4 papers
SAPO: Single-Rollout Autoregressive Policy Optimization for Agentic Reinforcement Learning
Dayang Liang, Lang Feng, Bo An +1
Agentic reinforcement learning (RL) has become a critical stage in the post-training of large language models. Existing critic-free, group-relative methods estimate policy advantag…
PlanPO: Group Planning-Aware Policy Optimization for Multi-Turn Agentic LLMs
Dayang Liang, Liyuan He, Xuan Feng +3
Group-relative policy optimization has emerged as a key paradigm for training agentic large language models (LLMs) on multi-turn interactive tasks. However, most existing variants…
Online Causal Kalman Filtering for Stable and Effective Policy Optimization
Shuo He, Lang Feng, Xin Cheng +2
Reinforcement learning for large language models suffers from high-variance token-level importance sampling (IS) ratios, which would destabilize policy optimization at scale. To im…
Task-Aware Exploration via a Predictive Bisimulation Metric
Dayang Liang, Ruihan Liu, Lipeng Wan +2
Accelerating exploration in visual reinforcement learning under sparse rewards remains challenging due to the substantial task-irrelevant variations. Despite advances in intrinsic…