Systematic Improvement of Monte-Carlo Tree Search with Self-generated Neural-Networks Controllers.
Fan XieZhiqing LiuYu WangWenhao HuangShuo WangPublished in: LION (2010)
Keyphrases
- monte carlo tree search
- neural network
- monte carlo
- tree search algorithm
- evaluation function
- genetic algorithm
- bayesian reinforcement learning
- control system
- fuzzy logic
- markov chain
- fuzzy systems
- decision making
- monte carlo search
- state space
- artificial neural networks
- search algorithm
- control law
- temporal difference
- temporal difference learning
- reinforcement learning