W
Wenjie Shi
Researcher at Tsinghua University
Publications - 11
Citations - 171
Wenjie Shi is an academic researcher from Tsinghua University. The author has contributed to research in topics: Reinforcement learning & Stability (learning theory). The author has an hindex of 6, co-authored 10 publications receiving 78 citations.
Papers
More filters
Journal ArticleDOI
Multi Pseudo Q-Learning-Based Deterministic Policy Gradient for Tracking Control of Autonomous Underwater Vehicles
TL;DR: In this article, a hybrid actor-critic architecture is proposed to achieve high-level tracking control accuracy of AUVs and stable learning by applying a hybrid actors-critics architecture, where multiple actors and critics are trained to learn a deterministic policy and action-value function, respectively.
Posted Content
Multi Pseudo Q-learning Based Deterministic Policy Gradient for Tracking Control of Autonomous Underwater Vehicles
TL;DR: The proposed MPQ-based deterministic policy gradient algorithm can achieve high-level tracking control accuracy of AUVs and stable learning by applying a hybrid actors-critics architecture, where multiple actors and critics are trained to learn a deterministicpolicy and action-value function, respectively.
Proceedings ArticleDOI
Soft Policy Gradient Method for Maximum Entropy Deep Reinforcement Learning.
Wenjie Shi,Shiji Song,Cheng Wu +2 more
TL;DR: This paper presents an off-policy actor-critic, model-free maximum entropy deep RL algorithm called deep soft policy gradient (DSPG) by combining hard policy gradient with soft Bellman equation to ensure stable learning while eliminating the need of two separate critics for soft value functions.
Proceedings Article
Regularized Anderson Acceleration for Off-Policy Deep Reinforcement Learning
TL;DR: This work proposes a general acceleration method for model-free, off-policy deep RL algorithms by drawing the idea underlying regularized Anderson acceleration (RAA), which is an effective approach to accelerating the solving of fixed point problems with perturbations.
Journal ArticleDOI
Self-Supervised Discovering of Interpretable Features for Reinforcement Learning.
TL;DR: A self-supervised interpretable framework is proposed, which can discover interpretable features to enable easy understanding of RL agents even for non-experts and provides valuable insight into the internal decision-making process of vision-based RL.