Intelligent Roundabout Insertion using Deep Reinforcement Learning.
Alessandro Paolo CapassoGiulio BacchianiDaniele MolinariPublished in: ICAART (2) (2020)
Keyphrases
- reinforcement learning
- learning capabilities
- reinforcement learning algorithms
- intelligent systems
- state space
- optimal policy
- function approximation
- robot control
- learning agents
- genetic algorithm
- multi agent
- agent technology
- hidden markov models
- optimal control
- robotic control
- temporal difference
- multi agent reinforcement learning
- policy search
- supervised learning
- markov decision processes
- decision support
- real time
- artificial neural networks
- expert systems
- e learning
- social networks
- search engine
- learning algorithm
- machine learning
- neural network
- data sets