--- references: - id: AyedLearning2019 author: - family: Ayed given: Ibrahim - family: Bézenac given: Emmanuel non-dropping-particle: de citation-key: AyedLearning2019 container-title: Advances In Neural Information Processing Systems event-title: NeurIPS issued: - year: 2019 language: en page: '12' title: Learning Dynamical Systems from Partial Observations type: paper-conference - id: CollinsLocallyConnected2021 author: - family: Collins given: Nicholas - family: Kurniawati given: Hanna citation-key: CollinsLocallyConnected2021 collection-title: Springer Proceedings in Advanced Robotics container-title: Algorithmic Foundations of Robotics XIV DOI: 10.1007/978-3-030-66723-8_8 editor: - family: LaValle given: Steven M. - family: Lin given: Ming - family: Ojala given: Timo - family: Shell given: Dylan - family: Yu given: Jingjin event-place: Cham ISBN: 978-3-030-66723-8 issued: - year: 2021 language: en page: 124-142 publisher: Springer International Publishing publisher-place: Cham title: 'Locally-Connected Interrelated Network: A Forward Propagation Primitive' type: paper-conference - id: CollinsPartially2019 accessed: - year: 2022 month: 6 day: 7 author: - family: Collins given: Nicholas - family: Kurniawati given: Hanna citation-key: CollinsPartially2019 DOI: 10.48550/arXiv.1907.04457 issued: - year: 2019 month: 7 day: 9 number: arXiv:1907.04457 publisher: arXiv title: >- Partially Observable Planning and Learning for Systems with Non-Uniform Dynamics type: article URL: http://arxiv.org/abs/1907.04457 - id: JaakkolaReinforcement1995 accessed: - year: 2017 month: 9 day: 13 author: - family: Jaakkola given: Tommi - family: Singh given: Satinder P. - family: Jordan given: Michael I. citation-key: JaakkolaReinforcement1995 container-title: Advances in neural information processing systems issued: - year: 1995 page: 345–352 title: >- Reinforcement learning algorithm for partially observable Markov decision problems type: paper-conference URL: >- http://papers.nips.cc/paper/951-reinforcement-learning-algorithm-for-partially-observable-markov-decision-problems.pdf - id: KurniawatiPartially2022 accessed: - year: 2022 month: 6 day: 7 author: - family: Kurniawati given: Hanna citation-key: KurniawatiPartially2022 container-title: Annual Review of Control, Robotics, and Autonomous Systems container-title-short: Annu. Rev. Control Robot. Auton. Syst. DOI: 10.1146/annurev-control-042920-092451 ISSN: 2573-5144, 2573-5144 issue: '1' issued: - year: 2022 month: 5 day: 3 language: en page: 253-277 title: Partially Observable Markov Decision Processes and Robotics type: article-journal volume: '5' - id: OhsawaUnbiased2021 accessed: - year: 2022 month: 2 day: 14 author: - family: Ohsawa given: Shohei citation-key: OhsawaUnbiased2021 container-title: arXiv:2106.03007 [cs, econ, stat] issued: - year: 2021 month: 6 day: 5 title: Unbiased Self-Play type: article-journal URL: http://arxiv.org/abs/2106.03007 - id: ParisottoNeural2017 author: - family: Parisotto given: Emilio - family: Salakhutdinov given: Ruslan citation-key: ParisottoNeural2017 container-title: arXiv:1702.08360 [cs] issued: - year: 2017 month: 2 day: 27 title: 'Neural Map: Structured Memory for Deep Reinforcement Learning' type: article-journal URL: http://arxiv.org/abs/1702.08360 - id: RoyFinding2005 author: - family: Roy given: Nicholas - family: Gordon given: Geoffrey - family: Thrun given: Sebastian citation-key: RoyFinding2005 container-title: Journal of Artificial Intelligence Research container-title-short: J. Artif. Int. Res. DOI: 10.1613/jair.1496 ISSN: 1076-9757 issue: '1' issued: - year: 2005 month: 1 day: 1 page: 1–40 title: Finding approximate POMDP solutions through belief compression type: article-journal volume: '23' - id: ThrunMonte1999 author: - family: Thrun given: Sebastian - family: Langford given: John - family: Fox given: Dieter citation-key: ThrunMonte1999 container-title: Proceedings of the International Conference on Machine Learning event-place: Bled, Slovenia event-title: International Conference on Machine Learning issued: - year: 1999 language: en publisher-place: Bled, Slovenia title: >- Monte carlo hidden markov models: Learning non-parametric models of partially observable stochastic processes type: paper-conference URL: http://robots.stanford.edu/papers/thrun.mchmm.pdf ...