Parallel reinforcement learning: a framework and case study

@article{Liu2018ParallelRL,
  title={Parallel reinforcement learning: a framework and case study},
  author={Teng Liu and Bin Tian and Yunfeng Ai and Li Li and Dongpu Cao and Fei-yue Wang},
  journal={IEEE/CAA Journal of Automatica Sinica},
  year={2018},
  volume={5},
  pages={827-835}
}
In this paper, a new machine learning framework is developed for complex system control, called parallel reinforcement learning. To overcome data deficiency of current data-driven algorithms, a parallel system is built to improve complex learning system by self-guidance. Based on the Markov chain ( MC ) theory, we combine the transfer learning, predictive learning, deep learning and reinforcement learning to tackle the data and action processes and to express the knowledge. Parallel… CONTINUE READING

References

Publications referenced by this paper.
SHOWING 1-10 OF 29 REFERENCES

Driving Cycle Equivalence and Transformation

  • IEEE Transactions on Vehicular Technology
  • 2017
VIEW 2 EXCERPTS

Parallel learning: a perspective and a framework

  • IEEE/CAA Journal of Automatica Sinica
  • 2017
VIEW 1 EXCERPT

Target-driven visual navigation in indoor scenes using deep reinforcement learning

  • 2017 IEEE International Conference on Robotics and Automation (ICRA)
  • 2017
VIEW 2 EXCERPTS

Similar Papers

Loading similar papers…