Value-Biased Maximum Likelihood Estimation for Model-based Reinforcement Learning in Discounted Linear MDPs.
Yu-Heng HungPing-Chun HsiehAkshay MeteP. R. KumarPublished in: CoRR (2023)
Keyphrases
- model based reinforcement learning
- markov decision processes
- maximum likelihood estimation
- em algorithm
- optimal policy
- maximum likelihood
- finite state
- parameter estimation
- state space
- expectation maximization
- reinforcement learning
- average cost
- dynamic programming
- probability distribution
- policy iteration
- infinite horizon
- partially observable
- average reward
- density function
- markov decision process
- action space
- reward function
- decision processes
- machine learning
- bayesian networks
- image segmentation
- decision problems
- statistical models
- markov random field