Discounted Beta-Bernoulli Reward Estimation for Sample-Efficient Reinforcement Learning with Verifiable Rewards 文章

ArXiv CS.AI2026-05-26NEWSen作者: Haechan Kim, Soohyun Ryu, Gyouk Chu, Doohyuk Jang, Eunho Yang
大语言模型
查看原文 →
关系图谱

Discounted Beta-Bernoulli Reward Estimation for Sample-Efficient Reinforcement Learning with Verifiable Rewards · 相关技术

相关技术

LLMORMODEPLAlanguage model远程代码执行（RCE）后训练statisticsreinforcement learningdivide-and-conquer partitioningStraight-Through EstimatorReinforcement learning with verifiable rewardsRLVRParts-of-Speech (POS) tagsLayout-as-Policylarge language modelsHISGroupForFFIARGANNRAW