On the Sample Complexity of Vanilla Model-Based Offline Reinforcement Learning with Dependent Samples.
Mustafa O. KarabagUfuk TopcuPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- model free
- statistically independent
- training samples
- reinforcement learning algorithms
- optimal policy
- optimal control
- real time
- function approximation
- learning algorithm
- data sets
- sample set
- sample points
- sampling methods
- neural network
- machine learning
- markov decision processes
- data driven
- state space
- monte carlo
- markov chain
- supervised learning
- data samples
- training set
- multi agent
- information systems