Supervised and Reinforcement Learning from Observations in Reconnaissance Blind Chess.
Timo BertramJohannes FürnkranzMartin MüllerPublished in: CoG (2022)
Keyphrases
- reinforcement learning
- supervised learning
- learning algorithm
- evaluation function
- semi supervised
- temporal difference
- function approximation
- reinforcement learning algorithms
- artificial intelligence
- unsupervised learning
- machine learning
- state space
- feature selection
- robotic control
- game playing
- learning process
- genetic algorithm
- temporal difference learning
- data sets
- optimal control
- model free
- search and rescue
- computer chess
- game tree search
- markov decision processes
- optimal policy