5 papers · 1 filter
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…
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…
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…
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…
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…