Efficient Learning from Delayed Rewards Through Symbiotic Evolution

Abstract

This paper presents a new reinforcement learning method called sane (Symbiotic, Adaptive Neuro-Evolution) that evolves a population of neurons through genetic algorithms to form a neural network for a given task. Symbiotic evolution promotes both cooperation and specialization in the population, which results in a fast, efficient genetic search and discourages convergence to suboptimal solutions. In the inverted pendulum problem, sane formed effective networks 9 to 16 times faster in CPU time than the Adaptive Heuristic Critic and 2 times faster than the GENITOR neuro-evolution approach without loss of generalization. Such efficient learning, combined with few domain assumptions, makes SANE a promising approach to a broad range of reinforcement learning problems, including many real-world applications.

Cite

Text

Moriarty and Miikkulainen. "Efficient Learning from Delayed Rewards Through Symbiotic Evolution." International Conference on Machine Learning, 1995. doi:10.1016/B978-1-55860-377-6.50056-6

Markdown

[Moriarty and Miikkulainen. "Efficient Learning from Delayed Rewards Through Symbiotic Evolution." International Conference on Machine Learning, 1995.](https://mlanthology.org/icml/1995/moriarty1995icml-efficient/) doi:10.1016/B978-1-55860-377-6.50056-6

BibTeX

@inproceedings{moriarty1995icml-efficient,
  title     = {{Efficient Learning from Delayed Rewards Through Symbiotic Evolution}},
  author    = {Moriarty, David E. and Miikkulainen, Risto},
  booktitle = {International Conference on Machine Learning},
  year      = {1995},
  pages     = {396-404},
  doi       = {10.1016/B978-1-55860-377-6.50056-6},
  url       = {https://mlanthology.org/icml/1995/moriarty1995icml-efficient/}
}