Embed to Control Partially Observed Systems: Representation Learning
with Provable Sample Efficiency

v1v2 (latest)

Embed to Control Partially Observed Systems: Representation Learning with Provable Sample Efficiency

26 May 2022

ArXiv (abs)PDF HTML

Papers citing "Embed to Control Partially Observed Systems: Representation Learning with Provable Sample Efficiency"

15 / 15 papers shown

Title
Scalable Policy-Based RL Algorithms for POMDPs Ameya Anjarlekar Rasoul Etesami R Srikant 84 0 0 08 Oct 2025
Transformers as Multi-task Learners: Decoupling Features in Hidden Markov Models Yifan Hao Chenlu Ye Chi Han Tong Zhang 205 0 0 02 Jun 2025
Statistical Tractability of Off-policy Evaluation of History-dependent Policies in POMDPsInternational Conference on Learning Representations (ICLR), 2025 Yuheng Zhang Nan Jiang OffRL 239 2 0 03 Mar 2025
Generalizing Multi-Step Inverse Models for Representation Learning to Finite-Memory POMDPs Lili Wu Ben Evans Riashat Islam Raihan Seraj Yonathan Efroni Alex Lamb 256 1 0 22 Apr 2024
Sample-Efficient Learning of POMDPs with Multiple Observations In HindsightInternational Conference on Learning Representations (ICLR), 2023 Jiacheng Guo Minshuo Chen Haiquan Wang Caiming Xiong Mengdi Wang Yu Bai 251 6 0 06 Jul 2023
Provably Efficient UCB-type Algorithms For Learning Predictive State RepresentationsInternational Conference on Learning Representations (ICLR), 2023 Ruiquan Huang Yitao Liang J. Yang OffRL 364 6 0 01 Jul 2023
Provably Efficient Representation Learning with Tractable Planning in Low-Rank POMDPInternational Conference on Machine Learning (ICML), 2023 Jiacheng Guo Zihao Li Huazheng Wang Mengdi Wang Zhuoran Yang Xuezhou Zhang 224 7 0 21 Jun 2023
Maximize to Explore: One Objective Function Fusing Estimation, Planning, and ExplorationNeural Information Processing Systems (NeurIPS), 2023 Zhihan Liu Miao Lu Wei Xiong Han Zhong Haotian Hu Shenao Zhang Sirui Zheng Zhuoran Yang Zhaoran Wang OffRL 328 24 0 29 May 2023
Representations and Exploration for Deep Reinforcement Learning using Singular Value DecompositionInternational Conference on Machine Learning (ICML), 2023 Yash Chandak S. Thakoor Z. Guo Yunhao Tang Rémi Munos Will Dabney Diana Borsa 271 6 0 01 May 2023
Improved Sample Complexity for Reward-free Reinforcement Learning under Low-rank MDPsInternational Conference on Learning Representations (ICLR), 2023 Yuan Cheng Ruiquan Huang J. Yang Yitao Liang OffRL 246 9 0 20 Mar 2023
Learning in POMDPs is Sample-Efficient with Hindsight ObservabilityInternational Conference on Machine Learning (ICML), 2023 Jonathan Lee Alekh Agarwal Christoph Dann Tong Zhang 247 23 0 31 Jan 2023
Partially Observable RL with B-Stability: Unified Structural Condition and Sharp Sample-Efficient AlgorithmsInternational Conference on Learning Representations (ICLR), 2022 Fan Chen Yu Bai Song Mei 299 24 0 29 Sep 2022
PAC Reinforcement Learning for Predictive State RepresentationsInternational Conference on Learning Representations (ICLR), 2022 Wenhao Zhan Masatoshi Uehara Wen Sun Jason D. Lee 364 43 0 12 Jul 2022
Provably Efficient Reinforcement Learning in Partially Observable Dynamical SystemsNeural Information Processing Systems (NeurIPS), 2022 Masatoshi Uehara Ayush Sekhari Jason D. Lee Nathan Kallus Wen Sun OffRL 279 40 0 24 Jun 2022
Finite-Time Analysis of Natural Actor-Critic for POMDPsSIAM Journal on Mathematics of Data Science (SIMODS), 2022 Semih Cayci Niao He R. Srikant 198 6 0 20 Feb 2022