Compositional Reinforcement Learning from Logical Specifications.
Kishor JothimuruganSuguman BansalOsbert BastaniRajeev AlurPublished in: NeurIPS (2021)
Keyphrases
- reinforcement learning
- function approximation
- functional requirements
- reinforcement learning algorithms
- machine learning
- specification language
- state space
- written in natural language
- temporal difference learning
- learning capabilities
- optimal control
- markov decision processes
- optimal policy
- supervised learning
- logical reasoning
- learning algorithm
- logical operations
- model free
- policy search
- multi agent reinforcement learning
- autonomous learning
- reinforcement learning methods
- multi agent
- high level
- genetic algorithm