A Tale of Sampling and Estimation in Discounted Reinforcement Learning.
Alberto Maria MetelliMirco MuttiMarcello RestelliPublished in: AISTATS (2023)
Keyphrases
- reinforcement learning
- markov decision processes
- optimal policy
- dynamic programming
- machine learning
- importance sampling
- estimation algorithm
- markov decision process
- accurate estimation
- state space
- robotic control
- data sets
- multi agent
- total reward
- multi agent reinforcement learning
- average reward
- finite horizon
- reinforcement learning algorithms
- infinite horizon
- estimation error
- optimal control
- function approximation
- active learning
- learning algorithm
- temporal difference
- semi parametric
- policy search