Learning through Probing: a decentralized reinforcement learning architecture for social dilemmas.
Nicolas AnastassacosMirco MusolesiPublished in: CoRR (2018)
Keyphrases
- reinforcement learning
- learning process
- learning algorithm
- learning systems
- learning capabilities
- learning problems
- online learning
- temporal difference learning
- supervised learning
- knowledge acquisition
- design principles
- learning tasks
- dynamic programming
- active learning
- partially observable
- reinforcement learning methods
- evolutionary learning
- mobile learning
- function approximation
- software architecture
- transfer learning
- prior knowledge
- cooperative
- decision trees