Verifying Reinforcement Learning up to Infinity.
Edoardo BacciMirco GiacobbeDavid ParkerPublished in: IJCAI (2021)
Keyphrases
- reinforcement learning
- function approximation
- model free
- model checking
- optimal policy
- markov decision processes
- reinforcement learning algorithms
- learning algorithm
- state space
- perceptual aliasing
- control problems
- direct policy search
- machine learning
- policy search
- action selection
- dynamic programming
- partially observable
- function approximators
- reinforcement learning methods
- transition model
- temporal difference
- robotic control