2015

Q-Networks for Binary Vector Actions

Yoshida, Naoto

Understand

In this paper reinforcement learning with binary vector actions was investigated.

  • We suggest an effective architecture of the neural networks for approximating an action-value function with binary vector actions.
  • The proposed architecture approximates the action-value function by a linear function with respect to the action vector, but is still non-linear with respect to the state input.
  • We show that this approximation method enables the efficient calculation of greedy action selection and softmax action selection.

Built on

  • Information processing in dynamical systems: foundations of harmony theory

    P Smolensky · 1986

    Earlier work this paper cites.

  • Learning from delayed rewards

    Christopher John Cornish Hellaby Watkins · 1989

    Earlier work this paper cites.

  • Q-learning

    Christopher JCH Watkins and Peter Dayan · 1992

    Earlier work this paper cites.

  • Self-improving reactive agents based on reinforcement learning, planning and teaching

    Long-Ji Lin · 1992

    Earlier work this paper cites.

Similar

  • Reinforcement learning: An introduction

    Richard S Sutton and Andrew G Barto · 1998

    Cited alongside, same era.

  • Using free energies to represent q-values in a multiagent reinforcement learning task

    Brian Sallans and Geoffrey E Hinton · 2000

    Cited alongside, same era.

  • Reinforcement learning with factored states and actions

    Brian Sallans and Geoffrey E Hinton · 2004

    Cited alongside, same era.

  • Reinforcement learning of motor skills in high dimensions: A path integral approach

    Evangelos Theodorou, Jonas Buchli, and Stefan Schaal · 2010

    Cited alongside, same era.

Then

  • Actor-critic reinforcement learning with energy-based policies

    Nicolas Heess, David Silver, and Yee Whye Teh · 2012

    Later among the works it cites.

  • Playing atari with deep reinforcement learning

    Original

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

    Later among the works it cites.

  • Human-level control through deep reinforcement learning

    Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A Rusu, Joel Veness, Marc G Bellemare, Alex Graves, Martin Riedmiller, Andreas K Fidjeland, Georg Ostrovski, et al · 2015

    Closest in time.

  • Continuous control with deep reinforcement learning

    Original

    Timothy P Lillicrap, Jonathan J Hunt, Alexander Pritzel, Nicolas Heess, Tom Erez, Yuval Tassa, David Silver, and Daan Wierstra · 2015

    Closest in time.

Beyond the bibliography

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

Open on alphaXiv

alphaXiv is searching for related work…