Improving reinforcement learning by using sequence trees.
Sertan GirginFaruk PolatReda AlhajjPublished in: Mach. Learn. (2010)
Keyphrases
- reinforcement learning
- decision trees
- hidden state
- learning process
- tree structure
- function approximation
- robotic control
- tree construction
- model free
- multi agent
- learning algorithm
- machine learning
- neural network
- markov decision processes
- action selection
- reinforcement learning algorithms
- multi agent reinforcement learning
- tree nodes