Speedy Q-Learning.
Mohammad Gheshlaghi AzarRémi MunosMohammad GhavamzadehHilbert J. KappenPublished in: NIPS (2011)
Keyphrases
- reinforcement learning
- function approximation
- cooperative
- multi agent
- state space
- stochastic approximation
- learning algorithm
- temporal difference learning
- action selection
- optimal policy
- model free
- multiagent learning
- data sets
- reinforcement learning algorithms
- stochastic shortest path
- learning rate
- state action
- potential field
- bucket brigade
- learning agent
- evaluation function
- dynamic programming
- multi agent systems
- hierarchical reinforcement learning
- relational reinforcement learning