Multi-Agent Reinforcement Learning with Vicarious Rewards.
Kevin IrwigWayne WobckePublished in: Electron. Trans. Artif. Intell. (1999)
Keyphrases
- multi agent reinforcement learning
- reinforcement learning
- learning agents
- markov decision processes
- multi agent
- stochastic games
- multi agent learning
- multi agent systems
- distributed control
- optimal policy
- function approximation
- reward function
- cooperative
- model free
- action selection
- reinforcement learning algorithms
- partially observable markov decision processes
- learning automata
- supervised learning
- state space
- mobile robot
- search space
- learning algorithm