Learning automata-based approach to learn dialogue policies in large state space.
Kumaravelan GopalakrishnanSivakumar RamakrishnanPublished in: Int. J. Intell. Inf. Database Syst. (2012)
Keyphrases
- learning automata
- state space
- reinforcement learning
- optimal policy
- pursuit algorithm
- hierarchical reinforcement learning
- reinforcement learning agents
- markov decision process
- learning automaton
- markov decision problems
- markov decision processes
- learning agent
- reward function
- reinforcement learning algorithms
- state variables
- dialogue management
- dynamical systems
- heuristic search
- neural network
- macro actions
- partially observable markov decision processes
- genetic algorithm
- basis functions
- markov chain
- search space
- natural language
- reward signal
- state abstraction
- human machine
- dialogue system
- finite state
- multi agent