DeepWiERL: Bringing Deep Reinforcement Learning to the Internet of Self-Adaptive Things.
Francesco RestucciaTommaso MelodiaPublished in: INFOCOM (2020)
Keyphrases
- reinforcement learning
- multi agent
- internet users
- learning algorithm
- function approximation
- dynamic programming
- database
- action selection
- markov decision processes
- robotic control
- multi agent reinforcement learning
- action space
- temporal difference
- model free
- communication technologies
- web technologies
- learning process
- machine learning
- data sets
- real time