collaborators

6 papers

cs.LG2026

HISR: Hindsight Information Modulated Segmental Process Rewards For Multi-turn Agentic Reinforcement Learning

Zhicong Lu, Zichuan Lin, Wei Jia +7

While large language models excel in diverse domains, their performance on complex longhorizon agentic decision-making tasks remains limited. Most existing methods concentrate on d…

cs.LG2026

Temporal Difference Learning with Constrained Initial Representations

Jiafei Lyu, Jingwen Yang, Zhongjian Qiao +5

Recently, there have been numerous attempts to enhance the sample efficiency of off-policy reinforcement learning (RL) agents when interacting with the environment, including archi…

cs.LG2026

Cross-Domain Offline Policy Adaptation via Selective Transition Correction

Mengbei Yan, Jiafei Lyu, Shengjie Sun +5

It remains a critical challenge to adapt policies across domains with mismatched dynamics in reinforcement learning (RL). In this paper, we study cross-domain offline RL, where an…

cs.AI2026

ProAct: Agentic Lookahead in Interactive Environments

Yangbin Yu, Mingyu Yang, Junyou Li +9

Existing Large Language Model (LLM) agents struggle in interactive environments requiring long-horizon planning, primarily due to compounding errors when simulating future states.…

cs.LG2026

EntroPIC: Towards Stable Long-Term Training of LLMs via Entropy Stabilization with Proportional-Integral Control

Kai Yang, Xin Xu, Yangkun Chen +5

Long-term training of large language models (LLMs) requires maintaining stable exploration to prevent the model from collapsing into sub-optimal behaviors. Entropy is crucial in th…

cs.LG2025

PROF: An LLM-based Reward Code Preference Optimization Framework for Offline Imitation Learning

Shengjie Sun, Jiafei Lyu, Runze Liu +4

Offline imitation learning (offline IL) enables training effective policies without requiring explicit reward annotations. Recent approaches attempt to estimate rewards for unlabel…