Reinforcement Learning in Continuous Time and Space

@article{Doya2000ReinforcementLI,
  title={Reinforcement Learning in Continuous Time and Space},
  author={Kenji Doya},
  journal={Neural Computation},
  year={2000},
  volume={12},
  pages={219-245}
}
This article presents a reinforcement learning framework for continuous-time dynamical systems without a priori discretization of time, state, and action. Basedonthe Hamilton-Jacobi-Bellman (HJB) equation for infinite-horizon, discounted reward problems, we derive algorithms for estimating value functions and improving policies with the use of function approximators. The process of value function estimation is formulated as the minimization of a continuous-time form of the temporal difference… CONTINUE READING
BETA

Similar Papers

Citations

Publications citing this paper.
SHOWING 1-10 OF 463 CITATIONS, ESTIMATED 84% COVERAGE

Muscle Synergy–Driven Robust Motion Control

VIEW 10 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

MOSAIC for Multiple-Reward Environments

VIEW 9 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Learning and Control Model of the Arm for Loading

VIEW 15 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Reinforcement Learning by Value Gradients

VIEW 5 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Reinforcement Learning in Continuous Time and Space: Interference and Not Ill Conditioning Is the Main Problem When Using Distributed Function Approximators

  • IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics)
  • 2008
VIEW 10 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Reinforcement Learning State Estimator

  • Neural Computation
  • 2007
VIEW 8 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2000
2019

CITATION STATISTICS

  • 82 Highly Influenced Citations

  • Averaged 28 Citations per year over the last 3 years

References

Publications referenced by this paper.
SHOWING 1-10 OF 40 REFERENCES

Advantage updating (Tech

L. C. Baird
  • Rep. No. WL-TR-93-1146). Wright Laboratory,
  • 1993
VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

Neuronlike adaptive elements that can solve difficult learning control problems

  • IEEE Transactions on Systems, Man, and Cybernetics
  • 1983
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL