An online multi-agent co-operative learning algorithm in POMDPs.
Fei LiuGuangzhou ZengPublished in: J. Exp. Theor. Artif. Intell. (2008)
Keyphrases
- multi agent
- reinforcement learning
- learning algorithm
- cooperative
- online learning
- partially observable markov decision processes
- distributed constraint optimization
- single agent
- online algorithms
- partially observable stochastic games
- multi agent systems
- dec pomdps
- supervised learning
- intelligent agents
- data sets
- agent oriented
- training data
- machine learning
- back propagation
- multiagent systems
- autonomous agents
- markov decision processes
- reinforcement learning algorithms
- training samples
- dynamic programming
- real time
- machine learning algorithms
- classification algorithm
- learning tasks
- training examples
- lower bound
- batch mode