6 papers
Sample-efficient LLM Optimization with Reset Replay
Zichuan Liu, Jinyu Wang, Lei Song +1
Recent advancements in LLM post-training, particularly through reinforcement learning and preference optimization, are key to boosting their reasoning capabilities. However, these…
Time-RA: Towards Time Series Reasoning for Anomaly Diagnosis with LLM Feedback
Yiyuan Yang, Zichuan Liu, Lei Song +6
Time series anomaly detection (TSAD) has traditionally focused on binary classification and often lacks the fine-grained categorization and explanatory reasoning required for trans…
Position: Rethinking Post-Hoc Search-Based Neural Approaches for Solving Large-Scale Traveling Salesman Problems
Yifan Xia, Xianliang Yang, Zichuan Liu +3
Recent advancements in solving large-scale traveling salesman problems (TSP) utilize the heatmap-guided Monte Carlo tree search (MCTS) paradigm, where machine learning (ML) models…
Knowing What Not to Do: Leverage Language Model Insights for Action Space Pruning in Multi-agent Reinforcement Learning
Zhihao Liu, Xianliang Yang, Zichuan Liu +7
Multi-agent reinforcement learning (MARL) is employed to develop autonomous agents that can learn to adopt cooperative or competitive strategies within complex environments. Howeve…
TimeX++: Learning Time-Series Explanations with Information Bottleneck
Zichuan Liu, Tianchun Wang, Jimeng Shi +7
Explaining deep learning models operating on time series data is crucial in various applications of interest which require interpretable and transparent insights from time series s…
Higher Replay Ratio Empowers Sample-Efficient Multi-Agent Reinforcement Learning
Linjie Xu, Zichuan Liu, Alexander Dockhorn +4
One of the notorious issues for Reinforcement Learning (RL) is poor sample efficiency. Compared to single agent RL, the sample efficiency for Multi-Agent Reinforcement Learning (MA…