Combining backpropagation with Equilibrium Propagation to improve an Actor-Critic reinforcement learning framework.
Yoshimasa KuboEric ChalmersArtur LuczakPublished in: Frontiers Comput. Neurosci. (2022)
Keyphrases
- back propagation
- reinforcement learning
- neural network
- actor critic
- learning algorithm
- artificial neural networks
- function approximation
- feedforward neural networks
- hidden layer
- reinforcement learning algorithms
- policy gradient
- artificial intelligence
- machine learning
- learning problems
- model free
- temporal difference
- real time