<?xml version="1.0"?>
<dblpperson name="Mianchu Wang" pid="342/7390" n="8">
<person key="homepages/342/7390" mdate="2023-03-20">
<author pid="342/7390">Mianchu Wang</author>
</person>
<r><inproceedings key="conf/iclr/WangJM25" mdate="2025-05-15">
<author pid="342/7390">Mianchu Wang</author>
<author pid="57/2622">Yue Jin</author>
<author pid="89/449">Giovanni Montana</author>
<title>Learning on One Mode: Addressing Multi-modality in Offline Reinforcement Learning.</title>
<year>2025</year>
<booktitle>ICLR</booktitle>
<ee type="oa">https://openreview.net/forum?id=upkxzurnLC</ee>
<crossref>conf/iclr/2025</crossref>
<url>db/conf/iclr/iclr2025.html#WangJM25</url>
</inproceedings>
</r>
<r><inproceedings key="conf/nips/WangM25" mdate="2026-06-23">
<author pid="342/7390">Mianchu Wang</author>
<author pid="89/449">Giovanni Montana</author>
<title>Retrosynthesis Planning via Worst-path Policy Optimisation in Tree-structured MDPs.</title>
<year>2025</year>
<booktitle>NeurIPS</booktitle>
<ee type="oa">http://papers.nips.cc/paper_files/paper/2025/hash/bfe7998398779dde03cad7a73b1f81b6-Abstract-Conference.html</ee>
<crossref>conf/nips/2025</crossref>
<url>db/conf/nips/neurips2025.html#WangM25</url>
</inproceedings>
</r>
<r><article publtype="informal" key="journals/corr/abs-2509-10504" mdate="2025-10-13">
<author pid="342/7390">Mianchu Wang</author>
<author pid="89/449">Giovanni Montana</author>
<title>Retrosynthesis Planning via Worst-path Policy Optimisation in Tree-structured MDPs.</title>
<year>2025</year>
<month>September</month>
<volume>abs/2509.10504</volume>
<journal>CoRR</journal>
<ee type="oa">https://doi.org/10.48550/arXiv.2509.10504</ee>
<url>db/journals/corr/corr2509.html#abs-2509-10504</url>
<stream>streams/journals/corr</stream>
</article>
</r>
<r><article key="journals/ml/WangJM24" mdate="2025-11-15">
<author pid="342/7390">Mianchu Wang</author>
<author orcid="0000-0002-0344-4868" pid="57/2622">Yue Jin</author>
<author orcid="0000-0003-3942-3900" pid="89/449">Giovanni Montana</author>
<title>Goal-conditioned offline reinforcement learning through state space partitioning.</title>
<pages>2435-2465</pages>
<year>2024</year>
<month>May</month>
<volume>113</volume>
<journal>Mach. Learn.</journal>
<number>5</number>
<ee type="oa">https://doi.org/10.1007/s10994-023-06500-z</ee>
<ee>https://www.wikidata.org/entity/Q128665597</ee>
<url>db/journals/ml/ml113.html#WangJM24</url>
</article>
</r>
<r><article key="journals/tmlr/Wang0CSFM24" mdate="2024-08-08">
<author pid="342/7390">Mianchu Wang</author>
<author pid="92/1942-10">Rui Yang 0010</author>
<author pid="16/3283">Xi Chen</author>
<author pid="82/2248">Hao Sun</author>
<author pid="67/463">Meng Fang</author>
<author pid="89/449">Giovanni Montana</author>
<title>GOPlan: Goal-conditioned Offline Reinforcement Learning by Planning with Learned Models.</title>
<year>2024</year>
<volume>2024</volume>
<journal>Trans. Mach. Learn. Res.</journal>
<ee type="oa">https://openreview.net/forum?id=zOKAmm8R9B</ee>
<url>db/journals/tmlr/tmlr2024.html#Wang0CSFM24</url>
</article>
</r>
<r><article publtype="informal" key="journals/corr/abs-2412-03258" mdate="2025-01-13">
<author pid="342/7390">Mianchu Wang</author>
<author pid="57/2622">Yue Jin</author>
<author pid="89/449">Giovanni Montana</author>
<title>Learning on One Mode: Addressing Multi-Modality in Offline Reinforcement Learning.</title>
<year>2024</year>
<volume>abs/2412.03258</volume>
<journal>CoRR</journal>
<ee type="oa">https://doi.org/10.48550/arXiv.2412.03258</ee>
<url>db/journals/corr/corr2412.html#abs-2412-03258</url>
<stream>streams/journals/corr</stream>
</article>
</r>
<r><article publtype="informal" key="journals/corr/abs-2303-09367" mdate="2023-03-20">
<author pid="342/7390">Mianchu Wang</author>
<author pid="57/2622">Yue Jin</author>
<author pid="89/449">Giovanni Montana</author>
<title>Goal-conditioned Offline Reinforcement Learning through State Space Partitioning.</title>
<year>2023</year>
<volume>abs/2303.09367</volume>
<journal>CoRR</journal>
<ee type="oa">https://doi.org/10.48550/arXiv.2303.09367</ee>
<url>db/journals/corr/corr2303.html#abs-2303-09367</url>
</article>
</r>
<r><article publtype="informal" key="journals/corr/abs-2310-20025" mdate="2024-08-08">
<author pid="342/7390">Mianchu Wang</author>
<author pid="92/1942-10">Rui Yang 0010</author>
<author pid="16/3283">Xi Chen</author>
<author pid="67/463">Meng Fang</author>
<title>GOPlan: Goal-conditioned Offline Reinforcement Learning by Planning with Learned Models.</title>
<year>2023</year>
<volume>abs/2310.20025</volume>
<journal>CoRR</journal>
<ee type="oa">https://doi.org/10.48550/arXiv.2310.20025</ee>
<url>db/journals/corr/corr2310.html#abs-2310-20025</url>
</article>
</r>
<coauthors n="6" nc="1">
<co c="0"><na f="c/Chen:Xi" pid="16/3283">Xi Chen</na></co>
<co c="0"><na f="f/Fang:Meng" pid="67/463">Meng Fang</na></co>
<co c="0"><na f="j/Jin:Yue" pid="57/2622">Yue Jin</na></co>
<co c="0"><na f="m/Montana:Giovanni" pid="89/449">Giovanni Montana</na></co>
<co c="0"><na f="s/Sun:Hao" pid="82/2248">Hao Sun</na></co>
<co c="0"><na f="y/Yang_0010:Rui" pid="92/1942-10">Rui Yang 0010</na></co>
</coauthors>
</dblpperson>

