Training Larger Networks for Deep Reinforcement Learning.
Kei OtaDevesh K. JhaAsako KanezakiPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- training algorithm
- training set
- supervised learning
- markov decision processes
- training process
- training examples
- multi agent
- reinforcement learning algorithms
- function approximation
- state space
- echo state networks
- temporal difference
- deep learning
- recurrent networks
- deep architectures
- test set
- online learning
- mobile robot
- feature selection
- learning algorithm
- machine learning
- network structure
- neural network
- optimal policy
- training phase
- network design
- network size
- social networks