Zhaohan Daniel

Jun 4, 2024 | arxiv.org | Zhaohan Daniel |Bernardo Avila

Feb 8, 2024 | arxiv.org | Zhaohan Daniel |Pierre D Harvey |Bernardo Avila

arXiv:2402.05749 (cs) Download PDF Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI) Cite as: arXiv:2402.05749 [cs.LG] (or arXiv:2402.05749v1 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2402.05749 Submission history From: Yunhao Tang [ view email] [v1] Thu, 8 Feb 2024 15:33:09 UTC (1,028 KB) Bibliographic Tools Bibliographic Explorer Toggle Bibliographic Explorer () Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart...

Dec 1, 2023 | arxiv.org | Mohammad Gheshlaghi |Zhaohan Daniel

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

May 1, 2023 | arxiv.org | Zhaohan Daniel

Representation learning and exploration are among the key challenges for any deep reinforcement learning agent. In this work, we provide a singular value decomposition based method that can be used to obtain representations that preserve the underlying transition structure in the domain.