Training and delayed reinforcements in Q-learning agents.
Pierguido V. C. CaironiMarco DorigoPublished in: Int. J. Intell. Syst. (1997)
Keyphrases
- multi agent
- cooperative
- multi agent systems
- single agent
- action selection
- multiagent systems
- reinforcement learning
- multiple agents
- multiagent learning
- autonomous agents
- software agents
- learning agent
- intelligent agents
- neural network
- function approximation
- training set
- agent receives
- mobile agents
- dynamic environments
- multi agent reinforcement learning
- training process
- learning agents
- interacting agents
- state space
- complex environments
- dynamic programming
- decision making
- learning algorithm
- artificial agents
- temporal difference learning
- resource allocation
- agent architecture
- training examples
- training samples
- supervised learning
- machine learning