Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- grammatical inference
- model free
- syntactic pattern recognition
- optimal policy
- markov decision processes
- machine learning
- tree grammars
- partially observable domains
- learning algorithm
- state space
- action selection
- temporal difference
- rl algorithms
- inference process
- control problems
- natural language
- autonomous learning
- transfer learning
- partially observable
- belief networks
- decision theoretic
- learning process
- bayesian networks
- multi agent
- continuous state
- optimal control
- graph grammars
- control policy
- policy iteration
- learning capabilities
- evidential reasoning
- reinforcement learning methods
- function approximators
- previously learned
- grammar rules
- learning classifier systems
- supervised learning
- actor critic
- policy search
- context free grammars