7 citations · 8 across the 4 of their papers we have counts for
4 papers
When to Trust Your Data: Enhancing Dyna-Style Model-Based Reinforcement Learning With Data Filter
Yansong Li, Zeyu Dong, Ertai Luo +3
Reinforcement learning (RL) algorithms can be divided into two classes: model-free algorithms, which are sample-inefficient, and model-based algorithms, which suffer from model bia…
Solving Strongly Convex and Smooth Stackelberg Games Without Modeling the Follower
Yansong Li, Shuo Han
Stackelberg games have been widely used to model interactive decision-making problems in a variety of domains such as energy systems, transportation, cybersecurity, and human-robot…
Composite FORCE learning of chaotic echo state networks for time-series prediction
Yansong Li, Kai Hu, Kohei Nakajima +1
Echo state network (ESN), a kind of recurrent neural networks, consists of a fixed reservoir in which neurons are connected randomly and recursively and obtains the desired output…
Accelerating Model-Free Policy Optimization Using Model-Based Gradient: A Composite Optimization Perspective
Yansong Li, Shuo Han
We develop an algorithm that combines model-based and model-free methods for solving a nonlinear optimal control problem with a quadratic cost in which the system model is given by…