Towards Multi-Agent Interactive Reinforcement Learning for Opportunistic Software Composition in Ambient Environments.
Kevin DelcourtPublished in: AAMAS (2022)
Keyphrases
- reinforcement learning
- multi agent
- multi agent environments
- graphic user interface
- intelligent environments
- function approximation
- real world
- software tools
- dynamic environments
- search based software testing
- ambient intelligence
- computer graphics
- user friendly
- interactive systems
- source code
- cooperative
- open systems
- learning agents
- reinforcement learning agents
- autonomous agents
- multiagent systems
- multi agent systems
- learning process
- computer systems
- machine learning
- transfer learning
- software development
- user interaction
- software design
- development process
- software architecture
- markov decision processes
- optimal policy
- optimal control
- web service composition
- reinforcement learning algorithms
- intelligent agents
- software systems
- working environment
- case study
- ami systems
- graphical display
- learning algorithm