Reward Biased Maximum Likelihood Estimation for Reinforcement Learning.
Akshay MeteRahul SinghXi LiuP. R. KumarPublished in: L4DC (2021)
Keyphrases
- maximum likelihood estimation
- reinforcement learning
- maximum likelihood
- em algorithm
- parameter estimation
- function approximation
- expectation maximization
- model free
- machine learning
- multivariate gaussian
- state space
- probability distribution
- markov decision processes
- mixture of gaussians
- reinforcement learning algorithms
- optimal policy
- boltzmann machine
- learning algorithm
- reward function
- density function
- average reward
- background subtraction
- eligibility traces
- supervised learning