Learning States Representations in POMDP
Machine Learning
2014-06-18 v4
Abstract
We propose to deal with sequential processes where only partial observations are available by learning a latent representation space on which policies may be accurately learned.
Cite
@article{arxiv.1312.6042,
title = {Learning States Representations in POMDP},
author = {Gabriella Contardo and Ludovic Denoyer and Thierry Artieres and Patrick Gallinari},
journal= {arXiv preprint arXiv:1312.6042},
year = {2014}
}
Comments
4 pages
Related papers
View all related →
Machine Learning · Computer Science
Learning Causal State Representations of Partially Observable Environments
Amy Zhang, Zachary C. Lipton, Luis Pineda, Kamyar Azizzadenesheli +4
2021-02-09
Machine Learning · Computer Science
Toward Learning POMDPs Beyond Full-Rank Actions and State Observability
Seiji Shaw, Travis Manderson, Chad Kessens, Nicholas Roy
2026-02-04
Machine Learning · Computer Science
Provable Representation with Efficient Planning for Partial Observable Reinforcement Learning
Hongming Zhang, Tongzheng Ren, Chenjun Xiao, Dale Schuurmans +1
2024-06-12
Machine Learning · Computer Science
Provable Reinforcement Learning with a Short-Term Memory
Yonathan Efroni, Chi Jin, Akshay Krishnamurthy, Sobhan Miryoosefi
2022-02-09
Machine Learning · Computer Science
Learning Policy Representations for Steerable Behavior Synthesis
Beiming Li, Sergio Rozada, Alejandro Ribeiro
2026-02-02
Machine Learning · Computer Science
PAC Reinforcement Learning for Predictive State Representations
Wenhao Zhan, Masatoshi Uehara, Wen Sun, Jason D. Lee
2022-08-16
Artificial Intelligence · Computer Science
Learning Explainable and Better Performing Representations of POMDP Strategies
Alexander Bork, Debraj Chakraborty, Kush Grover, Jan Kretinsky +1
2024-10-03
Machine Learning · Computer Science
Scaling Internal-State Policy-Gradient Methods for POMDPs
Douglas Aberdeen, Jonathan Baxter
2025-12-08
Machine Learning · Computer Science
Learning in POMDPs is Sample-Efficient with Hindsight Observability
Jonathan N. Lee, Alekh Agarwal, Christoph Dann, Tong Zhang
2023-02-07
Machine Learning · Computer Science
When Is Partially Observable Reinforcement Learning Not Scary?
Qinghua Liu, Alan Chung, Csaba Szepesvári, Chi Jin
2022-05-26
Robotics · Computer Science
Learning from Humans as an I-POMDP
Mark P. Woodward, Robert J. Wood
2012-04-03
Artificial Intelligence · Computer Science
Value-Function Approximations for Partially Observable Markov Decision Processes
M. Hauskrecht
2011-06-02
Optimization and Control · Mathematics
Sequential Stochastic Optimization in Separable Learning Environments
R. Reid Bishop, Chelsea C. White
2021-08-24
Machine Learning · Computer Science
Provably Efficient Representation Learning with Tractable Planning in Low-Rank POMDP
Jiacheng Guo, Zihao Li, Huazheng Wang, Mengdi Wang +2
2023-06-22
Machine Learning · Computer Science
Sample-Efficient Learning of POMDPs with Multiple Observations In Hindsight
Jiacheng Guo, Minshuo Chen, Huan Wang, Caiming Xiong +2
2023-07-07
Machine Learning · Computer Science
Near-Optimal Partially Observable Reinforcement Learning with Partial Online State Information
Ming Shi, Yingbin Liang, Ness B. Shroff
2026-01-27
Machine Learning · Computer Science
PcLast: Discovering Plannable Continuous Latent States
Anurag Koul, Shivakanth Sujit, Shaoru Chen, Ben Evans +10
2024-06-12
Artificial Intelligence · Computer Science
LLM-Guided Probabilistic Program Induction for POMDP Model Estimation
Aidan Curtis, Hao Tang, Thiago Veloso, Kevin Ellis +3
2025-05-13
Machine Learning · Computer Science
Learning latent state representation for speeding up exploration
Giulia Vezzani, Abhishek Gupta, Lorenzo Natale, Pieter Abbeel
2019-05-31
Machine Learning · Computer Science
Prospective Side Information for Latent MDPs
Jeongyeol Kwon, Yonathan Efroni, Shie Mannor, Constantine Caramanis
2023-10-12
Machine Learning · Computer Science
Learning State Representations in Complex Systems with Multimodal Data
Pavel Solovev, Vladimir Aliev, Pavel Ostyakov, Gleb Sterkin +6
2019-01-17
Machine Learning · Computer Science
Representing Spatial Trajectories as Distributions
Dídac Surís, Carl Vondrick
2022-10-05
Artificial Intelligence · Computer Science
Point-Based Methods for Model Checking in Partially Observable Markov Decision Processes
Maxime Bouton, Jana Tumova, Mykel J. Kochenderfer
2020-01-14
Machine Learning · Computer Science
Provably Efficient Reinforcement Learning in Partially Observable Dynamical Systems
Masatoshi Uehara, Ayush Sekhari, Jason D. Lee, Nathan Kallus +1
2022-06-27
Machine Learning · Computer Science
An Empirical Study of Representation Learning for Reinforcement Learning in Healthcare
Taylor W. Killian, Haoran Zhang, Jayakumar Subramanian, Mehdi Fatemi +1
2020-11-24