Compositionality and Bounds for Optimal Value Functions in Reinforcement Learning.
Jacob AdamczykStas TiomkinRahul V. KulkarniPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- worst case
- optimal control
- dynamic programming
- upper bound
- tight bounds
- learning process
- asymptotically optimal
- lower bound
- optimal solution
- learning algorithm
- machine learning
- data sets
- closed form
- neural network
- lower and upper bounds
- closed form expressions
- optimal design
- upper and lower bounds
- error tolerance
- control policy
- model free
- transfer learning