Reward-based training of recurrent neural networks for cognitive and value-based tasks

@inproceedings{Song2016RewardbasedTO,
  title={Reward-based training of recurrent neural networks for cognitive and value-based tasks},
  author={H. Francis Song and Guangyu Robert Yang and Xiao-Jing Wang},
  year={2016}
}
Trained neural network models, which exhibit many features observed in neural recordings from behaving animals and whose activity and connectivity can be fully analyzed, may provide insights into neural mechanisms. In contrast to commonly used methods for supervised learning from graded error signals, however, animals learn from reward feedback on definite actions through reinforcement learning. Reward maximization is particularly relevant when the optimal behavior depends on an animal's… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 25 CITATIONS

Toward evolutionary and developmental intelligence

  • Current Opinion in Behavioral Sciences
  • 2019
VIEW 1 EXCERPT
CITES BACKGROUND