Bayesian Curiosity for Efficient Exploration in Reinforcement Learning.
Tom BlauLionel OttFabio RamosPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- bayesian networks
- state space
- multi agent
- dynamic programming
- learning algorithm
- bayesian analysis
- bayesian decision
- machine learning
- learning process
- markov decision processes
- posterior probability
- function approximation
- reinforcement learning algorithms
- model free
- stochastic approximation
- bayesian learning
- posterior distribution
- transfer learning
- autonomous learning
- temporal difference learning
- optimal control
- data sets
- generative model
- maximum likelihood
- supervised learning
- support vector
- neural network