2019

Q-learning with UCB Exploration is Sample Efficient for Infinite-Horizon MDP

Dong, Kefan, Wang, Yuanhao, Chen, Xiaoyu et al.

Understand

A fundamental question in reinforcement learning is whether model-free algorithms are sample efficient.

  • Recently, Jin et al.
  • \cite{jin2018q} proposed a Q-learning algorithm with UCB exploration policy, and proved it has nearly optimal regret bound for finite-horizon episodic MDP.
  • In this paper, we adapt Q-learning with UCB-exploration bonus to infinite-horizon MDP with discounted rewards \emph{without} accessing a generative model.

Built on

  • R-max - a general polynomial time algorithm for near-optimal reinforcement learning

    Ronen I. Brafman and Moshe Tennenholtz · 2003

    Earlier work this paper cites.

  • Learning rates for q-learning

    Eyal Even-Dar and Yishay Mansour · 2003

    Earlier work this paper cites.

  • On the sample complexity of reinforcement learning

    Sham Machandranath Kakade et al · 2003

    Earlier work this paper cites.

  • Pac model-free reinforcement learning

    Alexander L Strehl, Lihong Li, Eric Wiewiora, John Langford, and Michael L Littman · 2006

    Earlier work this paper cites.

  • An analysis of model-based interval estimation for markov decision processes

    Alexander L Strehl and Michael L Littman · 2008

    Earlier work this paper cites.

  • Near-optimal regret bounds for reinforcement learning

    Thomas Jaksch, Ronald Ortner, and Peter Auer · 2010

    Earlier work this paper cites.

Similar

  • Model-based reinforcement learning with nearly tight exploration complexity bounds

    István Szita and Csaba Szepesvári · 2010

    Cited alongside, same era.

  • Speedy q-learning

    Mohammad Gheshlaghi Azar, Remi Munos, Mohammad Ghavamzadeh, and Hilbert Kappen · 2011

    Cited alongside, same era.

  • Pac bounds for discounted mdps

    Tor Lattimore and Marcus Hutter · 2012

    Cited alongside, same era.

  • Playing atari with deep reinforcement learning

    Original

    Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, and Martin Riedmiller · 2013

    Cited alongside, same era.

  • Trust region policy optimization

    John Schulman, Sergey Levine, Pieter Abbeel, Michael Jordan, and Philipp Moritz · 2015

    Cited alongside, same era.

  • Asynchronous methods for deep reinforcement learning

    Volodymyr Mnih, Adria Puigdomenech Badia, Mehdi Mirza, Alex Graves, Timothy Lillicrap, Tim Harley, David Silver, and Koray Kavukcuoglu · 2016

    Cited alongside, same era.

Then

  • Minimax regret bounds for reinforcement learning

    Original

    Mohammad Gheshlaghi Azar, Ian Osband, and Rémi Munos · 2017

    Later among the works it cites.

  • Unifying pac and regret: Uniform pac bounds for episodic reinforcement learning

    Christoph Dann, Tor Lattimore, and Emma Brunskill · 2017

    Later among the works it cites.

  • Is q-learning provably efficient?

    Chi Jin, Zeyuan Allen-Zhu, Sebastien Bubeck, and Michael I Jordan · 2018

    Later among the works it cites.

  • Near-optimal time and sample complexities for solving markov decision processes with a generative model

    Aaron Sidford, Mengdi Wang, Xian Wu, Lin Yang, and Yinyu Ye · 2018

    Later among the works it cites.

  • Variance reduced value iteration and faster algorithms for solving markov decision processes

    Aaron Sidford, Mengdi Wang, Xian Wu, and Yinyu Ye · 2018

    Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…