1 citations · 1 across the 6 of their papers we have counts for
7 papers
Near-Optimal Sample Complexity for Online Constrained MDPs
Chang Liu, Yunfan Li, Lin F. Yang
Safety is a fundamental challenge in reinforcement learning (RL), particularly in real-world applications such as autonomous driving, robotics, and healthcare. To address this, Con…
Beyond Entangled Planning: Task-Decoupled Planning for Long-Horizon Agents
Yunfan Li, Bingbing Xu, Xueyun Tian +2
Recent advances in large language models (LLMs) have enabled agents to autonomously execute complex, long-horizon tasks, yet planning remains a primary bottleneck for reliable task…
Chain-of-Memory: Lightweight Memory Construction with Dynamic Evolution for LLM Agents
Xiucheng Xu, Bingbing Xu, Xueyun Tian +4
External memory systems are pivotal for enabling Large Language Model (LLM) agents to maintain persistent knowledge and perform long-horizon decision-making. Existing paradigms typ…
Multi-Personality Generation of LLMs at Decoding-time
Rongxin Chen, Yunfan Li, Yige Yuan +2
Multi-personality generation for LLMs, enabling simultaneous embodiment of multiple personalization attributes, is a fundamental challenge. Existing retraining-based approaches are…
Inference-time Alignment in Continuous Space
Yige Yuan, Teng Xiao, Li Yunfan +5
Aligning large language models with human feedback at inference time has received increasing attention due to its flexibility. Existing methods rely on generating multiple response…
Hyper: Hyperparameter Robust Efficient Exploration in Reinforcement Learning
Yiran Wang, Chenshu Liu, Yunfan Li +3
The exploration \& exploitation dilemma poses significant challenges in reinforcement learning (RL). Recently, curiosity-based exploration methods achieved great success in tacklin…
Uniform Last-Iterate Guarantee for Bandits and Reinforcement Learning
Junyan Liu, Yunfan Li, Ruosong Wang +1
Existing metrics for reinforcement learning (RL) such as regret, PAC bounds, or uniform-PAC (Dann et al., 2017), typically evaluate the cumulative performance, while allowing the a…