Reinforcement Learning for LTLf/LDLf Goals.
Giuseppe De GiacomoLuca IocchiMarco FavoritoFabio PatriziPublished in: CoRR (2018)
Keyphrases
- reinforcement learning
- function approximation
- model free
- machine learning
- multiscale
- state space
- reinforcement learning algorithms
- learning algorithm
- multi agent
- learning process
- dynamic programming
- temporal difference learning
- markov decision processes
- robotic control
- multi agent reinforcement learning
- neural network
- optimal control
- databases
- partially observable
- markov decision process
- learning agents
- optimal policy
- information systems
- policy search
- relational reinforcement learning