Internally Driven Q-learning - Convergence and Generalization Results.
Eduardo AlonsoEsther MondragónNiclas Kjäll-OhlssonPublished in: ICAART (1) (2012)
Keyphrases
- stochastic approximation
- reinforcement learning
- stochastic shortest path
- convergence proof
- function approximation
- data driven
- learning algorithm
- cooperative
- convergence rate
- multi agent
- state space
- dynamic programming
- model free
- learning rate
- faster convergence
- action selection
- optimal policy
- decision trees
- bucket brigade
- learning tasks
- convergence speed
- real time
- monte carlo
- data sets