11 papers
Return Augmented Decision Transformer for Off-Dynamics Reinforcement Learning
Ruhan Wang, Yu Yang, Zhishuai Liu +2
We study offline off-dynamics reinforcement learning (RL) to utilize data from an easily accessible source domain to enhance policy learning in a target domain with limited data. O…
Convergence of Sign-based Random Reshuffling Algorithms for Nonconvex Optimization
Zhen Qin, Zhishuai Liu, Pan Xu
signSGD is attractive in nonconvex optimization because it communicates sign-valued rather than full-precision gradients. Several standard analyses assume independent stochastic-gr…
Sample Complexity of Distributionally Robust Off-Dynamics Reinforcement Learning with Online Interaction
Yiting He, Zhishuai Liu, Weixin Wang +1
Off-dynamics reinforcement learning (RL), where training and deployment transition dynamics are different, can be formulated as learning in a robust Markov decision process (RMDP)…
Robust Offline Reinforcement Learning with Linearly Structured f-Divergence Regularization
Cheng Tang, Zhishuai Liu, Pan Xu
The Robust Regularized Markov Decision Process (RRMDP) is proposed to learn policies robust to dynamics shifts by adding regularization to the transition dynamics in the value func…
Policy Regularized Distributionally Robust Markov Decision Processes with Linear Function Approximation
Jingwen Gu, Yiting He, Zhishuai Liu +1
Decision-making under distribution shift is a central challenge in reinforcement learning (RL), where training and deployment environments differ. We study this problem through the…
A Differential Manifold Perspective and Universality Analysis of Continuous Attractors in Artificial Neural Networks
Shaoxin Tian, Hongkai Liu, Yuying Yang +5
Continuous attractors are critical for information processing in both biological and artificial neural systems, with implications for spatial navigation, memory, and deep learning…