Adaptive Warm-Start MCTS in AlphaZero-like Deep Reinforcement Learning.
Hui WangMike PreussAske PlaatPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- state space
- adaptive control
- learning agent
- dynamic programming
- temporal difference
- function approximation
- adaptive algorithms
- data sets
- deep learning
- reinforcement learning algorithms
- model free
- adaptive learning
- optimal control
- markov chain
- expert systems
- multi agent
- artificial intelligence
- learning algorithm