Coordinated learning in multiagent MDPs with infinite state-space.
Francisco S. MeloM. Isabel RibeiroPublished in: Auton. Agents Multi Agent Syst. (2010)
Keyphrases
- state space
- reinforcement learning
- multi agent
- learning process
- markov decision processes
- learning algorithm
- multiagent learning
- supervised learning
- learning agents
- real time dynamic programming
- stochastic domains
- markov decision problems
- partially observable
- reinforcement learning algorithms
- learning tasks
- multiagent systems
- dynamic programming
- cooperative
- dynamical systems
- action selection
- heuristic search
- learning agent
- online learning
- linear programming
- active learning
- model based reinforcement learning