Emergence of Purposive and Grounded Communication through Reinforcement Learning.
Katsunari ShibataKazuki SasaharaPublished in: ICONIP (3) (2011)
Keyphrases
- reinforcement learning
- function approximation
- communication systems
- human computer
- information sharing
- model free
- reinforcement learning algorithms
- communication networks
- data acquisition
- markov decision processes
- supervised learning
- communication overhead
- information systems
- learning algorithm
- robotic control
- communication protocol
- resource constrained
- distributed control
- temporal difference
- database
- communication technologies
- learning classifier systems
- information exchange
- state space
- mobile devices
- e learning
- genetic algorithm
- machine learning