A Novel Update Mechanism for Q-Networks Based On Extreme Learning Machines

@article{Wilson2020ANU,
  title={A Novel Update Mechanism for Q-Networks Based On Extreme Learning Machines},
  author={C. Wilson and A. Riccardi and E. Minisci},
  journal={2020 International Joint Conference on Neural Networks (IJCNN)},
  year={2020},
  pages={1-7}
}
Reinforcement learning is a popular machine learning paradigm which can find near optimal solutions to complex problems. Most often, these procedures involve function approximation using neural networks with gradient based updates to optimise weights for the problem being considered. While this common approach generally works well, there are other update mechanisms which are largely unexplored in reinforcement learning. One such mechanism is Extreme Learning Machines. These were initially… Expand

References

SHOWING 1-10 OF 29 REFERENCES
Extreme learning machine: Theory and applications
  • 8,036
  • Highly Influential
  • PDF
Generalization in Reinforcement Learning: Successful Examples Using Sparse Coarse Coding
  • 1,196
  • PDF
Asynchronous Methods for Deep Reinforcement Learning
  • 4,016
  • PDF
Deep Reinforcement Learning with Double Q-Learning
  • 2,556
  • PDF
Reinforcement Learning: An Introduction
  • 28,283
  • Highly Influential
  • PDF
Evolutionary Algorithms for Reinforcement Learning
  • 350
  • PDF
An incremental extreme learning machine for online sequential learning problems
  • 53
Human-level control through deep reinforcement learning
  • 12,048
  • Highly Influential
  • PDF
...
1
2
3
...