An Empirical Relative Value Learning Algorithm for Non-parametric MDPs with Continuous State Space.
Hiteshi SharmaRahul JainAbhishek K. GuptaPublished in: ECC (2019)
Keyphrases
- continuous state spaces
- reinforcement learning
- learning algorithm
- state space
- markov decision processes
- action space
- control problems
- reinforcement learning algorithms
- continuous state
- rl algorithms
- function approximation
- markov decision problems
- model free
- dynamic programming
- markov chain
- partially observable markov decision processes
- optimal policy
- learning tasks
- optimal control
- machine learning algorithms
- machine learning
- active learning
- policy iteration
- markov decision process
- learning problems
- learning agent
- finite state
- learning rate
- training data