Effective unsupervised domain adaptation (UDA) requires a representation that captures transferable structure from both the labeled source domain and the unlabeled target domain. We introduce Joint Contrastive-Adversarial Representation Learning (JCAR), a two-stage framework that learns a common representation from the...
Yu-Ling Jiao, Li-Can Kang, Jerry Zhijian Yang et al.· 0 citations
In this work, we propose a transfer learning algorithm for covariate shift, integrating sample reweighting with representation learning. A key feature of our approach is the use of a lower-dimensional latent space for modeling, in contrast to conventional methods that operate directly in the high-dimensional ambient sp...
Yu-Ling Jiao, Li-Can Kang, Yang Xiang et al.· 0 citations
Finite-sample bounds are derived that separate the effects of critic estimation, neural drift regression, finite-sample SNIS, diffusion discretization, and inherited actor error on expected average policy suboptimality.
Yu-Ling Jiao, Li-Can Kang, Jerry Zhijian Yang et al.· 0 citations
A weighted Bellman residual minimization framework that incorporates density ratio weighting by effectively integrating expert demonstrations with behavioral data is introduced, providing specific guidance for the rational utilization of expert demonstrations.
Li-Can Kang, Jerry Zhijian Yang, Cheng Yuan et al.· 0 citations
In offline RL, estimating the optimal action-value function $Q^*$ can be formulated as solving the optimal Bellman equation based solely on offline observations. A fundamental challenge is that the reward function and transition kernel are unknown, so the optimal Bellman operator is not directly observable from data. T...
Xiao-Hong Chen, Yu-Ling Jiao, Li-Can Kang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
