A nonlinear hidden layer enables actor-critic agents to learn multiple paired association navigation.
M. Ganesh KumarCheston TanCamilo LibedinskyShih-Cheng YenAndrew Yong-Yi TanPublished in: CoRR (2021)
Keyphrases
- hidden layer
- multi agent systems
- back propagation
- multi agent
- learning rate
- actor critic
- activation function
- neural network
- feed forward
- decision making
- feed forward neural networks
- multiple agents
- artificial neural networks
- neural nets
- recurrent neural networks
- reinforcement learning
- rbf neural network
- multilayer perceptron
- radial basis function
- feedforward neural networks
- neuro fuzzy
- function approximation
- optimal control
- dynamic environments
- policy gradient