v1v2 (latest)

A PAC RL Algorithm for Episodic POMDPs

25 May 2016

Papers citing "A PAC RL Algorithm for Episodic POMDPs"

37 / 37 papers shown

Statistical Tractability of Off-policy Evaluation of History-dependent Policies in POMDPsInternational Conference on Learning Representations (ICLR), 2025

Yuheng Zhang

Nan Jiang

OffRL

302

03 Mar 2025

Efficient Learning of POMDPs with Known Observation Model in Average-Reward Setting

Alessio Russo

Alberto Maria Metelli

Marcello Restelli

251

02 Oct 2024

RL in Latent MDPs is Tractable: Online Guarantees via Off-Policy Evaluation

Jeongyeol Kwon

Shie Mannor

Constantine Caramanis

Yonathan Efroni

OffRL

444

03 Jun 2024

On the Curses of Future and History in Future-dependent Value Functions for Off-policy Evaluation

Yuheng Zhang

Nan Jiang

OffRL

318

22 Feb 2024

Provable Representation with Efficient Planning for Partial Observable Reinforcement LearningInternational Conference on Machine Learning (ICML), 2023

451

20 Nov 2023

Posterior Sampling-based Online Learning for Episodic POMDPs

450

16 Oct 2023

Learning Optimal Admission Control in Partially Observable Queueing Networks

Jonatha Anselmi

B. Gaujal

Louis-Sébastien Rebuffi

176

04 Aug 2023

Sample-Efficient Learning of POMDPs with Multiple Observations In HindsightInternational Conference on Learning Representations (ICLR), 2023

Mengdi Wang

298

06 Jul 2023

Provably Efficient UCB-type Algorithms For Learning Predictive State RepresentationsInternational Conference on Learning Representations (ICLR), 2023

424

01 Jul 2023

Provably Efficient Representation Learning with Tractable Planning in Low-Rank POMDPInternational Conference on Machine Learning (ICML), 2023

280

21 Jun 2023

Representations and Exploration for Deep Reinforcement Learning using Singular Value DecompositionInternational Conference on Machine Learning (ICML), 2023

346

01 May 2023

Act-Then-Measure: Reinforcement Learning for Partially Observable Environments with Active MeasuringInternational Conference on Automated Planning and Scheduling (ICAPS), 2023

220

14 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

360

31 Jan 2023

An Instrumental Variable Approach to Confounded Off-Policy EvaluationInternational Conference on Machine Learning (ICML), 2022

361

29 Dec 2022

Reward-Mixing MDPs with a Few Latent Contexts are Learnable

Jeongyeol Kwon

Yonathan Efroni

Constantine Caramanis

Shie Mannor

213

05 Oct 2022

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

345

29 Sep 2022

Future-Dependent Value-Based Off-Policy Evaluation in POMDPsNeural Information Processing Systems (NeurIPS), 2022

499

26 Jul 2022

PAC Reinforcement Learning for Predictive State RepresentationsInternational Conference on Learning Representations (ICLR), 2022

542

12 Jul 2022

Computationally Efficient PAC RL in POMDPs with Latent Determinism and Conditional EmbeddingsInternational Conference on Machine Learning (ICML), 2022

262

24 Jun 2022

Provably Efficient Reinforcement Learning in Partially Observable Dynamical SystemsNeural Information Processing Systems (NeurIPS), 2022

317

24 Jun 2022

Learning in Observable POMDPs, without Computationally Intractable OraclesNeural Information Processing Systems (NeurIPS), 2022

Noah Golowich

Ankur Moitra

Dhruv Rohatgi

274

07 Jun 2022

Sample-Efficient Reinforcement Learning of Partially Observable Markov GamesNeural Information Processing Systems (NeurIPS), 2022

Qinghua Liu

Csaba Szepesvári

Chi Jin

313

02 Jun 2022

Pessimism in the Face of Confounders: Provably Efficient Offline Reinforcement Learning in Partially Observable Markov Decision ProcessesInternational Conference on Learning Representations (ICLR), 2022

432

26 May 2022

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

382

26 May 2022

Reinforcement Learning from Partial Observation: Linear Function Approximation with Provable Sample EfficiencyInternational Conference on Machine Learning (ICML), 2022

Qi Cai

Zhuoran Yang

Zhaoran Wang

242

20 Apr 2022

When Is Partially Observable Reinforcement Learning Not Scary?Annual Conference Computational Learning Theory (COLT), 2022

278

123

19 Apr 2022

Provable Reinforcement Learning with a Short-Term MemoryInternational Conference on Machine Learning (ICML), 2022

256

08 Feb 2022

Planning in Observable POMDPs in Quasipolynomial Time

Noah Golowich

Ankur Moitra

Dhruv Rohatgi

311

12 Jan 2022

Reinforcement Learning in Reward-Mixing MDPs

Jeongyeol Kwon

Yonathan Efroni

Constantine Caramanis

Shie Mannor

412

07 Oct 2021

Sublinear Regret for Learning POMDPsProduction and operations management (POM), 2021

Yi Xiong

Ningyuan Chen

Xiang Zhou

449

08 Jul 2021

RL for Latent MDPs: Regret Guarantees and a Lower BoundNeural Information Processing Systems (NeurIPS), 2021

Jeongyeol Kwon

Yonathan Efroni

Constantine Caramanis

Shie Mannor

330

09 Feb 2021

Sequential Transfer in Reinforcement Learning with a Generative Model

Andrea Tirinzoni

Riccardo Poiani

Marcello Restelli

220

01 Jul 2020

Sample-Efficient Reinforcement Learning of Undercomplete POMDPs

416

22 Jun 2020

Hidden Markov Model Estimation-Based Q-learning for Partially Observable Markov Decision Process

Hyung-Jin Yoon

Donghwan Lee

N. Hovakimyan

230

17 Sep 2018

On Oracle-Efficient PAC RL with Rich ObservationsNeural Information Processing Systems (NeurIPS), 2018

355

105

01 Mar 2018

Reinforcement Learning in Rich-Observation MDPs using Spectral Methods

Kamyar Azizzadenesheli

A. Lazaric

Anima Anandkumar

346

11 Nov 2016

Reinforcement Learning of POMDPs using Spectral Methods

Kamyar Azizzadenesheli

A. Lazaric

Anima Anandkumar

268

141

25 Feb 2016