Deep Reinforcement Learning Methods in Match-3 Game.
Ildar KamaldinovIlya MakarovPublished in: AIST (2019)
Keyphrases
- reinforcement learning methods
- monte carlo tree search
- reinforcement learning
- reinforcement learning algorithms
- dynamical systems
- model free
- control problems
- control strategies
- model construction
- supervised learning
- action space
- state space
- monte carlo
- learning strategies
- markov chain
- temporal difference
- cooperative