Optimistic-Pessimistic Q-Learning Algorithm for Multi-Agent Systems.
Natalia AkchurinaPublished in: MATES (2008)
Keyphrases
- multi agent systems
- learning algorithm
- game theory
- multi agent
- agent architecture
- autonomous agents
- generalization ability
- machine learning
- reinforcement learning
- learning scheme
- machine learning algorithms
- cooperative
- multi agent reinforcement learning
- agent systems
- learning problems
- learning tasks
- intelligent agents
- supervised learning
- training data
- back propagation
- agent platform
- membership queries
- active learning
- learning models
- learning process
- agent technology
- feature space
- sample complexity
- reinforcement learning algorithms
- learning rate
- single agent
- distributed problem solving
- support vector