23 citations · 77 across the 13 of their papers we have counts for
7 papers · 1 filter
STOPS: Short-Term-based Volatility-controlled Policy Search and its Global Convergence
Liangliang Xu, Daoming Lyu, Yangchen Pan +2
It remains challenging to deploy existing risk-averse approaches to real-world applications. The reasons are multi-fold, including the lack of global optimality guarantee and the n…
TDM: Trustworthy Decision-Making via Interpretability Enhancement
Daoming Lyu, Fangkai Yang, Hugh Kwon +3
Human-robot interactive decision-making is increasingly becoming ubiquitous, and trust is an influential factor in determining the reliance on autonomy. However, it is not reasonab…
Variance-Reduced Off-Policy Memory-Efficient Policy Search
Daoming Lyu, Qi Qi, Mohammad Ghavamzadeh +3
Off-policy policy optimization is a challenging problem in reinforcement learning (RL). The algorithms designed for this problem often suffer from high variance in their estimators…
Stable and Efficient Policy Evaluation
Daoming Lyu, Bo Liu, Matthieu Geist +3
Policy evaluation algorithms are essential to reinforcement learning due to their ability to predict the performance of a policy. However, there are two long-standing issues lying…
A Block Coordinate Ascent Algorithm for Mean-Variance Optimization
Bo Liu, Tengyang Xie, Yangyang Xu +4
Risk management in dynamic decision problems is a primary concern in many fields, including financial investment, autonomous driving, and healthcare. The mean-variance function is…
PEORL: Integrating Symbolic Planning and Hierarchical Reinforcement Learning for Robust Decision-Making
Fangkai Yang, Daoming Lyu, Bo Liu +1
Reinforcement learning and symbolic planning have both been used to build intelligent autonomous agents. Reinforcement learning relies on learning from interactions with real world…
OTD: (Near)-Optimal Off-Policy TD Learning
Bo Liu, Daoming Lyu, Wen Dong +1
Temporal difference learning and Residual Gradient methods are the most widely used temporal difference based learning algorithms; however, it has been shown that none of their obj…