Adaptive Warm-Start MCTS in AlphaZero-Like Deep Reinforcement Learning.
Hui WangMike PreussAske PlaatPublished in: PRICAI (3) (2021)
Keyphrases
- reinforcement learning
- adaptive algorithms
- learning capabilities
- optimal control
- state space
- real time
- learning algorithm
- image sequences
- function approximation
- learning process
- active learning
- actor critic
- robot control
- optimal policy
- dynamic programming
- multi agent
- search engine
- artificial intelligence
- genetic algorithm
- information retrieval
- machine learning