What is the Value of an Action in Ice Hockey? Q-Learning for the NHL.
Oliver SchulteZeyu ZhaoKurt RoutleyPublished in: MLSA@PKDD/ECML (2015)
Keyphrases
- action selection
- reinforcement learning
- state action
- state space
- function approximation
- cooperative
- stochastic approximation
- learning rate
- multi agent
- learning algorithm
- reinforcement learning algorithms
- multi agent reinforcement learning
- positional information
- evaluation function
- dynamic programming
- decision making
- neural network
- bucket brigade