Credit_assignment - 标签 - vllbc02's blogs

Credit_assignment

2025

Process-Supervised Reinforcement Learning for Interactive Multimodal Tool-Use Agents 09-23

Harnessing Uncertainty：Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents 09-13

GTPO：Trajectory-Based Policy Optimization in Large Language Models 08-08

GTPO and GRPO-S：Token and Sequence-Level Reward Shaping with Policy Entropy 08-08

Group-in-Group Policy Optimization for LLM Agent Training 08-07

CAPO：Towards Enhancing LLM Reasoning through Verifiable Generative Credit Assignment 08-07

Beyond Policy Optimization：A Data Curation Flywheel for Sparse-Reward Long-Horizon Planning 08-07

RLVMR：Reinforcement Learning with Verifiable Meta-Reasoning Rewards for Robust Long-Horizon Agents 08-02

Good Learners Think Their Thinking：Generative PRM Makes Large Reasoning Model More Efficient Math Learne 08-02

PROCESS REINFORCEMENT THROUGH IMPLICIT REWARDS 07-16