Provably Safe Reinforcement Learning: A Theoretical and Experimental Comparison.
Hanna KrasowskiJakob ThummMarlon MüllerXiao WangMatthias AlthoffPublished in: CoRR (2022)
Keyphrases
- experimental comparison
- reinforcement learning
- theoretical analysis
- feature selection
- function approximation
- markov decision processes
- learning algorithm
- reinforcement learning algorithms
- optimal policy
- databases
- transition model
- model free
- multi agent
- genetic algorithm
- machine learning
- real time
- hidden markov models
- monte carlo
- evolutionary algorithm
- theoretical basis
- case study
- theoretical issues
- robotic control