Communications that Emerge through Reinforcement Learning Using a (Recurrent) Neural Network.
Katsunari ShibataPublished in: CoRR (2017)
Keyphrases
- reinforcement learning
- function approximation
- model free
- machine learning
- markov decision processes
- transfer learning
- data sets
- temporal difference
- learning algorithm
- optimal policy
- reinforcement learning algorithms
- communication systems
- state space
- multi agent
- multiple access
- function approximators
- learning agents
- control problems
- continuous state
- robotic control
- direct policy search
- learning problems
- supervised learning
- learning process
- information systems
- genetic algorithm
- information retrieval
- neural network