays an important role in improving LLMs on mathematical reasoning tasks. However, existing rollout-based reinforcement learning methods (GRPO, DAPO, GSPO, etc.) fail to explicitly consider LLMs' learning ability for samples of different difficulty levels, which is contrary to the human cognitive process of mathematical reasoning tasks from easy to difficult. Intuitively, we find that the variance of the rollout group's reward in RLVR partly reflects the difficulty of the current sample for LLMs. Samples that are too easy or too difficult have a lower variance, while samples with moderate difficulty have a higher variance. Based on this, we propose VCRL, a curriculum reinforcement learning framework that dynamically controls the difficulty of training samples based on the variance of group rewards. Experiments on five mathematical benchmarks and two models reveal the advantages of VCRL over the current LLM RL baselines.
Code (0)
등록된 구현이 없습니다.
Tasks
Reinforcement LearningMathematical ReasoningSimilar Papers 제목 키워드 기반
Variational Curriculum Reinforcement Learning for Unsupervised Discovery of Skills
Mutual information-based reinforcement learning (RL) has been proposed as a promising framework for retrieving complex skills autonomously without a task-oriented reward function through mutual information (MI) maximizat…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Robot NavigationCVPO: Enhancing LLM Reinforcement Learning Reasoning via Value-Variance Adaptation and Dynamic Curriculum Learning
Reinforcement learning (RL) has emerged as an effective method for enhancing the reasoning capabilities of large language models (LLMs). However, existing methods suffer from insufficient precision in feedback on generat…
Reinforcement LearningVI-CuRL: Stabilizing Verifier-Independent RL Reasoning via Confidence-Guided Variance Reduction
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a dominant paradigm for enhancing Large Language Models (LLMs) reasoning, yet its reliance on external verifiers limits its scalability. Recent finding…
Reinforcement LearningSelector-Guided Autonomous Curriculum for One-Shot Reinforcement Learning from Verifiable Rewards
Recently, Reinforcement Learning from Verifiable Rewards (RLVR) has been established as a highly effective technique for augmenting the math reasoning skills of Large Language Models (LLMs) based on a single instance. Cu…
Reinforcement LearningLearning to Reason at the Frontier of Learnability
Reinforcement learning is now widely adopted as the final stage of large language model training, especially for reasoning-style tasks such as maths problems. Typically, models attempt each question many times during a s…
Language ModelingLanguage ModellingLarge Language Modelreinforcement-learning+1