Bridging the Gap between Reinforcement Learning and Knowledge Representation: A Logical Off- and On-Policy Framework
Emad SaadPublished in: CoRR (2010)
Keyphrases
- reinforcement learning
- knowledge representation
- main contribution
- optimal policy
- theoretical framework
- artificial intelligence
- logical framework
- policy search
- neural network
- sequential decision making
- action selection
- answer set programming
- function approximation
- markov decision processes
- semantic web
- probabilistic model
- learning algorithm