Reward Biased Maximum Likelihood Estimation for Reinforcement Learning.
Akshay MeteRahul SinghP. R. KumarPublished in: CoRR (2020)
Keyphrases
- maximum likelihood estimation
- reinforcement learning
- maximum likelihood
- em algorithm
- function approximation
- parameter estimation
- expectation maximization
- multivariate gaussian
- eligibility traces
- state space
- mixture of gaussians
- probability distribution
- reinforcement learning algorithms
- model free
- optimal policy
- markov decision processes
- reward function
- boltzmann machine
- partially observable environments
- density function
- supervised learning
- unsupervised learning
- learning algorithm
- machine learning
- statistical analysis
- semi supervised
- average reward
- policy gradient
- bayesian networks
- data mining