Settling the Horizon-Dependence of Sample Complexity in Reinforcement Learning

1 November 2021

Papers citing "Settling the Horizon-Dependence of Sample Complexity in Reinforcement Learning"

29 / 29 papers shown

Title
Rapidly Adapting Policies to the Real World via Simulation-Guided Fine-Tuning Patrick Yin Tyler Westenbroek Simran Bagaria Kevin Huang Ching-an Cheng Andrey Kobolov Abhishek Gupta 144 3 0 04 Feb 2025
Settling the Sample Complexity of Online Reinforcement Learning Zihan Zhang Yuxin Chen Jason D. Lee S. Du OffRL 188 23 0 25 Jul 2023
Nearly Horizon-Free Offline Reinforcement Learning Zhaolin Ren Jialian Li Bo Dai S. Du Sujay Sanghavi OffRL 69 49 0 25 Mar 2021
UCB Momentum Q-learning: Correcting the bias without forgetting Pierre Menard O. D. Domingues Xuedong Shang Michal Valko 118 42 0 01 Mar 2021
Nearly Minimax Optimal Reward-free Reinforcement Learning Zihan Zhang S. Du Xiangyang Ji OffRL 60 31 0 12 Oct 2020
Is Reinforcement Learning More Difficult Than Bandits? A Near-optimal Algorithm Escaping the Curse of Horizon Zihan Zhang Xiangyang Ji S. Du OffRL 106 105 0 28 Sep 2020
A Unifying View of Optimism in Episodic Reinforcement Learning Gergely Neu Ciara Pike-Burke 60 67 0 03 Jul 2020
$Q$ -learning with Logarithmic Regret Kunhe Yang Lin F. Yang S. Du 74 61 0 16 Jun 2020
Breaking the Sample Size Barrier in Model-Based Reinforcement Learning with a Generative Model Gen Li Yuting Wei Yuejie Chi Yuxin Chen 102 129 0 26 May 2020
Is Long Horizon Reinforcement Learning More Difficult Than Short Horizon Reinforcement Learning? Ruosong Wang S. Du Lin F. Yang Sham Kakade OffRL 69 52 0 01 May 2020
Almost Optimal Model-Free Reinforcement Learning via Reference-Advantage Decomposition Zihan Zhang Yuanshuo Zhou Xiangyang Ji OffRL 65 156 0 21 Apr 2020
Regret Minimization for Reinforcement Learning by Evaluating the Optimal Bias Function Zihan Zhang Xiangyang Ji 60 72 0 12 Jun 2019
Worst-Case Regret Bounds for Exploration via Randomized Value Functions Daniel Russo OffRL 45 85 0 07 Jun 2019
Non-Asymptotic Gap-Dependent Regret Bounds for Tabular MDPs Max Simchowitz Kevin Jamieson 63 145 0 09 May 2019
Q-learning with UCB Exploration is Sample Efficient for Infinite-Horizon MDP Kefan Dong Yuanhao Wang Xiaoyu Chen Liwei Wang OffRL 60 96 0 27 Jan 2019
Tighter Problem-Dependent Regret Bounds in Reinforcement Learning without Domain Knowledge using Value Function Bounds Andrea Zanette Emma Brunskill OffRL 104 276 0 01 Jan 2019
Policy Certificates: Towards Accountable Reinforcement Learning Christoph Dann Ashutosh Adhikari Wei Wei Jimmy J. Lin OffRL 120 144 0 07 Nov 2018
Is Q-learning Provably Efficient? Chi Jin Zeyuan Allen-Zhu Sébastien Bubeck Michael I. Jordan OffRL 70 807 0 10 Jul 2018
Variance-Aware Regret Bounds for Undiscounted Reinforcement Learning in MDPs M. S. Talebi Odalric-Ambrym Maillard 56 72 0 05 Mar 2018
Variance Reduced Value Iteration and Faster Algorithms for Solving Markov Decision Processes Aaron Sidford Mengdi Wang X. Wu Yinyu Ye 56 127 0 27 Oct 2017
Unifying PAC and Regret: Uniform PAC Bounds for Episodic Reinforcement Learning Christoph Dann Tor Lattimore Emma Brunskill 76 309 0 22 Mar 2017
Minimax Regret Bounds for Reinforcement Learning M. G. Azar Ian Osband Rémi Munos 86 775 0 16 Mar 2017
On Lower Bounds for Regret in Reinforcement Learning Ian Osband Benjamin Van Roy 81 101 0 09 Aug 2016
Why is Posterior Sampling Better than Optimism for Reinforcement Learning? Ian Osband Benjamin Van Roy BDL 83 261 0 01 Jul 2016
Sample Complexity of Episodic Fixed-Horizon Reinforcement Learning Christoph Dann Emma Brunskill 69 249 0 29 Oct 2015
(More) Efficient Reinforcement Learning via Posterior Sampling Ian Osband Daniel Russo Benjamin Van Roy 119 534 0 04 Jun 2013
On the Sample Complexity of Reinforcement Learning with a Generative Model M. G. Azar Rémi Munos H. Kappen 74 156 0 27 Jun 2012
REGAL: A Regularization based Algorithm for Reinforcement Learning in Weakly Communicating MDPs Peter L. Bartlett Ambuj Tewari 91 284 0 09 May 2012
PAC Bounds for Discounted MDPs Tor Lattimore Marcus Hutter 94 189 0 17 Feb 2012