5 papers
SHAP-Guided Kernel Actor-Critic for Explainable Reinforcement Learning
Na Li, Hangguan Shan, Wei Ni +2
Actor-critic (AC) methods are a cornerstone of reinforcement learning (RL) but offer limited interpretability. Current explainable RL methods seldom use state attributions to assis…
Multivariate Time Series Forecasting with Hybrid Euclidean-SPD Manifold Graph Neural Networks
Yong Fang, Na Li, Hangguan Shan +4
Multivariate Time Series (MTS) forecasting plays a vital role in various real-world applications, such as traffic management and predictive maintenance. Existing approaches typical…
Learning Causal States Under Partial Observability and Perturbation
Na Li, Hangguan Shan, Wei Ni +3
A critical challenge for reinforcement learning (RL) is making decisions based on incomplete and noisy observations, especially in perturbed and partially observable Markov decisio…
Sample-Efficient Tabular Self-Play for Offline Robust Reinforcement Learning
Na Li, Zewu Zheng, Wei Ni +3
Multi-agent reinforcement learning (MARL), as a thriving field, explores how multiple agents independently make decisions in a shared dynamic environment. Due to environmental unce…
Provable Memory Efficient Self-Play Algorithm for Model-free Reinforcement Learning
Na Li, Yuchen Jiao, Hangguan Shan +1
The thriving field of multi-agent reinforcement learning (MARL) studies how a group of interacting agents make decisions autonomously in a shared dynamic environment. Existing theo…