Correlation Priors for Reinforcement Learning.
Bastian AltAdrian SosicHeinz KoepplPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- correlation coefficient
- dynamic programming
- function approximation
- learning process
- reinforcement learning algorithms
- prior knowledge
- bayesian framework
- optimal policy
- action space
- machine learning
- neural network
- multi agent reinforcement learning
- markov decision processes
- control policy
- high correlation
- partially observable
- correlation analysis
- temporal difference learning
- prior information
- database
- generative model
- decision trees
- information systems
- data sets
- real time